https://variables.md/ The model market, diffed daily. One-line facts from OpenRouter catalog snapshots. en https://variables.md/changelog/2026-08-30/ https://variables.md/changelog/2026-08-30/ Sun, 30 Aug 2026 10:29:22 GMT - ~deepseek/deepseek-v4-flash-latest: completion price $0.1/M → $0.16/M (+60.0%) - ~z-ai/glm-latest: prompt price $1.2/M → $1.19/M (−1.0%) - ~z-ai/glm-latest: completion price $4/M → $4.18/M (+4.5%) - arcee-ai/trinity-large-thinking: prompt price $0.22/M → $0.25/M (+13.6%) - arcee-ai/trinity-large-thinking: completion price $0.85/M → $0.8/M (−5.9%) - deepseek/deepseek-v4-flash: prompt price $0.084/M → $0.08/M (−4.3%) - deepseek/deepseek-v4-flash: completion price $0.167/M → $0.16/M (−4.3%) - deepseek/deepseek-v4-flash-0731: prompt price $0.045/M → $0.065/M (+44.4%) - deepseek/deepseek-v4-flash-0731: completion price $0.09/M → $0.18/M (+100.0%) - deepseek/deepseek-v4-pro: prompt price $0.63/M → $0.437/M (−30.6%) - deepseek/deepseek-v4-pro: completion price $1.26/M → $0.875/M (−30.6%) - qwen/qwen3-next-80b-a3b-instruct: prompt price $0.1/M → $0.09/M (−10.0%) - thinkingmachines/inkling: prompt price $0.95/M → $1/M (+5.3%) - z-ai/glm-5.1: prompt price $1.26/M → $0.966/M (−23.3%) - z-ai/glm-5.1: completion price $3.96/M → $3.04/M (−23.3%) - OpenInference: deepseek/deepseek-v4-flash-0731 quantization fp4 → fp8 - Relace: z-ai/glm-5.3-flash quantization fp8 → fp4 - Baidu: deepseek/deepseek-v4-flash prompt price $0.084/M → $0.08/M (−4.0%) - Baidu: deepseek/deepseek-v4-flash completion price $0.167/M → $0.16/M (−4.0%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.165/M → $0.17/M (+3.0%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.084/M → $0.08/M (−4.3%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.167/M → $0.16/M (−4.3%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.165/M → $0.17/M (+3.0%) - OpenInference: deepseek/deepseek-v4-flash-0731 completion price $0.1/M → $0.16/M (+60.0%) - Phala: deepseek/deepseek-v4-flash-0731 prompt price $0.22/M → $0.44/M (+100.0%) - Phala: deepseek/deepseek-v4-flash-0731 completion price $0.66/M → $1.32/M (+100.0%) - Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.045/M → $0.065/M (+44.4%) - Relace: deepseek/deepseek-v4-flash-0731 completion price $0.09/M → $0.18/M (+100.0%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.639/M → $0.446/M (−30.2%) - Baidu: deepseek/deepseek-v4-pro completion price $1.28/M → $0.892/M (−30.2%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.63/M → $0.437/M (−30.6%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.26/M → $0.875/M (−30.6%) - Mancer 2: openai/gpt-oss-120b prompt price $0.085/M → $0.07/M (−17.6%) - Reka: qwen/qwen3.8-27b prompt price $0.45/M → $0.25/M (−44.4%) - Reka: qwen/qwen3.8-27b completion price $3.2/M → $3/M (−6.2%) - Mancer 2: z-ai/glm-4.7 prompt price $0.65/M → $0.7/M (+7.7%) - Io Net: z-ai/glm-5.3 prompt price $1.25/M → $1.19/M (−5.0%) - Io Net: z-ai/glm-5.3 completion price $4.4/M → $4.18/M (−5.0%) - Morph: z-ai/glm-5.3 prompt price $1.4/M → $1.25/M (−10.7%) - Morph: z-ai/glm-5.3-flash completion price $0.5/M → $0.42/M (−16.0%) - Relace: z-ai/glm-5.3-flash prompt price $0.075/M → $0.05/M (−33.3%) - Relace: z-ai/glm-5.3-flash completion price $0.25/M → $0.167/M (−33.3%) - OpenAI now serves openai/gpt-5.6-luna (unknown, 1,050,000 ctx, $0.4/M in / $2.4/M out) - OpenAI now serves openai/gpt-5.6-luna-pro (unknown, 1,050,000 ctx, $0.4/M in / $2.4/M out) - Darkbloom now serves qwen/qwen3-vl-30b-a3b-instruct (fp4, 131,072 ctx, $0.09/M in / $0.4/M out) - OpenInference no longer serves google/gemma-4-31b-it (was bf16) - Fireworks no longer serves minimax/minimax-m2.7 (was unknown) - Fireworks no longer serves moonshotai/kimi-k2.7-code (was unknown) - OpenAI no longer serves openai/gpt-5.6-luna (was unknown) - OpenAI no longer serves openai/gpt-5.6-luna-pro (was unknown) - Makora no longer serves z-ai/glm-5.3-flash (was unknown) https://variables.md/changelog/2026-08-29/ https://variables.md/changelog/2026-08-29/ Sat, 29 Aug 2026 11:39:57 GMT - DeepSeek: DeepSeek V4 Flash 0731 (batch) (deepseek/deepseek-v4-flash-0731:batch) added to the catalog: 1,048,576 ctx, $0.14/M in / $0.28/M out - DeepSeek: DeepSeek V4 Pro 0813 (batch) (deepseek/deepseek-v4-pro-0813:batch) added to the catalog: 1,048,576 ctx, $1.32/M in / $3.96/M out - Google: Gemma 4 31B (batch) (google/gemma-4-31b-it:batch) added to the catalog: 262,144 ctx, $0.39/M in / $0.97/M out - Meta: Muse Glimmer 30B (batch) (meta/muse-glimmer-30b:batch) added to the catalog: 131,072 ctx, $0.35/M in / $1.5/M out - MoonshotAI: Kimi K3 (batch) (moonshotai/kimi-k3:batch) added to the catalog: 1,048,576 ctx, $3/M in / $15/M out - OpenAI: gpt-oss-120b (batch) (openai/gpt-oss-120b:batch) added to the catalog: 131,072 ctx, $0.15/M in / $0.6/M out - OpenAI: gpt-oss-20b (batch) (openai/gpt-oss-20b:batch) added to the catalog: 131,072 ctx, $0.05/M in / $0.2/M out - Qwen: Qwen3.5-9B (batch) (qwen/qwen3.5-9b:batch) added to the catalog: 262,144 ctx, $0.17/M in / $0.25/M out - Thinking Machines: Inkling Small (batch) (thinkingmachines/inkling-small:batch) added to the catalog: 524,288 ctx, $0.5/M in / $1.2/M out - Z.ai: GLM 5.3 Flash (batch) (z-ai/glm-5.3-flash:batch) added to the catalog: 1,048,575 ctx, $0.15/M in / $0.5/M out - AllenAI: Olmo 3 32B Think (allenai/olmo-3-32b-think) removed from the catalog - Arcee AI: Virtuoso Large (arcee-ai/virtuoso-large) removed from the catalog - ~google/gemini-flash-latest: prompt price $0.375/M → $0.75/M (+100.0%) - ~google/gemini-flash-latest: completion price $1.88/M → $3.75/M (+100.0%) - ~z-ai/glm-latest: prompt price $1.25/M → $1.2/M (−4.0%) - ~z-ai/glm-latest: completion price $4.4/M → $4/M (−9.1%) - deepseek/deepseek-v4-flash: prompt price $0.087/M → $0.084/M (−3.5%) - deepseek/deepseek-v4-flash: completion price $0.174/M → $0.167/M (−3.5%) - deepseek/deepseek-v4-flash-0731: prompt price $0.06/M → $0.045/M (−25.0%) - deepseek/deepseek-v4-flash-0731: completion price $0.12/M → $0.09/M (−25.0%) - deepseek/deepseek-v4-pro: prompt price $0.762/M → $0.63/M (−17.3%) - deepseek/deepseek-v4-pro: completion price $1.52/M → $1.26/M (−17.3%) - google/gemini-3.7-flash: prompt price $0.375/M → $0.75/M (+100.0%) - google/gemini-3.7-flash: completion price $1.88/M → $3.75/M (+100.0%) - meta/muse-glimmer-30b: prompt price $0.35/M → $0.3/M (−14.3%) - meta/muse-glimmer-30b: completion price $1.5/M → $1.2/M (−20.0%) - nvidia/nemotron-3.5-lightning: prompt price $0.1/M → $0.08/M (−20.0%) - nvidia/nemotron-3.5-lightning: completion price $0.25/M → $0.2/M (−20.0%) - qwen/qwen3-vl-30b-a3b-instruct: prompt price $0.13/M → $0.15/M (+15.4%) - qwen/qwen3-vl-30b-a3b-instruct: completion price $0.52/M → $0.6/M (+15.4%) - qwen/qwen3.8-2.4t-a95b:batch: prompt price $2/M → $2.5/M (+25.0%) - qwen/qwen3.8-2.4t-a95b:batch: completion price $6/M → $6.25/M (+4.2%) - tencent/hy3: prompt price $0.083/M → $0.132/M (+60.0%) - tencent/hy3: completion price $0.33/M → $0.528/M (+60.0%) - Modal: qwen/qwen3.8-2.4t-a95b quantization nvfp4 → unknown - DeepInfra: z-ai/glm-5.3 quantization bf16 → fp8 - DigitalOcean: deepseek/deepseek-v3.2 prompt price $0.5/M → $0.25/M (−50.0%) - DigitalOcean: deepseek/deepseek-v3.2 completion price $1.6/M → $0.8/M (−50.0%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.087/M → $0.084/M (−3.9%) - Baidu: deepseek/deepseek-v4-flash completion price $0.174/M → $0.167/M (−3.9%) - DigitalOcean: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.068/M (−51.5%) - DigitalOcean: deepseek/deepseek-v4-flash completion price $0.28/M → $0.168/M (−40.0%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.16/M → $0.165/M (+3.1%) - Mancer 2: deepseek/deepseek-v4-flash completion price $0.45/M → $0.5/M (+11.1%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.087/M → $0.084/M (−3.5%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.174/M → $0.167/M (−3.5%) - Alibaba: deepseek/deepseek-v4-flash-0731 prompt price $0.176/M → $0.352/M (+100.0%) - Alibaba: deepseek/deepseek-v4-flash-0731 completion price $0.528/M → $1.06/M (+100.0%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.07/M → $0.045/M (−35.7%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.14/M → $0.09/M (−35.7%) - DigitalOcean: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.08/M (−42.9%) - DigitalOcean: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.252/M (−10.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.112/M → $0.352/M (+214.3%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.224/M → $1.06/M (+371.4%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.16/M → $0.165/M (+3.1%) - Mancer 2: deepseek/deepseek-v4-flash-0731 completion price $0.45/M → $0.5/M (+11.1%) - Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.06/M → $0.045/M (−25.0%) - Relace: deepseek/deepseek-v4-flash-0731 completion price $0.12/M → $0.09/M (−25.0%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.771/M → $0.639/M (−17.1%) - Baidu: deepseek/deepseek-v4-pro completion price $1.54/M → $1.28/M (−17.1%) - DigitalOcean: deepseek/deepseek-v4-pro prompt price $1.74/M → $0.87/M (−50.0%) - DigitalOcean: deepseek/deepseek-v4-pro completion price $3.48/M → $1.74/M (−50.0%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.792/M → $1.04/M (+31.8%) - GMICloud: deepseek/deepseek-v4-pro completion price $2.38/M → $2.09/M (−12.1%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.762/M → $0.63/M (−17.3%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.52/M → $1.26/M (−17.3%) - Alibaba: deepseek/deepseek-v4-pro-0813 prompt price $0.581/M → $1.12/M (+93.2%) - Alibaba: deepseek/deepseek-v4-pro-0813 completion price $1.74/M → $3.37/M (+93.2%) - StreamLake: deepseek/deepseek-v4-pro-0813 prompt price $0.579/M → $1.12/M (+93.4%) - StreamLake: deepseek/deepseek-v4-pro-0813 completion price $1.74/M → $3.36/M (+93.4%) - Google: google/gemini-3.7-flash prompt price $0.375/M → $0.75/M (+100.0%) - Google: google/gemini-3.7-flash completion price $1.88/M → $3.75/M (+100.0%) - Google: google/gemini-3.7-flash prompt price $0.188/M → $0.375/M (+100.0%) - Google: google/gemini-3.7-flash completion price $0.938/M → $1.88/M (+100.0%) - Google: google/gemini-3.7-flash prompt price $0.675/M → $1.35/M (+100.0%) - Google: google/gemini-3.7-flash completion price $3.38/M → $6.75/M (+100.0%) - OpenInference: google/gemma-4-31b-it prompt price $0.08/M → $0.07/M (−12.5%) - DigitalOcean: meta-llama/llama-4-maverick prompt price $0.25/M → $0.2/M (−20.0%) - DigitalOcean: meta-llama/llama-4-maverick completion price $0.87/M → $0.696/M (−20.0%) - DigitalOcean: moonshotai/kimi-k3 prompt price $3/M → $2.85/M (−5.0%) - DigitalOcean: moonshotai/kimi-k3 completion price $15/M → $14.3/M (−5.0%) - DigitalOcean: openai/gpt-oss-120b prompt price $0.1/M → $0.055/M (−45.0%) - DigitalOcean: openai/gpt-oss-120b completion price $0.7/M → $0.385/M (−45.0%) - AkashML: qwen/qwen3.8-27b prompt price $0.4/M → $0.35/M (−12.5%) - Parasail: qwen/qwen3.8-27b prompt price $0.45/M → $0.35/M (−22.2%) - Tencent: tencent/hy3 prompt price $0.083/M → $0.132/M (+60.0%) - Tencent: tencent/hy3 completion price $0.33/M → $0.528/M (+60.0%) - DigitalOcean: xiaomi/mimo-v2.5-pro prompt price $0.8/M → $0.4/M (−50.0%) - DigitalOcean: xiaomi/mimo-v2.5-pro completion price $3/M → $1.5/M (−50.0%) - Baidu: z-ai/glm-5.2 prompt price $0.419/M → $0.372/M (−11.0%) - Baidu: z-ai/glm-5.2 completion price $1.32/M → $1.17/M (−11.0%) - DigitalOcean: z-ai/glm-5.2 prompt price $1.4/M → $0.7/M (−50.0%) - DigitalOcean: z-ai/glm-5.2 completion price $4.4/M → $2.2/M (−50.0%) - Novita: z-ai/glm-5.2 prompt price $0.742/M → $0.342/M (−54.0%) - Novita: z-ai/glm-5.2 completion price $2.33/M → $1.07/M (−54.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.42/M → $0.328/M (−22.0%) - StreamLake: z-ai/glm-5.2 completion price $1.32/M → $1.03/M (−22.0%) - DeepInfra: z-ai/glm-5.3 prompt price $1.4/M → $1.2/M (−14.3%) - DeepInfra: z-ai/glm-5.3 completion price $4.4/M → $4/M (−9.1%) - DeepInfra: z-ai/glm-5.3-flash prompt price $0.15/M → $0.075/M (−50.0%) - DeepInfra: z-ai/glm-5.3-flash completion price $0.5/M → $0.25/M (−50.0%) - SambaNova: google/gemma-4-31b-it context length 262,144 → 131,072 - Sail Research now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.065/M in / $0.18/M out) - CoreWeave now serves deepseek/deepseek-v4-pro-0813 (fp8, 1,048,576 ctx, $1.31/M in / $3.96/M out) - Sail Research now serves deepseek/deepseek-v4-pro-0813 (fp4, 1,048,576 ctx, $1.32/M in / $3.96/M out) - AkashML now serves z-ai/glm-5.3 (fp8, 1,048,576 ctx, $1.3/M in / $4.4/M out) - AtlasCloud now serves z-ai/glm-5.3 (fp8, 262,144 ctx, $1.4/M in / $4.4/M out) - DigitalOcean now serves z-ai/glm-5.3 (unknown, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Modal now serves z-ai/glm-5.3 (unknown, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Morph now serves z-ai/glm-5.3 (fp4, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Novita now serves z-ai/glm-5.3 (fp8, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Parasail now serves z-ai/glm-5.3 (fp8, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Together now serves z-ai/glm-5.3 (unknown, 1,048,575 ctx, $1.4/M in / $4.4/M out) - Fireworks now serves z-ai/glm-5.3-flash (unknown, 1,048,576 ctx, $0.15/M in / $0.5/M out) - Makora now serves z-ai/glm-5.3-flash (unknown, 1,048,576 ctx, $0.14/M in / $0.47/M out) - Relace now serves z-ai/glm-5.3-flash (fp8, 1,048,576 ctx, $0.075/M in / $0.25/M out) - SiliconFlow now serves z-ai/glm-5.3-flash (fp8, 1,048,576 ctx, $0.15/M in / $0.5/M out) - Cloudflare no longer serves z-ai/glm-5.2 (was unknown) - Morph no longer serves z-ai/glm-5.2 (was fp4) https://variables.md/changelog/2026-08-28/ https://variables.md/changelog/2026-08-28/ Fri, 28 Aug 2026 17:27:01 GMT - Mistral: Codestral 2508 (batch) (mistralai/codestral-2508:batch) added to the catalog: 256,000 ctx, $0.3/M in / $0.9/M out - Mistral: Ministral 3 8B 2512 (batch) (mistralai/ministral-8b-2512:batch) added to the catalog: 262,144 ctx, $0.15/M in / $0.15/M out - Mistral: Mistral Large 3 2512 (batch) (mistralai/mistral-large-2512:batch) added to the catalog: 262,144 ctx, $0.5/M in / $1.5/M out - Mistral: Mistral Medium 3.5 (batch) (mistralai/mistral-medium-3-5:batch) added to the catalog: 262,144 ctx, $0.75/M in / $3.75/M out - Mistral: Mistral Medium 3.1 (batch) (mistralai/mistral-medium-3.1:batch) added to the catalog: 131,072 ctx, $0.4/M in / $2/M out - Mistral: Mistral Small 4 (batch) (mistralai/mistral-small-2603:batch) added to the catalog: 262,144 ctx, $0.15/M in / $0.6/M out - Qwen: Qwen3.8 2.4T A95B (batch) (qwen/qwen3.8-2.4t-a95b:batch) added to the catalog: 1,010,000 ctx, $2/M in / $6/M out - Tencent: Hy4 preview (tencent/hy4-preview) added to the catalog: 1,048,576 ctx, $0.834/M in / $2.5/M out - Mistral: Ministral 8B (mistralai/ministral-8b) removed from the catalog - MoonshotAI: Kimi K2.7 Code (batch) (moonshotai/kimi-k2.7-code:batch) removed from the catalog - OpenAI: GPT-3.5 Turbo (batch) (openai/gpt-3.5-turbo:batch) removed from the catalog - OpenAI: GPT-4 Turbo (batch) (openai/gpt-4-turbo:batch) removed from the catalog - OpenAI: GPT-4.1 Mini (batch) (openai/gpt-4.1-mini:batch) removed from the catalog - OpenAI: GPT-4.1 Nano (batch) (openai/gpt-4.1-nano:batch) removed from the catalog - OpenAI: GPT-4.1 (batch) (openai/gpt-4.1:batch) removed from the catalog - OpenAI: GPT-4o-mini (batch) (openai/gpt-4o-mini:batch) removed from the catalog - OpenAI: GPT-4o (batch) (openai/gpt-4o:batch) removed from the catalog - OpenAI: GPT-5 Codex (batch) (openai/gpt-5-codex:batch) removed from the catalog - OpenAI: GPT-5 Mini (batch) (openai/gpt-5-mini:batch) removed from the catalog - OpenAI: GPT-5 Nano (batch) (openai/gpt-5-nano:batch) removed from the catalog - OpenAI: GPT-5 Pro (batch) (openai/gpt-5-pro:batch) removed from the catalog - OpenAI: GPT-5 (batch) (openai/gpt-5:batch) removed from the catalog - OpenAI: GPT-5.1 (batch) (openai/gpt-5.1:batch) removed from the catalog - OpenAI: GPT-5.2 Pro (batch) (openai/gpt-5.2-pro:batch) removed from the catalog - OpenAI: GPT-5.2 (batch) (openai/gpt-5.2:batch) removed from the catalog - OpenAI: GPT-5.4 Mini (batch) (openai/gpt-5.4-mini:batch) removed from the catalog - OpenAI: GPT-5.4 Nano (batch) (openai/gpt-5.4-nano:batch) removed from the catalog - OpenAI: GPT-5.4 Pro (batch) (openai/gpt-5.4-pro:batch) removed from the catalog - OpenAI: GPT-5.4 (batch) (openai/gpt-5.4:batch) removed from the catalog - OpenAI: GPT-5.5 Pro (batch) (openai/gpt-5.5-pro:batch) removed from the catalog - OpenAI: GPT-5.5 (batch) (openai/gpt-5.5:batch) removed from the catalog - OpenAI: GPT-5.6 Luna Pro (batch) (openai/gpt-5.6-luna-pro:batch) removed from the catalog - OpenAI: GPT-5.6 Luna (batch) (openai/gpt-5.6-luna:batch) removed from the catalog - OpenAI: GPT-5.6 Sol Pro (batch) (openai/gpt-5.6-sol-pro:batch) removed from the catalog - OpenAI: GPT-5.6 Sol (batch) (openai/gpt-5.6-sol:batch) removed from the catalog - OpenAI: GPT-5.6 Terra Pro (batch) (openai/gpt-5.6-terra-pro:batch) removed from the catalog - OpenAI: GPT-5.6 Terra (batch) (openai/gpt-5.6-terra:batch) removed from the catalog - OpenAI: o1-pro (batch) (openai/o1-pro:batch) removed from the catalog - OpenAI: o1 (batch) (openai/o1:batch) removed from the catalog - OpenAI: o3 Mini High (batch) (openai/o3-mini-high:batch) removed from the catalog - OpenAI: o3 Mini (batch) (openai/o3-mini:batch) removed from the catalog - OpenAI: o3 Pro (batch) (openai/o3-pro:batch) removed from the catalog - OpenAI: o3 (batch) (openai/o3:batch) removed from the catalog - OpenAI: o4 Mini High (batch) (openai/o4-mini-high:batch) removed from the catalog - OpenAI: o4 Mini (batch) (openai/o4-mini:batch) removed from the catalog - TheDrummer: Rocinante 12B (thedrummer/rocinante-12b) removed from the catalog - ~z-ai/glm-latest: prompt price $1.4/M → $1.25/M (−10.7%) - deepseek/deepseek-v3.2: prompt price $0.26/M → $0.269/M (+3.5%) - deepseek/deepseek-v3.2: completion price $0.38/M → $0.4/M (+5.3%) - deepseek/deepseek-v4-flash: prompt price $0.078/M → $0.087/M (+11.3%) - deepseek/deepseek-v4-flash: completion price $0.156/M → $0.174/M (+11.3%) - deepseek/deepseek-v4-pro: prompt price $0.87/M → $0.762/M (−12.4%) - deepseek/deepseek-v4-pro: completion price $1.74/M → $1.52/M (−12.4%) - deepseek/deepseek-v4-pro-0813: prompt price $1.12/M → $0.66/M (−41.2%) - deepseek/deepseek-v4-pro-0813: completion price $3.37/M → $1.98/M (−41.2%) - nvidia/nemotron-3-ultra-550b-a55b: prompt price $0.6/M → $0.5/M (−16.7%) - nvidia/nemotron-3-ultra-550b-a55b: completion price $3.6/M → $2.2/M (−38.9%) - nvidia/nemotron-3.5-lightning: prompt price $0.08/M → $0.1/M (+25.0%) - nvidia/nemotron-3.5-lightning: completion price $0.2/M → $0.25/M (+25.0%) - qwen/qwen3.5-122b-a10b: prompt price $0.26/M → $0.29/M (+11.5%) - qwen/qwen3.5-122b-a10b: completion price $2.08/M → $2.4/M (+15.4%) - ~z-ai/glm-latest: context length 1,048,576 → 1,310,720 - google/gemma-3-27b-it: context length 262,144 → 131,072 - kwaipilot/kat-coder-pro-v2.5: context length 256,000 → 262,144 - mistralai/voxtral-small-24b-2507: context length 32,000 → 32,768 - nvidia/nemotron-3-ultra-550b-a55b: context length 512,288 → 262,144 - z-ai/glm-5.3: context length 1,048,576 → 1,310,720 - AkashML: qwen/qwen3.8-27b quantization bf16 → fp8 - DigitalOcean: deepseek/deepseek-v3.2 prompt price $0.25/M → $0.5/M (+100.0%) - DigitalOcean: deepseek/deepseek-v3.2 completion price $0.8/M → $1.6/M (+100.0%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.079/M → $0.087/M (+9.5%) - Baidu: deepseek/deepseek-v4-flash completion price $0.159/M → $0.174/M (+9.5%) - DigitalOcean: deepseek/deepseek-v4-flash prompt price $0.068/M → $0.14/M (+106.2%) - DigitalOcean: deepseek/deepseek-v4-flash completion price $0.168/M → $0.28/M (+66.7%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.15/M → $0.16/M (+6.7%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.078/M → $0.087/M (+11.3%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.156/M → $0.174/M (+11.3%) - AkashML: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.1/M (−28.6%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.06/M → $0.07/M (+16.6%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.12/M → $0.14/M (+16.6%) - DigitalOcean: deepseek/deepseek-v4-flash-0731 prompt price $0.08/M → $0.14/M (+75.0%) - DigitalOcean: deepseek/deepseek-v4-flash-0731 completion price $0.252/M → $0.28/M (+11.1%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.15/M → $0.16/M (+6.7%) - Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.05/M → $0.06/M (+20.0%) - Relace: deepseek/deepseek-v4-flash-0731 completion price $0.1/M → $0.12/M (+20.0%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.22/M → $0.088/M (−60.0%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.66/M → $0.264/M (−60.0%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.791/M → $0.771/M (−2.6%) - Baidu: deepseek/deepseek-v4-pro completion price $1.58/M → $1.54/M (−2.6%) - DigitalOcean: deepseek/deepseek-v4-pro prompt price $0.87/M → $1.74/M (+100.0%) - DigitalOcean: deepseek/deepseek-v4-pro completion price $1.74/M → $3.48/M (+100.0%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.87/M → $0.762/M (−12.4%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.74/M → $1.52/M (−12.4%) - StreamLake: deepseek/deepseek-v4-pro-0813 prompt price $0.66/M → $0.579/M (−12.2%) - StreamLake: deepseek/deepseek-v4-pro-0813 completion price $1.98/M → $1.74/M (−12.2%) - DigitalOcean: meta-llama/llama-4-maverick prompt price $0.2/M → $0.25/M (+25.0%) - DigitalOcean: meta-llama/llama-4-maverick completion price $0.696/M → $0.87/M (+25.0%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.548/M → $0.529/M (−3.5%) - Baidu: moonshotai/kimi-k2.6 completion price $2.31/M → $2.23/M (−3.5%) - Decart: moonshotai/kimi-k2.6 prompt price $0.548/M → $0.537/M (−2.0%) - Decart: moonshotai/kimi-k2.6 completion price $2.31/M → $2.26/M (−2.0%) - Inceptron: moonshotai/kimi-k2.6 prompt price $0.54/M → $0.53/M (−1.9%) - DigitalOcean: moonshotai/kimi-k3 prompt price $2.85/M → $3/M (+5.3%) - DigitalOcean: moonshotai/kimi-k3 completion price $14.3/M → $15/M (+5.3%) - Amazon Bedrock: openai/gpt-5.6-sol prompt price $5.5/M → $4.4/M (−20.0%) - Amazon Bedrock: openai/gpt-5.6-sol completion price $33/M → $22/M (−33.3%) - DigitalOcean: openai/gpt-oss-120b prompt price $0.055/M → $0.1/M (+81.8%) - DigitalOcean: openai/gpt-oss-120b completion price $0.385/M → $0.7/M (+81.8%) - Mancer 2: openai/gpt-oss-120b prompt price $0.08/M → $0.085/M (+6.2%) - Darkbloom: qwen/qwen3.6-35b-a3b prompt price $0.07/M → $0.05/M (−28.6%) - DigitalOcean: xiaomi/mimo-v2.5-pro prompt price $0.4/M → $0.8/M (+100.0%) - DigitalOcean: xiaomi/mimo-v2.5-pro completion price $1.5/M → $3/M (+100.0%) - DeepInfra: z-ai/glm-5.2 prompt price $0.75/M → $0.487/M (−35.0%) - DeepInfra: z-ai/glm-5.2 completion price $2.4/M → $1.56/M (−35.0%) - DigitalOcean: z-ai/glm-5.2 prompt price $0.7/M → $1.4/M (+100.0%) - DigitalOcean: z-ai/glm-5.2 completion price $2.2/M → $4.4/M (+100.0%) - Inceptron: z-ai/glm-5.2 prompt price $0.75/M → $0.71/M (−5.3%) - Inceptron: z-ai/glm-5.2 completion price $2.4/M → $2.35/M (−2.1%) - NextBit now serves deepseek/deepseek-v4-flash (fp8, 1,048,576 ctx, $0.14/M in / $0.28/M out) - OpenInference now serves google/gemma-4-31b-it (bf16, 262,144 ctx, $0.08/M in / $0.35/M out) - AtlasCloud now serves kwaipilot/kat-coder-pro-v2.5 (fp8, 262,144 ctx, $0.74/M in / $2.96/M out) - Mistral now serves mistralai/voxtral-small-24b-2507 (unknown, 32,768 ctx, $0.1/M in / $0.3/M out) - Mistral now serves mistralai/voxtral-small-24b-2507 (unknown, 32,000 ctx, $0.11/M in / $0.33/M out) - Sail Research now serves moonshotai/kimi-k3 (fp4, 974,842 ctx, $2.6/M in / $13/M out) - Novita now serves qwen/qwen3.8-2.4t-a95b (unknown, 1,000,000 ctx, $2/M in / $6/M out) - Novita now serves qwen/qwen3.8-27b (unknown, 1,000,000 ctx, $0.42/M in / $3/M out) - BaseTen now serves z-ai/glm-5.3 (fp4, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Cloudflare now serves z-ai/glm-5.3 (unknown, 1,310,720 ctx, $1.4/M in / $4.4/M out) - DeepInfra now serves z-ai/glm-5.3 (bf16, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Fireworks now serves z-ai/glm-5.3 (unknown, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Friendli now serves z-ai/glm-5.3 (unknown, 1,048,576 ctx, $1.4/M in / $4.4/M out) - GMICloud now serves z-ai/glm-5.3 (fp8, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Io Net now serves z-ai/glm-5.3 (fp8, 262,144 ctx, $1.25/M in / $4.4/M out) - DigitalOcean now serves z-ai/glm-5.3-flash (unknown, 1,048,576 ctx, $0.15/M in / $0.5/M out) - Friendli now serves z-ai/glm-5.3-flash (unknown, 1,048,576 ctx, $0.15/M in / $0.5/M out) - Morph now serves z-ai/glm-5.3-flash (fp8, 1,048,576 ctx, $0.15/M in / $0.5/M out) - Phala now serves z-ai/glm-5.3-flash (fp8, 1,048,576 ctx, $0.15/M in / $0.5/M out) - Wafer now serves z-ai/glm-5.3-flash (unknown, 1,048,576 ctx, $0.15/M in / $0.5/M out) - Together no longer serves deepseek/deepseek-v4-pro (was unknown) - Phala no longer serves google/gemma-3-27b-it (was unknown) - Novita no longer serves inclusionai/ling-3.0-flash (was unknown) - Together no longer serves minimax/minimax-m3 (was unknown) - Mistral no longer serves mistralai/mistral-small-2603 (was unknown) - Together no longer serves nvidia/nemotron-3-ultra-550b-a55b (was unknown) - Morph no longer serves qwen/qwen3.5-397b-a17b (was fp4) - Morph no longer serves qwen/qwen3.6-27b (was fp4) - Morph no longer serves qwen/qwen3.8-27b (was fp4) - AkashML no longer serves z-ai/glm-5.2 (was fp8) - Makora no longer serves z-ai/glm-5.2 (was fp8) - Wafer no longer serves z-ai/glm-5.2 (was fp4) https://variables.md/changelog/2026-08-27/ https://variables.md/changelog/2026-08-27/ Thu, 27 Aug 2026 16:31:15 GMT - Ling 3.0 Flash Fin (free) (inclusionai/ling-3.0-flash-fin:free) added to the catalog: 262,144 ctx, $0/M in / $0/M out - Qwen: Qwen3.8 Flash (qwen/qwen3.8-flash) added to the catalog: 1,000,000 ctx, $0.15/M in / $0.47/M out - Z.ai: GLM 5.3 Flash (z-ai/glm-5.3-flash) added to the catalog: 1,310,720 ctx, $0.075/M in / $0.25/M out - Ox Alpha (stealth/ox-alpha) removed from the catalog - Z.ai: GLM 5.2 (batch) (z-ai/glm-5.2:batch) removed from the catalog - ~deepseek/deepseek-v4-flash-latest: completion price $0.075/M → $0.1/M (+33.3%) - deepseek/deepseek-v4-flash: prompt price $0.089/M → $0.078/M (−12.0%) - deepseek/deepseek-v4-flash: completion price $0.177/M → $0.156/M (−12.0%) - moonshotai/kimi-k2.7-code: prompt price $0.67/M → $0.66/M (−1.5%) - qwen/qwen3-235b-a22b-2507: prompt price $0.09/M → $0.087/M (−2.8%) - qwen/qwen3-235b-a22b-2507: completion price $0.55/M → $0.35/M (−36.4%) - qwen/qwen3.6-35b-a3b: prompt price $0.14/M → $0.1/M (−28.6%) - qwen/qwen3.6-35b-a3b: completion price $1/M → $0.9/M (−10.0%) - tencent/hy3: prompt price $0.132/M → $0.083/M (−37.5%) - tencent/hy3: completion price $0.528/M → $0.33/M (−37.5%) - z-ai/glm-4.6: prompt price $0.5/M → $0.43/M (−14.0%) - z-ai/glm-4.6: completion price $2/M → $1.75/M (−12.5%) - DeepInfra: xiaomi/mimo-v2.5 quantization bf16 → fp8 - Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.079/M (−43.3%) - Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.159/M (−43.3%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.15/M (+7.1%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.089/M → $0.078/M (−12.0%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.177/M → $0.156/M (−12.0%) - Alibaba: deepseek/deepseek-v4-flash-0731 prompt price $0.352/M → $0.176/M (−50.0%) - Alibaba: deepseek/deepseek-v4-flash-0731 completion price $1.06/M → $0.528/M (−50.0%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.06/M (−57.2%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.12/M (−57.2%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.155/M → $0.15/M (−3.2%) - Morph: deepseek/deepseek-v4-flash-0731 prompt price $0.079/M → $0.099/M (+25.0%) - OpenInference: deepseek/deepseek-v4-flash-0731 completion price $0.075/M → $0.1/M (+33.3%) - Phala: deepseek/deepseek-v4-flash-0731 prompt price $0.2/M → $0.22/M (+10.0%) - Phala: deepseek/deepseek-v4-flash-0731 completion price $0.4/M → $0.66/M (+65.0%) - Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.06/M → $0.05/M (−16.7%) - Relace: deepseek/deepseek-v4-flash-0731 completion price $0.12/M → $0.1/M (−16.7%) - SiliconFlow: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.22/M (+57.1%) - SiliconFlow: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.66/M (+135.7%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.247/M → $0.22/M (−10.9%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.741/M → $0.66/M (−10.9%) - Baidu: deepseek/deepseek-v4-pro prompt price $1.69/M → $0.791/M (−53.2%) - Baidu: deepseek/deepseek-v4-pro completion price $3.38/M → $1.58/M (−53.2%) - Alibaba: deepseek/deepseek-v4-pro-0813 prompt price $1.12/M → $0.581/M (−48.2%) - Alibaba: deepseek/deepseek-v4-pro-0813 completion price $3.37/M → $1.74/M (−48.2%) - StreamLake: deepseek/deepseek-v4-pro-0813 prompt price $1.32/M → $0.66/M (−50.0%) - StreamLake: deepseek/deepseek-v4-pro-0813 completion price $3.96/M → $1.98/M (−50.0%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.95/M → $0.548/M (−42.3%) - Baidu: moonshotai/kimi-k2.6 completion price $4/M → $2.31/M (−42.3%) - Decart: moonshotai/kimi-k2.6 prompt price $0.568/M → $0.548/M (−3.5%) - Decart: moonshotai/kimi-k2.6 completion price $3.33/M → $2.31/M (−30.7%) - Inceptron: moonshotai/kimi-k2.6 prompt price $0.57/M → $0.54/M (−5.3%) - Inceptron: moonshotai/kimi-k2.7-code prompt price $0.67/M → $0.66/M (−1.5%) - Mancer 2: openai/gpt-oss-120b prompt price $0.085/M → $0.08/M (−5.9%) - AkashML: qwen/qwen3.6-35b-a3b prompt price $0.14/M → $0.1/M (−28.6%) - AkashML: qwen/qwen3.6-35b-a3b completion price $1/M → $0.9/M (−10.0%) - Baidu: tencent/hy3 prompt price $0.132/M → $0.132/M (−0.1%) - Baidu: tencent/hy3 completion price $0.528/M → $0.527/M (−0.1%) - Tencent: tencent/hy3 prompt price $0.132/M → $0.083/M (−37.5%) - Tencent: tencent/hy3 completion price $0.528/M → $0.33/M (−37.5%) - DeepInfra: xiaomi/mimo-v2.5 prompt price $0.4/M → $0.13/M (−67.5%) - DeepInfra: xiaomi/mimo-v2.5 completion price $2/M → $0.65/M (−67.5%) - Baidu: z-ai/glm-5.1 prompt price $1.4/M → $0.909/M (−35.1%) - Baidu: z-ai/glm-5.1 completion price $4.4/M → $2.86/M (−35.1%) - Baidu: z-ai/glm-5.2 prompt price $1.4/M → $0.419/M (−70.1%) - Baidu: z-ai/glm-5.2 completion price $4.4/M → $1.32/M (−70.1%) - StreamLake: z-ai/glm-5.2 prompt price $0.735/M → $0.42/M (−42.9%) - StreamLake: z-ai/glm-5.2 completion price $2.31/M → $1.32/M (−42.9%) - SambaNova: google/gemma-4-31b-it context length 131,072 → 262,144 - CoreWeave: meta-llama/llama-3.1-70b-instruct context length 128,000 → 131,072 - CoreWeave: meta-llama/llama-3.1-8b-instruct context length 128,000 → 131,072 - CoreWeave: z-ai/glm-5.2 context length 262,144 → 1,048,576 - NextBit now serves deepseek/deepseek-v4-flash-0731 (fp8, 1,048,576 ctx, $0.44/M in / $1.32/M out) - NextBit now serves deepseek/deepseek-v4-pro (fp8, 1,048,576 ctx, $1.72/M in / $3.45/M out) - Google now serves google/gemini-3.1-flash-lite (unknown, 1,048,576 ctx, $0.275/M in / $1.65/M out) - Google now serves google/gemini-3.5-flash-lite (unknown, 1,048,576 ctx, $0.33/M in / $2.75/M out) - Mistral now serves mistralai/mistral-large (unknown, 128,000 ctx, $2/M in / $6/M out) - Mistral now serves mistralai/mistral-large (unknown, 128,000 ctx, $2.2/M in / $6.6/M out) - Mistral now serves mistralai/mistral-large-2407 (unknown, 131,072 ctx, $2.2/M in / $6.6/M out) - Mistral now serves mistralai/mistral-saba (unknown, 32,768 ctx, $0.22/M in / $0.66/M out) - Mistral now serves mistralai/mixtral-8x22b-instruct (unknown, 65,536 ctx, $2.2/M in / $6.6/M out) - Fireworks now serves moonshotai/kimi-k2.7-code (unknown, 262,144 ctx, $1.9/M in / $8/M out) - Parasail now serves moonshotai/kimi-k3 (fp4, 1,048,576 ctx, $3/M in / $15/M out) - Darkbloom now serves qwen/qwen3.5-35b-a3b (fp4, 262,144 ctx, $0.08/M in / $0.75/M out) - Morph now serves qwen/qwen3.5-397b-a17b (fp4, 262,144 ctx, $0.5/M in / $3.5/M out) - Morph now serves qwen/qwen3.6-27b (fp4, 131,072 ctx, $0.289/M in / $2.4/M out) - Morph now serves qwen/qwen3.8-27b (fp4, 131,072 ctx, $0.289/M in / $2.4/M out) - StreamLake now serves xiaomi/mimo-v2.5 (unknown, 1,000,000 ctx, $0.168/M in / $0.336/M out) - AkashML now serves z-ai/glm-5.2 (fp8, 1,048,576 ctx, $0.77/M in / $2.42/M out) - Sail Research no longer serves deepseek/deepseek-v4-flash (was fp4) - Io Net no longer serves deepseek/deepseek-v4-flash-0731 (was fp8) - Sail Research no longer serves deepseek/deepseek-v4-pro-0813 (was fp4) - Morph no longer serves minimax/minimax-m3 (was fp4) - Sail Research no longer serves moonshotai/kimi-k3 (was fp4) - Nebius no longer serves qwen/qwen3-next-80b-a3b-thinking (was fp8) - Io Net no longer serves z-ai/glm-5.2 (was fp4) https://variables.md/changelog/2026-08-26/ https://variables.md/changelog/2026-08-26/ Wed, 26 Aug 2026 05:50:35 GMT - MiniMax: MiniMax M3 (free) (minimax/minimax-m3:free) added to the catalog: 1,048,576 ctx, $0/M in / $0/M out - Google: Gemma 3n 4B (google/gemma-3n-e4b-it) removed from the catalog - Qwen: Qwen Plus 0728 (thinking) (qwen/qwen-plus-2025-07-28:thinking) removed from the catalog - ~deepseek/deepseek-v4-flash-latest: prompt price $0.035/M → $0.03/M (−14.3%) - ~moonshotai/kimi-latest: prompt price $2.8/M → $2.55/M (−8.9%) - ~moonshotai/kimi-latest: completion price $14/M → $12.8/M (−8.9%) - deepseek/deepseek-v4-flash-0731: prompt price $0.14/M → $0.06/M (−57.1%) - deepseek/deepseek-v4-flash-0731: completion price $0.28/M → $0.12/M (−57.1%) - deepseek/deepseek-v4-pro: prompt price $0.79/M → $0.87/M (+10.1%) - deepseek/deepseek-v4-pro: completion price $1.58/M → $1.74/M (+10.1%) - google/gemma-4-31b-it: prompt price $0.1/M → $0.09/M (−10.0%) - meta-llama/llama-3.3-70b-instruct: prompt price $0.1/M → $0.71/M (+610.0%) - meta-llama/llama-3.3-70b-instruct: completion price $0.32/M → $0.71/M (+121.9%) - meta-llama/llama-4-scout: prompt price $0.1/M → $0.11/M (+10.0%) - meta-llama/llama-4-scout: completion price $0.3/M → $0.34/M (+13.3%) - qwen/qwen2.5-vl-72b-instruct: prompt price $0.8/M → $0.25/M (−68.8%) - qwen/qwen2.5-vl-72b-instruct: completion price $1/M → $0.75/M (−25.0%) - qwen/qwen3.5-397b-a17b: prompt price $0.5/M → $0.39/M (−22.0%) - qwen/qwen3.5-397b-a17b: completion price $3.6/M → $2.34/M (−35.0%) - qwen/qwen3.6-27b: prompt price $0.32/M → $0.6/M (+87.5%) - qwen/qwen3.6-27b: completion price $3.2/M → $3.6/M (+12.5%) - qwen/qwen3.8-27b: prompt price $0.4/M → $0.425/M (+6.3%) - qwen/qwen3.8-27b: completion price $3/M → $2.55/M (−15.0%) - meta-llama/llama-guard-4-12b: context length 1,048,576 → 163,840 - GMICloud: deepseek/deepseek-v4-flash-0731 quantization fp4 → fp8 - Io Net: z-ai/glm-5.2 quantization fp8 → fp4 - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.15/M → $0.155/M (+3.3%) - OpenInference: deepseek/deepseek-v4-flash-0731 prompt price $0.035/M → $0.03/M (−14.3%) - Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.04/M → $0.06/M (+50.0%) - Relace: deepseek/deepseek-v4-flash-0731 completion price $0.08/M → $0.12/M (+50.0%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.088/M → $0.247/M (+180.7%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.064/M → $0.741/M (+1057.9%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.79/M → $0.87/M (+10.1%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.58/M → $1.74/M (+10.1%) - Decart: moonshotai/kimi-k2.6 prompt price $0.587/M → $0.568/M (−3.1%) - Decart: moonshotai/kimi-k2.6 completion price $2.47/M → $3.33/M (+34.9%) - Inceptron: moonshotai/kimi-k2.6 completion price $3.41/M → $3.39/M (−0.6%) - AkashML: openai/gpt-oss-120b prompt price $0.037/M → $0.03/M (−18.9%) - AkashML: openai/gpt-oss-120b completion price $0.49/M → $0.17/M (−65.3%) - AkashML: qwen/qwen3.8-27b completion price $3/M → $2.55/M (−15.0%) - DeepInfra: xiaomi/mimo-v2.5-pro prompt price $1/M → $0.39/M (−61.0%) - DeepInfra: xiaomi/mimo-v2.5-pro completion price $3/M → $1.17/M (−61.0%) - Inceptron: z-ai/glm-5.2 completion price $2.9/M → $2.4/M (−17.2%) - Io Net: z-ai/glm-5.2 prompt price $1.26/M → $0.68/M (−46.0%) - Io Net: z-ai/glm-5.2 completion price $4.4/M → $3.3/M (−25.0%) - Novita: z-ai/glm-5.2 prompt price $0.7/M → $0.742/M (+6.0%) - Novita: z-ai/glm-5.2 completion price $2.2/M → $2.33/M (+6.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.693/M → $0.735/M (+6.1%) - StreamLake: z-ai/glm-5.2 completion price $2.18/M → $2.31/M (+6.1%) - AkashML: deepseek/deepseek-v4-flash-0731 context length 131,072 → 1,048,576 - GMICloud: deepseek/deepseek-v4-flash-0731 context length 1,048,576 → 1,048,575 - Makora now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,000,000 ctx, $0.09/M in / $0.195/M out) - Makora now serves moonshotai/kimi-k3 (unknown, 1,048,576 ctx, $2.55/M in / $12.8/M out) - Sail Research now serves moonshotai/kimi-k3 (fp4, 974,842 ctx, $2.6/M in / $13/M out) - OpenAI now serves openai/gpt-5.1 (unknown, 400,000 ctx, $0.625/M in / $5/M out) - OpenAI now serves openai/gpt-5.1 (unknown, 400,000 ctx, $1.25/M in / $10/M out) - OpenAI now serves openai/gpt-5.1 (unknown, 400,000 ctx, $2.5/M in / $20/M out) - OpenAI now serves openai/gpt-5.4 (unknown, 1,050,000 ctx, $5/M in / $30/M out) - OpenAI now serves openai/gpt-5.4-mini (unknown, 400,000 ctx, $1.5/M in / $9/M out) - Darkbloom now serves openai/gpt-oss-20b (fp8, 131,072 ctx, $0.02/M in / $0.1/M out) - Upstage now serves upstage/solar-pro4 (unknown, 524,288 ctx, $0.03/M in / $0.12/M out) - Amazon Bedrock now serves x-ai/grok-4.6 (unknown, 500,000 ctx, $2.2/M in / $6.6/M out) - Makora now serves z-ai/glm-5.2 (fp4, 980,000 ctx, $0.72/M in / $2.38/M out) - Makora now serves z-ai/glm-5.2 (fp8, 1,048,576 ctx, $0.94/M in / $2.8/M out) - OpenInference no longer serves google/gemma-4-31b-it (was bf16) - Together no longer serves meta-llama/llama-guard-4-12b (was unknown) - OpenAI no longer serves openai/gpt-5.1 (was unknown) - OpenAI no longer serves openai/gpt-5.1 (was unknown) - OpenAI no longer serves openai/gpt-5.1 (was unknown) - OpenAI no longer serves openai/gpt-5.4 (was unknown) - OpenAI no longer serves openai/gpt-5.4-mini (was unknown) https://variables.md/changelog/2026-08-25/ https://variables.md/changelog/2026-08-25/ Tue, 25 Aug 2026 05:47:50 GMT - MiniMax: MiniMax M2.7 (free) (minimax/minimax-m2.7:free) added to the catalog: 196,608 ctx, $0/M in / $0/M out - Mistral: Devstral 2 2512 (mistralai/devstral-2512) added to the catalog: 262,144 ctx, $0.44/M in / $2.2/M out - inclusionAI: Ling-2.6-1T (inclusionai/ling-2.6-1t) removed from the catalog - inclusionAI: Ling-2.6-flash (inclusionai/ling-2.6-flash) removed from the catalog - inclusionAI: Ring-2.6-1T (inclusionai/ring-2.6-1t) removed from the catalog - NVIDIA: Nemotron 3 Nano 30B A3B (free) (nvidia/nemotron-3-nano-30b-a3b:free) removed from the catalog - NVIDIA: Nemotron Nano 12B 2 VL (free) (nvidia/nemotron-nano-12b-v2-vl:free) removed from the catalog - NVIDIA: Nemotron Nano 9B V2 (free) (nvidia/nemotron-nano-9b-v2:free) removed from the catalog - ~deepseek/deepseek-v4-flash-latest: prompt price $0.04/M → $0.035/M (−12.5%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.08/M → $0.075/M (−6.3%) - ~moonshotai/kimi-latest: prompt price $2.6/M → $2.8/M (+7.7%) - ~moonshotai/kimi-latest: completion price $13/M → $14/M (+7.7%) - deepseek/deepseek-v4-flash: prompt price $0.057/M → $0.089/M (+54.4%) - deepseek/deepseek-v4-flash: completion price $0.115/M → $0.177/M (+54.4%) - deepseek/deepseek-v4-pro: prompt price $0.526/M → $0.79/M (+50.2%) - deepseek/deepseek-v4-pro: completion price $1.05/M → $1.58/M (+50.2%) - minimax/minimax-m2.7: prompt price $0.24/M → $0.3/M (+25.0%) - minimax/minimax-m2.7: completion price $0.96/M → $1.2/M (+25.0%) - moonshotai/kimi-k2.5: prompt price $0.45/M → $0.6/M (+33.3%) - moonshotai/kimi-k2.5: completion price $2.25/M → $3/M (+33.3%) - thinkingmachines/inkling: prompt price $1/M → $0.95/M (−5.0%) - z-ai/glm-5.1: prompt price $0.966/M → $1.26/M (+30.4%) - z-ai/glm-5.1: completion price $3.04/M → $3.96/M (+30.4%) - z-ai/glm-5.2: prompt price $0.966/M → $1.19/M (+23.2%) - z-ai/glm-5.2: completion price $3.04/M → $3.74/M (+23.2%) - qwen/qwen3-235b-a22b-thinking-2507: context length 262,144 → 131,072 - thinkingmachines/inkling-small:free: context length 262,144 → 1,048,576 - thinkingmachines/inkling:free: context length 262,144 → 1,048,576 - GMICloud: deepseek/deepseek-v4-flash-0731 quantization fp8 → fp4 - CoreWeave: google/gemma-4-31b-it quantization bf16 → fp4 - GMICloud: deepseek/deepseek-v4-flash prompt price $0.059/M → $0.112/M (+90.5%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.118/M → $0.224/M (+90.5%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.057/M → $0.089/M (+54.4%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.115/M → $0.177/M (+54.4%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.067/M → $0.112/M (+66.7%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.134/M → $0.224/M (+66.7%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.15/M (+7.1%) - OpenInference: deepseek/deepseek-v4-flash-0731 prompt price $0.04/M → $0.035/M (−12.5%) - OpenInference: deepseek/deepseek-v4-flash-0731 completion price $0.13/M → $0.075/M (−42.3%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.207/M → $0.088/M (−57.4%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.15/M → $0.064/M (−57.4%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.528/M → $0.792/M (+50.0%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.58/M → $2.38/M (+50.0%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.526/M → $0.79/M (+50.2%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.05/M → $1.58/M (+50.2%) - Alibaba: deepseek/deepseek-v4-pro-0813 prompt price $1.16/M → $1.12/M (−3.4%) - Alibaba: deepseek/deepseek-v4-pro-0813 completion price $3.48/M → $3.37/M (−3.4%) - GMICloud: minimax/minimax-m2.7 prompt price $0.24/M → $0.3/M (+25.0%) - GMICloud: minimax/minimax-m2.7 completion price $0.96/M → $1.2/M (+25.0%) - GMICloud: minimax/minimax-m3 prompt price $0.24/M → $0.6/M (+150.0%) - GMICloud: minimax/minimax-m3 completion price $0.96/M → $2.4/M (+150.0%) - Mistral: mistralai/mistral-small-2603 prompt price $0.165/M → $0.15/M (−9.1%) - Mistral: mistralai/mistral-small-2603 completion price $0.66/M → $0.6/M (−9.1%) - Inceptron: moonshotai/kimi-k2.6 prompt price $0.6/M → $0.57/M (−5.0%) - Alibaba: qwen/qwen3.8-27b prompt price $0.5/M → $0.425/M (−15.0%) - Alibaba: qwen/qwen3.8-27b completion price $3/M → $2.55/M (−15.0%) - Mancer 2: z-ai/glm-4.7 prompt price $0.6/M → $0.65/M (+8.3%) - GMICloud: z-ai/glm-5.2 prompt price $1.4/M → $1.05/M (−25.0%) - GMICloud: z-ai/glm-5.2 completion price $4.4/M → $3.3/M (−25.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 context length 1,048,575 → 1,048,576 - Mistral now serves mistralai/codestral-2508 (unknown, 256,000 ctx, $0.33/M in / $0.99/M out) - Mistral now serves mistralai/ministral-14b-2512 (unknown, 262,144 ctx, $0.2/M in / $0.2/M out) - Mistral now serves mistralai/ministral-14b-2512 (unknown, 262,144 ctx, $0.22/M in / $0.22/M out) - Mistral now serves mistralai/ministral-3b-2512 (unknown, 131,072 ctx, $0.1/M in / $0.1/M out) - Mistral now serves mistralai/ministral-3b-2512 (unknown, 131,072 ctx, $0.11/M in / $0.11/M out) - Mistral now serves mistralai/ministral-8b (unknown, 128,000 ctx, $0.11/M in / $0.11/M out) - Mistral now serves mistralai/ministral-8b-2512 (unknown, 262,144 ctx, $0.15/M in / $0.15/M out) - Mistral now serves mistralai/ministral-8b-2512 (unknown, 262,144 ctx, $0.165/M in / $0.165/M out) - Mistral now serves mistralai/mistral-large-2512 (unknown, 262,144 ctx, $0.5/M in / $1.5/M out) - Mistral now serves mistralai/mistral-large-2512 (unknown, 262,144 ctx, $0.55/M in / $1.65/M out) - Mistral now serves mistralai/mistral-medium-3 (unknown, 131,072 ctx, $0.4/M in / $2/M out) - Mistral now serves mistralai/mistral-medium-3 (unknown, 131,072 ctx, $0.44/M in / $2.2/M out) - Mistral now serves mistralai/mistral-medium-3-5 (unknown, 262,144 ctx, $1.5/M in / $7.5/M out) - Mistral now serves mistralai/mistral-medium-3-5 (unknown, 262,144 ctx, $1.65/M in / $8.25/M out) - Mistral now serves mistralai/mistral-medium-3.1 (unknown, 131,072 ctx, $0.4/M in / $2/M out) - Mistral now serves mistralai/mistral-medium-3.1 (unknown, 131,072 ctx, $0.44/M in / $2.2/M out) - Mistral now serves mistralai/mistral-nemo (unknown, 131,072 ctx, $0.165/M in / $0.165/M out) - Mistral now serves mistralai/mistral-small-2603 (unknown, 262,144 ctx, $0.165/M in / $0.66/M out) - Mistral now serves mistralai/mistral-small-2603 (unknown, 262,144 ctx, $0.165/M in / $0.66/M out) - Mistral now serves mistralai/mistral-small-3.2-24b-instruct (unknown, 131,072 ctx, $0.11/M in / $0.33/M out) - GMICloud now serves moonshotai/kimi-k2.6 (fp8, 262,144 ctx, $0.855/M in / $3.6/M out) - Fireworks now serves moonshotai/kimi-k3 (unknown, 1,048,576 ctx, $4.5/M in / $22.5/M out) - Nebius now serves nvidia/nemotron-3-nano-30b-a3b (fp8, 262,144 ctx, $0.06/M in / $0.24/M out) - OpenAI now serves openai/gpt-5.2 (unknown, 400,000 ctx, $3.5/M in / $28/M out) - OpenAI now serves openai/gpt-5.3-codex (unknown, 400,000 ctx, $3.5/M in / $28/M out) - OpenAI now serves openai/gpt-5.5 (unknown, 1,050,000 ctx, $12.5/M in / $75/M out) - Cloudflare now serves qwen/qwen3.8-27b (unknown, 262,144 ctx, $0.45/M in / $3.2/M out) - Phala now serves qwen/qwen3.8-27b (unknown, 262,144 ctx, $0.4/M in / $3/M out) - Io Net now serves z-ai/glm-5.2 (fp8, 262,144 ctx, $1.26/M in / $4.4/M out) - Mistral now serves z-ai/glm-5.2 (unknown, 1,048,576 ctx, $1.4/M in / $4.4/M out) - Mistral now serves z-ai/glm-5.2 (unknown, 1,048,576 ctx, $1.54/M in / $4.84/M out) - Decart no longer serves deepseek/deepseek-v4-flash-0731 (was fp4) - Sail Research no longer serves deepseek/deepseek-v4-flash-0731 (was fp4) - Mistral no longer serves mistralai/ministral-8b (was unknown) - Sail Research no longer serves moonshotai/kimi-k3 (was fp4) - Wafer no longer serves moonshotai/kimi-k3 (was unknown) - OpenAI no longer serves openai/gpt-5.2 (was unknown) - OpenAI no longer serves openai/gpt-5.3-codex (was unknown) - OpenAI no longer serves openai/gpt-5.5 (was unknown) - Together no longer serves qwen/qwen-2.5-7b-instruct (was unknown) - DeepInfra no longer serves qwen/qwen3-235b-a22b-thinking-2507 (was fp8) https://variables.md/changelog/2026-08-24/ https://variables.md/changelog/2026-08-24/ Mon, 24 Aug 2026 05:53:58 GMT - ~deepseek/deepseek-v4-flash-latest: prompt price $0.055/M → $0.04/M (−27.3%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.14/M → $0.08/M (−42.9%) - deepseek/deepseek-v4-flash: prompt price $0.053/M → $0.057/M (+8.2%) - deepseek/deepseek-v4-flash: completion price $0.106/M → $0.115/M (+8.2%) - deepseek/deepseek-v4-flash-0731: prompt price $0.08/M → $0.14/M (+75.0%) - deepseek/deepseek-v4-flash-0731: completion price $0.18/M → $0.28/M (+55.6%) - deepseek/deepseek-v4-pro: prompt price $0.397/M → $0.526/M (+32.6%) - deepseek/deepseek-v4-pro: completion price $0.794/M → $1.05/M (+32.6%) - minimax/minimax-m2.7: prompt price $0.3/M → $0.24/M (−20.0%) - minimax/minimax-m2.7: completion price $1.2/M → $0.96/M (−20.0%) - qwen/qwen3.5-397b-a17b: prompt price $0.39/M → $0.5/M (+28.2%) - qwen/qwen3.5-397b-a17b: completion price $2.34/M → $3.6/M (+53.8%) - qwen/qwen3.6-27b: prompt price $0.6/M → $0.32/M (−46.7%) - qwen/qwen3.6-27b: completion price $3.6/M → $3.2/M (−11.1%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.053/M → $0.14/M (+163.2%) - Baidu: deepseek/deepseek-v4-flash completion price $0.106/M → $0.28/M (+163.2%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.145/M → $0.14/M (−3.4%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.053/M → $0.057/M (+8.2%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.106/M → $0.115/M (+8.2%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.066/M → $0.14/M (+112.8%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.132/M → $0.28/M (+112.8%) - Io Net: deepseek/deepseek-v4-flash-0731 prompt price $0.249/M → $0.219/M (−12.0%) - Io Net: deepseek/deepseek-v4-flash-0731 completion price $0.69/M → $0.49/M (−29.0%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.145/M → $0.14/M (−3.4%) - Morph: deepseek/deepseek-v4-flash-0731 prompt price $0.12/M → $0.079/M (−34.2%) - OpenInference: deepseek/deepseek-v4-flash-0731 prompt price $0.05/M → $0.04/M (−20.0%) - Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.07/M → $0.04/M (−42.9%) - Relace: deepseek/deepseek-v4-flash-0731 completion price $0.14/M → $0.08/M (−42.9%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.066/M → $0.207/M (+215.0%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.131/M → $0.15/M (+14.5%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.406/M → $1.69/M (+316.7%) - Baidu: deepseek/deepseek-v4-pro completion price $0.811/M → $3.38/M (+316.7%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.397/M → $0.526/M (+32.6%) - StreamLake: deepseek/deepseek-v4-pro completion price $0.794/M → $1.05/M (+32.6%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.541/M → $0.95/M (+75.4%) - Baidu: moonshotai/kimi-k2.6 completion price $2.28/M → $4/M (+75.4%) - Decart: moonshotai/kimi-k2.6 prompt price $0.549/M → $0.587/M (+6.8%) - Decart: moonshotai/kimi-k2.6 completion price $2.31/M → $2.47/M (+6.8%) - Chutes: qwen/qwen3.8-27b prompt price $0.4/M → $0.35/M (−12.5%) - Chutes: qwen/qwen3.8-27b completion price $3/M → $2.75/M (−8.3%) - Baidu: tencent/hy3 prompt price $0.125/M → $0.132/M (+5.3%) - Baidu: tencent/hy3 completion price $0.502/M → $0.528/M (+5.3%) - Baidu: z-ai/glm-5.1 prompt price $0.896/M → $1.4/M (+56.3%) - Baidu: z-ai/glm-5.1 completion price $2.82/M → $4.4/M (+56.3%) - Baidu: z-ai/glm-5.2 prompt price $0.35/M → $1.4/M (+300.0%) - Baidu: z-ai/glm-5.2 completion price $1.1/M → $4.4/M (+300.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.336/M → $0.693/M (+106.3%) - StreamLake: z-ai/glm-5.2 completion price $1.06/M → $2.18/M (+106.3%) - OpenInference: deepseek/deepseek-v4-flash-0731 context length 262,144 → 1,048,576 - Reka now serves z-ai/glm-5.2 (fp8, 262,144 ctx, $1.1/M in / $3.75/M out) https://variables.md/changelog/2026-08-23/ https://variables.md/changelog/2026-08-23/ Sun, 23 Aug 2026 05:45:37 GMT - Tencent: Hy-MT2-7B (tencent/hy-mt2-7b) added to the catalog: 8,192 ctx, $0.074/M in / $0.295/M out - ~deepseek/deepseek-v4-flash-latest: prompt price $0.065/M → $0.055/M (−15.4%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.18/M → $0.14/M (−22.2%) - deepseek/deepseek-v4-flash: prompt price $0.074/M → $0.053/M (−28.4%) - deepseek/deepseek-v4-flash: completion price $0.148/M → $0.106/M (−28.4%) - deepseek/deepseek-v4-pro: prompt price $0.481/M → $0.397/M (−17.6%) - deepseek/deepseek-v4-pro: completion price $0.963/M → $0.794/M (−17.6%) - deepseek/deepseek-v4-pro-0813: prompt price $1.19/M → $1.12/M (−5.6%) - deepseek/deepseek-v4-pro-0813: completion price $3.56/M → $3.37/M (−5.6%) - meta/muse-glimmer-30b: prompt price $0.3/M → $0.35/M (+16.7%) - meta/muse-glimmer-30b: completion price $1.1/M → $1.5/M (+36.4%) - moonshotai/kimi-k2.6: prompt price $0.541/M → $0.95/M (+75.4%) - moonshotai/kimi-k2.6: completion price $2.28/M → $4/M (+75.4%) - openai/gpt-oss-120b: prompt price $0.03/M → $0.037/M (+23.3%) - qwen/qwen3-30b-a3b: prompt price $0.13/M → $0.12/M (−7.7%) - qwen/qwen3-30b-a3b: completion price $0.52/M → $0.5/M (−3.8%) - qwen/qwen3.8-27b: prompt price $0.45/M → $0.4/M (−11.1%) - qwen/qwen3.8-27b: completion price $3.2/M → $3/M (−6.2%) - thinkingmachines/inkling: prompt price $0.95/M → $1/M (+5.3%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.074/M → $0.053/M (−28.3%) - Baidu: deepseek/deepseek-v4-flash completion price $0.148/M → $0.106/M (−28.3%) - GMICloud: deepseek/deepseek-v4-flash prompt price $0.084/M → $0.059/M (−30.0%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.168/M → $0.118/M (−30.0%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.145/M (+3.6%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.074/M → $0.053/M (−28.4%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.148/M → $0.106/M (−28.4%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.069/M → $0.066/M (−4.1%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.137/M → $0.132/M (−4.1%) - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.068/M → $0.064/M (−5.3%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.135/M → $0.128/M (−5.3%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.084/M → $0.067/M (−20.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.168/M → $0.134/M (−20.0%) - Io Net: deepseek/deepseek-v4-flash-0731 prompt price $0.229/M → $0.249/M (+8.7%) - Io Net: deepseek/deepseek-v4-flash-0731 completion price $0.59/M → $0.69/M (+16.9%) - Novita: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.44/M (+214.3%) - Novita: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $1.32/M (+371.4%) - OpenInference: deepseek/deepseek-v4-flash-0731 prompt price $0.065/M → $0.05/M (−23.1%) - OpenInference: deepseek/deepseek-v4-flash-0731 completion price $0.18/M → $0.13/M (−27.8%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.068/M → $0.066/M (−4.1%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.137/M → $0.131/M (−4.1%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.49/M → $0.406/M (−17.2%) - Baidu: deepseek/deepseek-v4-pro completion price $0.98/M → $0.811/M (−17.2%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.792/M → $0.528/M (−33.3%) - GMICloud: deepseek/deepseek-v4-pro completion price $2.38/M → $1.58/M (−33.3%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.481/M → $0.397/M (−17.6%) - StreamLake: deepseek/deepseek-v4-pro completion price $0.963/M → $0.794/M (−17.6%) - GMICloud: deepseek/deepseek-v4-pro-0813 prompt price $1.19/M → $1.12/M (−5.6%) - GMICloud: deepseek/deepseek-v4-pro-0813 completion price $3.56/M → $3.37/M (−5.6%) - Darkbloom: google/gemma-4-26b-a4b-it prompt price $0.05/M → $0.042/M (−16.0%) - Darkbloom: google/gemma-4-26b-a4b-it completion price $0.25/M → $0.22/M (−12.0%) - GMICloud: qwen/qwen3-235b-a22b-2507 prompt price $0.35/M → $0.087/M (−75.0%) - GMICloud: qwen/qwen3-235b-a22b-2507 completion price $1.4/M → $0.35/M (−75.0%) - Darkbloom: qwen/qwen3.6-35b-a3b prompt price $0.08/M → $0.07/M (−12.5%) - Darkbloom: qwen/qwen3.6-35b-a3b completion price $0.75/M → $0.7/M (−6.7%) - AkashML: qwen/qwen3.8-27b prompt price $0.45/M → $0.4/M (−11.1%) - AkashML: qwen/qwen3.8-27b completion price $3.2/M → $3/M (−6.2%) - Alibaba: qwen/qwen3.8-27b prompt price $0.575/M → $0.5/M (−13.0%) - Alibaba: qwen/qwen3.8-27b completion price $3.45/M → $3/M (−13.0%) - GMICloud: z-ai/glm-5.2 prompt price $0.742/M → $1.4/M (+88.7%) - GMICloud: z-ai/glm-5.2 completion price $2.33/M → $4.4/M (+88.7%) - Novita: z-ai/glm-5.2 prompt price $0.741/M → $0.7/M (−5.5%) - Novita: z-ai/glm-5.2 completion price $2.33/M → $2.2/M (−5.5%) - DeepInfra now serves deepseek/deepseek-v4-pro-0813 (fp8, 1,048,576 ctx, $1.3/M in / $2.6/M out) - Nebius no longer serves deepseek/deepseek-v4-flash-0731 (was fp8) https://variables.md/changelog/2026-08-22/ https://variables.md/changelog/2026-08-22/ Sat, 22 Aug 2026 05:42:56 GMT - DeepSeek: DeepSeek V4 Flash Vision Exp (deepseek/deepseek-v4-flash-vision-exp) added to the catalog: 1,048,576 ctx, $0.22/M in / $0.66/M out - Meta: Muse Spark 1.2 Contributor (meta/muse-spark-1.2-contributor) added to the catalog: 1,048,576 ctx, $0.1/M in / $0.2/M out - Thinking Machines: Inkling Small (free) (thinkingmachines/inkling-small:free) added to the catalog: 262,144 ctx, $0/M in / $0/M out - Thinking Machines: Inkling (free) (thinkingmachines/inkling:free) added to the catalog: 262,144 ctx, $0/M in / $0/M out - Deep Cogito: Cogito v2.1 671B (deepcogito/cogito-v2.1-671b) removed from the catalog - OpenAI: gpt-oss-20b (free) (openai/gpt-oss-20b:free) removed from the catalog - ~deepseek/deepseek-v4-flash-latest: completion price $0.14/M → $0.18/M (+28.6%) - ~openai/gpt-latest: prompt price $2.5/M → $2/M (−20.0%) - ~openai/gpt-latest: completion price $15/M → $10/M (−33.3%) - deepseek/deepseek-chat-v3.1: prompt price $0.25/M → $0.55/M (+120.0%) - deepseek/deepseek-chat-v3.1: completion price $0.95/M → $1.65/M (+73.7%) - deepseek/deepseek-v3.2: prompt price $0.269/M → $0.26/M (−3.3%) - deepseek/deepseek-v3.2: completion price $0.4/M → $0.38/M (−5.0%) - deepseek/deepseek-v4-flash: prompt price $0.083/M → $0.074/M (−10.3%) - deepseek/deepseek-v4-flash: completion price $0.165/M → $0.148/M (−10.3%) - deepseek/deepseek-v4-flash-0731: prompt price $0.14/M → $0.08/M (−42.9%) - deepseek/deepseek-v4-flash-0731: completion price $0.28/M → $0.18/M (−35.7%) - deepseek/deepseek-v4-pro: prompt price $1.6/M → $0.481/M (−69.9%) - deepseek/deepseek-v4-pro: completion price $3.2/M → $0.963/M (−69.9%) - minimax/minimax-m2.5: completion price $0.95/M → $1.08/M (+13.7%) - mistralai/mistral-small-3.2-24b-instruct: prompt price $0.094/M → $0.075/M (−20.0%) - mistralai/mistral-small-3.2-24b-instruct: completion price $0.25/M → $0.2/M (−20.0%) - moonshotai/kimi-k2.6: prompt price $0.95/M → $0.541/M (−43.0%) - moonshotai/kimi-k2.6: completion price $4/M → $2.28/M (−43.0%) - openai/gpt-5.6-sol: prompt price $2.5/M → $2/M (−20.0%) - openai/gpt-5.6-sol: completion price $15/M → $10/M (−33.3%) - openai/gpt-5.6-sol-pro: prompt price $2.5/M → $2/M (−20.0%) - openai/gpt-5.6-sol-pro: completion price $15/M → $10/M (−33.3%) - openai/gpt-5.6-sol-pro:batch: prompt price $1.25/M → $1/M (−20.0%) - openai/gpt-5.6-sol-pro:batch: completion price $7.5/M → $5/M (−33.3%) - openai/gpt-5.6-sol:batch: prompt price $1.25/M → $1/M (−20.0%) - openai/gpt-5.6-sol:batch: completion price $7.5/M → $5/M (−33.3%) - qwen/qwen3-14b: prompt price $0.227/M → $0.12/M (−47.3%) - qwen/qwen3-14b: completion price $0.91/M → $0.24/M (−73.6%) - qwen/qwen3-next-80b-a3b-instruct: prompt price $0.09/M → $0.1/M (+11.1%) - mistralai/mistral-small-3.2-24b-instruct: context length 256,000 → 131,072 - Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.074/M (−47.0%) - Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.148/M (−47.0%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.083/M → $0.074/M (−10.3%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.165/M → $0.148/M (−10.3%) - Alibaba: deepseek/deepseek-v4-flash-0731 prompt price $0.402/M → $0.352/M (−12.4%) - Alibaba: deepseek/deepseek-v4-flash-0731 completion price $1.21/M → $1.06/M (−12.4%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.069/M (−51.0%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.137/M (−51.0%) - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.077/M → $0.068/M (−12.8%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.155/M → $0.135/M (−12.8%) - Fireworks: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.22/M (+57.1%) - Fireworks: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.66/M (+135.7%) - Io Net: deepseek/deepseek-v4-flash-0731 prompt price $0.189/M → $0.229/M (+21.2%) - Io Net: deepseek/deepseek-v4-flash-0731 completion price $0.42/M → $0.59/M (+40.5%) - OpenInference: deepseek/deepseek-v4-flash-0731 completion price $0.14/M → $0.18/M (+28.6%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.079/M → $0.068/M (−12.9%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.157/M → $0.137/M (−12.9%) - Baidu: deepseek/deepseek-v4-pro prompt price $1.69/M → $0.49/M (−71.0%) - Baidu: deepseek/deepseek-v4-pro completion price $3.38/M → $0.98/M (−71.0%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.79/M → $0.481/M (−39.1%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.58/M → $0.963/M (−39.1%) - Alibaba: deepseek/deepseek-v4-pro-0813 prompt price $1.21/M → $1.16/M (−3.6%) - Alibaba: deepseek/deepseek-v4-pro-0813 completion price $3.62/M → $3.48/M (−3.6%) - Io Net: mistralai/mistral-nemo prompt price $0.042/M → $0.044/M (+4.8%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.95/M → $0.541/M (−43.0%) - Baidu: moonshotai/kimi-k2.6 completion price $4/M → $2.28/M (−43.0%) - Decart: moonshotai/kimi-k2.6 prompt price $0.587/M → $0.549/M (−6.3%) - Decart: moonshotai/kimi-k2.6 completion price $2.47/M → $2.31/M (−6.3%) - OpenAI: openai/gpt-5.6-sol prompt price $2.5/M → $2/M (−20.0%) - OpenAI: openai/gpt-5.6-sol completion price $15/M → $10/M (−33.3%) - OpenAI: openai/gpt-5.6-sol prompt price $1.25/M → $1/M (−20.0%) - OpenAI: openai/gpt-5.6-sol completion price $7.5/M → $5/M (−33.3%) - OpenAI: openai/gpt-5.6-sol prompt price $5/M → $4/M (−20.0%) - OpenAI: openai/gpt-5.6-sol completion price $30/M → $20/M (−33.3%) - OpenAI: openai/gpt-5.6-sol-pro prompt price $2.5/M → $2/M (−20.0%) - OpenAI: openai/gpt-5.6-sol-pro completion price $15/M → $10/M (−33.3%) - OpenAI: openai/gpt-5.6-sol-pro prompt price $1.25/M → $1/M (−20.0%) - OpenAI: openai/gpt-5.6-sol-pro completion price $7.5/M → $5/M (−33.3%) - OpenAI: openai/gpt-5.6-sol-pro prompt price $5/M → $4/M (−20.0%) - OpenAI: openai/gpt-5.6-sol-pro completion price $30/M → $20/M (−33.3%) - Baidu: tencent/hy3 prompt price $0.132/M → $0.125/M (−5.0%) - Baidu: tencent/hy3 completion price $0.528/M → $0.502/M (−5.0%) - Baidu: z-ai/glm-5.1 prompt price $1.4/M → $0.896/M (−36.0%) - Baidu: z-ai/glm-5.1 completion price $4.4/M → $2.82/M (−36.0%) - Baidu: z-ai/glm-5.2 prompt price $1.4/M → $0.35/M (−75.0%) - Baidu: z-ai/glm-5.2 completion price $4.4/M → $1.1/M (−75.0%) - Morph: z-ai/glm-5.2 prompt price $0.935/M → $0.842/M (−10.0%) - Morph: z-ai/glm-5.2 completion price $3.48/M → $3.14/M (−10.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.734/M → $0.336/M (−54.2%) - StreamLake: z-ai/glm-5.2 completion price $2.31/M → $1.06/M (−54.2%) - Nebius now serves deepseek/deepseek-v4-flash-0731 (fp8, 1,048,576 ctx, $0.14/M in / $0.28/M out) - Phala now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,048,576 ctx, $1.45/M in / $4.36/M out) - Sail Research now serves deepseek/deepseek-v4-pro-0813 (fp4, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Novita now serves inclusionai/ling-3.0-flash (unknown, 262,144 ctx, $0.042/M in / $0.126/M out) - Alibaba now serves moonshotai/kimi-k3 (unknown, 1,048,576 ctx, $3.45/M in / $17.3/M out) - CoreWeave now serves qwen/qwen3.8-27b (fp8, 262,144 ctx, $0.4/M in / $3/M out) - Phala now serves tencent/hy3 (unknown, 262,144 ctx, $0.15/M in / $0.64/M out) - Mistral now serves z-ai/glm-5.2 (unknown, 1,048,576 ctx, $1.4/M in / $4.4/M out) - DeepSeek no longer serves deepseek/deepseek-v4-flash (was unknown) - DeepSeek no longer serves deepseek/deepseek-v4-pro (was unknown) - Venice no longer serves mistralai/mistral-small-3.2-24b-instruct (was fp8) - DigitalOcean no longer serves qwen/qwen3.8-2.4t-a95b (was unknown) https://variables.md/changelog/2026-08-21/ https://variables.md/changelog/2026-08-21/ Fri, 21 Aug 2026 05:48:43 GMT - Mancer: Weaver (alpha) (mancer/weaver) added to the catalog: 8,000 ctx, $0.5/M in / $0.75/M out - Mistral: Ministral 8B (mistralai/ministral-8b) added to the catalog: 128,000 ctx, $0.11/M in / $0.11/M out - Ox Alpha (stealth/ox-alpha) added to the catalog: 1,048,576 ctx, $0/M in / $0/M out - Tencent: Hy-MT2-1.8B (tencent/hy-mt2-1.8b) added to the catalog: 8,192 ctx, $0.044/M in / $0.177/M out - Tencent: Hy-MT2-30B-A3B (tencent/hy-mt2-30b-a3b) added to the catalog: 8,192 ctx, $0.074/M in / $0.295/M out - deepseek/deepseek-v4-flash: prompt price $0.089/M → $0.083/M (−6.8%) - deepseek/deepseek-v4-flash: completion price $0.177/M → $0.165/M (−6.8%) - deepseek/deepseek-v4-pro: prompt price $1.44/M → $1.6/M (+11.1%) - deepseek/deepseek-v4-pro: completion price $2.88/M → $3.2/M (+11.1%) - google/gemma-4-31b-it: prompt price $0.09/M → $0.1/M (+11.1%) - meta/muse-glimmer-30b: prompt price $0.35/M → $0.3/M (−14.3%) - meta/muse-glimmer-30b: completion price $1.5/M → $1.1/M (−26.7%) - minimax/minimax-m2.5: prompt price $0.225/M → $0.27/M (+20.0%) - minimax/minimax-m2.5: completion price $0.9/M → $0.95/M (+5.6%) - moonshotai/kimi-k2.7-code: prompt price $0.71/M → $0.67/M (−5.6%) - moonshotai/kimi-k2.7-code: completion price $3.5/M → $3.4/M (−2.9%) - qwen/qwen3-14b: prompt price $0.12/M → $0.227/M (+89.6%) - qwen/qwen3-14b: completion price $0.24/M → $0.91/M (+279.2%) - liquid/lfm-2.5-2.6b:free: context length 128,000 → 65,536 - nvidia/nemotron-3.5-lightning: context length 1,000,000 → 262,144 - thinkingmachines/inkling-small: context length 524,288 → 1,048,576 - z-ai/glm-5.2:batch: context length 512,000 → 1,048,575 - GMICloud: deepseek/deepseek-v4-flash prompt price $0.112/M → $0.084/M (−25.0%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.224/M → $0.168/M (−25.0%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.145/M → $0.14/M (−3.4%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.089/M → $0.083/M (−6.8%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.177/M → $0.165/M (−6.8%) - Ambient: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.08/M (−42.9%) - Ambient: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.18/M (−35.7%) - AtlasCloud: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.44/M (+214.3%) - AtlasCloud: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $1.32/M (+371.4%) - Cloudflare: deepseek/deepseek-v4-flash-0731 prompt price $0.08/M → $0.44/M (+450.0%) - Cloudflare: deepseek/deepseek-v4-flash-0731 completion price $0.18/M → $1.32/M (+633.3%) - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.076/M → $0.077/M (+1.2%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.153/M → $0.155/M (+1.2%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.112/M → $0.084/M (−25.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.224/M → $0.168/M (−25.0%) - Io Net: deepseek/deepseek-v4-flash-0731 prompt price $0.149/M → $0.189/M (+26.8%) - Io Net: deepseek/deepseek-v4-flash-0731 completion price $0.32/M → $0.42/M (+31.3%) - Morph: deepseek/deepseek-v4-flash-0731 prompt price $0.139/M → $0.12/M (−13.7%) - GMICloud: deepseek/deepseek-v4-pro prompt price $1.06/M → $0.792/M (−25.0%) - GMICloud: deepseek/deepseek-v4-pro completion price $3.17/M → $2.38/M (−25.0%) - Novita: deepseek/deepseek-v4-pro prompt price $1.44/M → $1.6/M (+11.1%) - Novita: deepseek/deepseek-v4-pro completion price $2.88/M → $3.2/M (+11.1%) - StreamLake: deepseek/deepseek-v4-pro prompt price $1.04/M → $0.79/M (−24.3%) - StreamLake: deepseek/deepseek-v4-pro completion price $2.09/M → $1.58/M (−24.3%) - Alibaba: deepseek/deepseek-v4-pro-0813 prompt price $1.32/M → $1.21/M (−8.7%) - Alibaba: deepseek/deepseek-v4-pro-0813 completion price $3.96/M → $3.62/M (−8.7%) - DigitalOcean: minimax/minimax-m2.5 prompt price $0.225/M → $0.3/M (+33.3%) - DigitalOcean: minimax/minimax-m2.5 completion price $0.9/M → $1.2/M (+33.3%) - Morph: minimax/minimax-m3 prompt price $0.3/M → $0.255/M (−15.0%) - Morph: minimax/minimax-m3 completion price $1.2/M → $1.02/M (−15.0%) - DigitalOcean: moonshotai/kimi-k2.5 prompt price $0.375/M → $0.5/M (+33.3%) - DigitalOcean: moonshotai/kimi-k2.5 completion price $2.02/M → $2.7/M (+33.3%) - DigitalOcean: moonshotai/kimi-k2.6 prompt price $0.76/M → $0.95/M (+25.0%) - DigitalOcean: moonshotai/kimi-k2.6 completion price $3.2/M → $4/M (+25.0%) - DigitalOcean: nvidia/nemotron-3-super-120b-a12b prompt price $0.165/M → $0.3/M (+81.8%) - DigitalOcean: nvidia/nemotron-3-super-120b-a12b completion price $0.358/M → $0.65/M (+81.8%) - Mancer 2: openai/gpt-oss-120b prompt price $0.08/M → $0.085/M (+6.2%) - DigitalOcean: qwen/qwen3.5-397b-a17b prompt price $0.302/M → $0.55/M (+81.8%) - DigitalOcean: qwen/qwen3.5-397b-a17b completion price $1.93/M → $3.5/M (+81.8%) - Venice: qwen/qwen3.6-35b-a3b prompt price $0.098/M → $0.1/M (+2.0%) - Venice: qwen/qwen3.6-35b-a3b completion price $0.95/M → $1/M (+5.3%) - Alibaba: qwen/qwen3.8-27b prompt price $0.55/M → $0.575/M (+4.5%) - Alibaba: qwen/qwen3.8-27b completion price $3.3/M → $3.45/M (+4.5%) - DigitalOcean: z-ai/glm-5 prompt price $0.75/M → $1/M (+33.3%) - DigitalOcean: z-ai/glm-5 completion price $2.4/M → $3.2/M (+33.3%) - DigitalOcean: z-ai/glm-5.1 prompt price $0.975/M → $1.3/M (+33.3%) - Morph: z-ai/glm-5.2 prompt price $1.1/M → $0.935/M (−15.0%) - Morph: z-ai/glm-5.2 completion price $4.1/M → $3.48/M (−15.0%) - Novita: z-ai/glm-5.2 prompt price $0.665/M → $0.741/M (+11.4%) - Novita: z-ai/glm-5.2 completion price $2.09/M → $2.33/M (+11.4%) - StreamLake: z-ai/glm-5.2 prompt price $0.666/M → $0.734/M (+10.1%) - StreamLake: z-ai/glm-5.2 completion price $2.09/M → $2.31/M (+10.1%) - Alibaba now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,000,000 ctx, $0.402/M in / $1.21/M out) - Reka now serves deepseek/deepseek-v4-flash-0731 (fp4, 262,144 ctx, $0.22/M in / $0.66/M out) - Darkbloom now serves google/gemma-4-26b-a4b-it (unknown, 131,072 ctx, $0.05/M in / $0.25/M out) - SambaNova now serves minimax/minimax-m3 (unknown, 1,048,576 ctx, $0.6/M in / $2.4/M out) - Darkbloom now serves qwen/qwen3.6-35b-a3b (fp4, 262,144 ctx, $0.08/M in / $0.75/M out) - BaseTen now serves thinkingmachines/inkling-small (fp8, 1,048,576 ctx, $0.5/M in / $1.2/M out) - Novita no longer serves inclusionai/ling-3.0-flash (was unknown) - Sail Research no longer serves moonshotai/kimi-k2.6 (was int4) - Venice no longer serves nvidia/nemotron-3.5-lightning (was fp4) https://variables.md/changelog/2026-08-20/ https://variables.md/changelog/2026-08-20/ Thu, 20 Aug 2026 05:46:28 GMT - Z.ai: GLM Latest (~z-ai/glm-latest) added to the catalog: 1,048,576 ctx, $1.4/M in / $4.4/M out - AI21: Jamba Large 1.7 (ai21/jamba-large-1.7) removed from the catalog - Mancer: Weaver (alpha) (mancer/weaver) removed from the catalog - ~deepseek/deepseek-v4-flash-latest: prompt price $0.076/M → $0.065/M (−15.0%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.153/M → $0.14/M (−8.5%) - deepseek/deepseek-chat-v3-0324: prompt price $0.27/M → $0.25/M (−7.4%) - deepseek/deepseek-chat-v3-0324: completion price $1.12/M → $1/M (−10.7%) - deepseek/deepseek-v4-flash: prompt price $0.083/M → $0.089/M (+7.3%) - deepseek/deepseek-v4-flash: completion price $0.165/M → $0.177/M (+7.3%) - deepseek/deepseek-v4-pro: prompt price $0.66/M → $1.44/M (+118.2%) - deepseek/deepseek-v4-pro: completion price $1.98/M → $2.88/M (+45.5%) - deepseek/deepseek-v4-pro-0813: prompt price $0.66/M → $1.19/M (+80.0%) - deepseek/deepseek-v4-pro-0813: completion price $1.98/M → $3.56/M (+80.0%) - minimax/minimax-m2.5: prompt price $0.22/M → $0.225/M (+2.3%) - qwen/qwen3.5-35b-a3b: prompt price $0.225/M → $0.25/M (+11.1%) - qwen/qwen3.5-35b-a3b: completion price $1.8/M → $1.25/M (−30.6%) - qwen/qwen3.6-27b: prompt price $0.3/M → $0.6/M (+100.0%) - qwen/qwen3.6-27b: completion price $2/M → $3.6/M (+80.0%) - qwen/qwen3.8-27b: context length 262,144 → 1,000,000 - GMICloud: deepseek/deepseek-v4-flash prompt price $0.084/M → $0.112/M (+33.3%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.168/M → $0.224/M (+33.3%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.083/M → $0.089/M (+7.3%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.165/M → $0.177/M (+7.3%) - Cloudflare: deepseek/deepseek-v4-flash-0731 prompt price $0.44/M → $0.08/M (−81.8%) - Cloudflare: deepseek/deepseek-v4-flash-0731 completion price $1.32/M → $0.18/M (−86.4%) - OpenInference: deepseek/deepseek-v4-flash-0731 prompt price $0.08/M → $0.065/M (−18.8%) - OpenInference: deepseek/deepseek-v4-flash-0731 completion price $0.18/M → $0.14/M (−22.2%) - Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.105/M → $0.07/M (−33.3%) - Relace: deepseek/deepseek-v4-flash-0731 completion price $0.21/M → $0.14/M (−33.3%) - Sail Research: deepseek/deepseek-v4-flash-0731 prompt price $0.09/M → $0.065/M (−27.8%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.696/M → $1.06/M (+51.7%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.39/M → $3.17/M (+127.6%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.694/M → $1.04/M (+50.4%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.39/M → $2.09/M (+50.4%) - AkashML: meta-llama/llama-3.3-70b-instruct prompt price $0.13/M → $0.2/M (+53.8%) - AkashML: meta-llama/llama-3.3-70b-instruct completion price $0.4/M → $0.52/M (+30.0%) - Decart: moonshotai/kimi-k2.6 prompt price $0.568/M → $0.587/M (+3.2%) - Decart: moonshotai/kimi-k2.6 completion price $3.33/M → $2.47/M (−25.9%) - Mancer 2: openai/gpt-oss-120b prompt price $0.085/M → $0.08/M (−5.9%) - Chutes: qwen/qwen3.8-27b prompt price $0.45/M → $0.4/M (−11.1%) - Chutes: qwen/qwen3.8-27b completion price $3.2/M → $3/M (−6.2%) - Novita: z-ai/glm-5.2 prompt price $0.741/M → $0.665/M (−10.2%) - Novita: z-ai/glm-5.2 completion price $2.33/M → $2.09/M (−10.2%) - StreamLake: z-ai/glm-5.2 prompt price $0.734/M → $0.666/M (−9.2%) - StreamLake: z-ai/glm-5.2 completion price $2.31/M → $2.09/M (−9.2%) - Sail Research: deepseek/deepseek-v4-flash-0731 context length 262,144 → 1,048,576 - Together: moonshotai/kimi-k3 context length 1,000,000 → 1,048,576 - Nebius: qwen/qwen3-next-80b-a3b-thinking context length 8,000 → 128,000 - GMICloud now serves deepseek/deepseek-chat-v3-0324 (fp8, 163,840 ctx, $0.29/M in / $1.14/M out) - Novita now serves inclusionai/ling-3.0-flash (unknown, 262,144 ctx, $0.042/M in / $0.126/M out) - Mistral now serves mistralai/mistral-small-2603 (unknown, 262,144 ctx, $0.165/M in / $0.66/M out) - GMICloud now serves moonshotai/kimi-k2.7-code (fp8, 262,144 ctx, $0.95/M in / $4/M out) - Fireworks now serves moonshotai/kimi-k3 (unknown, 1,048,576 ctx, $3.3/M in / $16.5/M out) - GMICloud now serves qwen/qwen3-235b-a22b-2507 (fp8, 262,144 ctx, $0.35/M in / $1.4/M out) - Alibaba now serves qwen/qwen3.8-27b (unknown, 1,000,000 ctx, $0.55/M in / $3.3/M out) - Parasail now serves qwen/qwen3.8-27b (fp8, 262,144 ctx, $0.45/M in / $3.2/M out) - Reka now serves qwen/qwen3.8-27b (fp8, 262,144 ctx, $0.45/M in / $3.2/M out) - Fireworks now serves z-ai/glm-5.2 (unknown, 1,048,576 ctx, $2.1/M in / $6.6/M out) - Inceptron no longer serves minimax/minimax-m2.5 (was fp8) - Together no longer serves moonshotai/kimi-k2.6 (was unknown) - AtlasCloud no longer serves moonshotai/kimi-k2.7-code (was int4) - Nebius no longer serves nvidia/nemotron-3-super-120b-a12b (was fp4) - AkashML no longer serves qwen/qwen3.5-35b-a3b (was fp8) - AkashML no longer serves z-ai/glm-5.2 (was fp8) https://variables.md/changelog/2026-08-19/ https://variables.md/changelog/2026-08-19/ Wed, 19 Aug 2026 05:47:12 GMT - LiquidAI: LFM2.5-2.6B (free) (liquid/lfm-2.5-2.6b:free) added to the catalog: 128,000 ctx, $0/M in / $0/M out - Z.ai: GLM 5.3 (z-ai/glm-5.3) added to the catalog: 1,048,576 ctx, $1.4/M in / $4.4/M out - ~deepseek/deepseek-v4-flash-latest: prompt price $0.079/M → $0.076/M (−2.7%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.157/M → $0.153/M (−2.7%) - google/gemma-4-31b-it: prompt price $0.1/M → $0.09/M (−10.0%) - minimax/minimax-m3:batch: prompt price $0.15/M → $0.3/M (+100.0%) - minimax/minimax-m3:batch: completion price $0.6/M → $1.2/M (+100.0%) - moonshotai/kimi-k2.5: prompt price $0.57/M → $0.45/M (−21.1%) - moonshotai/kimi-k2.5: completion price $2.85/M → $2.25/M (−21.1%) - moonshotai/kimi-k2.7-code:batch: prompt price $0.475/M → $0.95/M (+100.0%) - moonshotai/kimi-k2.7-code:batch: completion price $2/M → $4/M (+100.0%) - nvidia/nemotron-3-ultra-550b-a55b:batch: prompt price $0.3/M → $0.6/M (+100.0%) - nvidia/nemotron-3-ultra-550b-a55b:batch: completion price $1.8/M → $3.6/M (+100.0%) - qwen/qwen3-next-80b-a3b-instruct: prompt price $0.1/M → $0.09/M (−10.0%) - qwen/qwen3.5-122b-a10b: prompt price $0.29/M → $0.26/M (−10.3%) - qwen/qwen3.5-122b-a10b: completion price $2.4/M → $2.08/M (−13.3%) - qwen/qwen3.6-27b: prompt price $0.6/M → $0.3/M (−50.0%) - qwen/qwen3.6-27b: completion price $3.6/M → $2/M (−44.4%) - thinkingmachines/inkling:batch: prompt price $0.5/M → $1/M (+100.0%) - thinkingmachines/inkling:batch: completion price $2.02/M → $4.05/M (+100.0%) - z-ai/glm-5.2: prompt price $0.5/M → $0.966/M (+93.2%) - z-ai/glm-5.2: completion price $3.15/M → $3.04/M (−3.6%) - z-ai/glm-5.2:batch: prompt price $0.7/M → $1.4/M (+100.0%) - z-ai/glm-5.2:batch: completion price $2.2/M → $4.4/M (+100.0%) - z-ai/glm-5.2:free: context length 128,000 → 256,000 - DeepSeek: deepseek/deepseek-v4-flash-0731 quantization fp8 → unknown - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.145/M (+3.6%) - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.079/M → $0.076/M (−3.4%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.158/M → $0.153/M (−3.4%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.084/M → $0.112/M (+33.3%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.168/M → $0.224/M (+33.3%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.145/M (+3.6%) - Alibaba: deepseek/deepseek-v4-pro-0813 prompt price $1.45/M → $1.32/M (−9.1%) - Alibaba: deepseek/deepseek-v4-pro-0813 completion price $4.36/M → $3.96/M (−9.1%) - GMICloud: deepseek/deepseek-v4-pro-0813 prompt price $1.22/M → $1.19/M (−2.5%) - GMICloud: deepseek/deepseek-v4-pro-0813 completion price $2.44/M → $3.56/M (+46.3%) - Phala: meta/muse-glimmer-30b completion price $1.2/M → $1.1/M (−8.3%) - Chutes: qwen/qwen3.8-27b prompt price $0.4/M → $0.45/M (+12.5%) - Chutes: qwen/qwen3.8-27b completion price $3/M → $3.2/M (+6.7%) - Io Net: qwen/qwen3.8-27b prompt price $0.44/M → $0.48/M (+9.1%) - Io Net: qwen/qwen3.8-27b completion price $3.15/M → $3.4/M (+7.9%) - Ambient: z-ai/glm-5.2 prompt price $1.05/M → $0.6/M (−42.9%) - Ambient: z-ai/glm-5.2 completion price $4.4/M → $2/M (−54.5%) - Phala: z-ai/glm-5.2 prompt price $1.13/M → $1.26/M (+11.1%) - StreamLake: z-ai/glm-5.2 prompt price $0.56/M → $0.734/M (+31.0%) - StreamLake: z-ai/glm-5.2 completion price $1.76/M → $2.31/M (+31.0%) - Io Net: qwen/qwen3.8-27b context length 262,100 → 65,500 - OpenInference now serves deepseek/deepseek-v4-flash-0731 (fp4, 262,144 ctx, $0.08/M in / $0.18/M out) - StreamLake now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,024,000 ctx, $1.32/M in / $3.96/M out) - Parasail now serves meta/muse-glimmer-30b (bf16, 131,072 ctx, $0.3/M in / $1.1/M out) - Phala no longer serves deepseek/deepseek-v4-pro-0813 (was unknown) - Morph no longer serves google/gemma-4-31b-it (was fp4) - Nebius no longer serves minimax/minimax-m2.5 (was fp4) - DigitalOcean no longer serves qwen/qwen3-coder-30b-a3b-instruct (was unknown) - Chutes no longer serves qwen/qwen3.5-397b-a17b (was fp8) - Io Net no longer serves qwen/qwen3.6-27b (was fp8) - Morph no longer serves qwen/qwen3.6-27b (was fp4) https://variables.md/changelog/2026-08-18/ https://variables.md/changelog/2026-08-18/ Tue, 18 Aug 2026 05:45:21 GMT - LiquidAI: LFM2.5-2.6B (free) (liquid/lfm-2.5-2.6b:free) removed from the catalog - ~deepseek/deepseek-v4-flash-latest: prompt price $0.06/M → $0.079/M (+30.3%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.121/M → $0.157/M (+30.3%) - ~openai/gpt-latest: prompt price $5/M → $2.5/M (−50.0%) - ~openai/gpt-latest: completion price $30/M → $15/M (−50.0%) - deepseek/deepseek-v3.1-terminus: completion price $0.95/M → $1/M (+5.3%) - openai/gpt-5.6-luna: prompt price $0.1/M → $0.2/M (+100.0%) - openai/gpt-5.6-luna: completion price $0.6/M → $1.2/M (+100.0%) - openai/gpt-5.6-luna-pro: prompt price $0.1/M → $0.2/M (+100.0%) - openai/gpt-5.6-luna-pro: completion price $0.6/M → $1.2/M (+100.0%) - openai/gpt-5.6-sol: prompt price $5/M → $2.5/M (−50.0%) - openai/gpt-5.6-sol: completion price $30/M → $15/M (−50.0%) - openai/gpt-5.6-sol-pro: prompt price $5/M → $2.5/M (−50.0%) - openai/gpt-5.6-sol-pro: completion price $30/M → $15/M (−50.0%) - openai/gpt-5.6-sol-pro:batch: prompt price $2.5/M → $1.25/M (−50.0%) - openai/gpt-5.6-sol-pro:batch: completion price $15/M → $7.5/M (−50.0%) - openai/gpt-5.6-sol:batch: prompt price $2.5/M → $1.25/M (−50.0%) - openai/gpt-5.6-sol:batch: completion price $15/M → $7.5/M (−50.0%) - openai/gpt-5.6-terra: prompt price $1/M → $2/M (+100.0%) - openai/gpt-5.6-terra: completion price $6/M → $12/M (+100.0%) - openai/gpt-5.6-terra-pro: prompt price $1/M → $2/M (+100.0%) - openai/gpt-5.6-terra-pro: completion price $6/M → $12/M (+100.0%) - qwen/qwen3.6-27b: prompt price $0.289/M → $0.6/M (+107.6%) - qwen/qwen3.6-27b: completion price $2.4/M → $3.6/M (+50.0%) - z-ai/glm-4.6: prompt price $0.55/M → $0.5/M (−9.1%) - z-ai/glm-4.6: completion price $2.2/M → $2/M (−9.1%) - z-ai/glm-5.2: prompt price $1.19/M → $0.5/M (−58.0%) - z-ai/glm-5.2: completion price $3.74/M → $3.15/M (−15.8%) - ~deepseek/deepseek-v4-flash-latest: context length 1,048,576 → 1,310,720 - deepseek/deepseek-v4-flash-0731: context length 1,048,576 → 1,310,720 - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.06/M → $0.079/M (+31.3%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.121/M → $0.158/M (+31.3%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.083/M → $0.079/M (−4.8%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.165/M → $0.157/M (−4.8%) - Novita: deepseek/deepseek-v4-pro prompt price $1.17/M → $1.44/M (+23.3%) - Novita: deepseek/deepseek-v4-pro completion price $2.34/M → $2.88/M (+23.3%) - Novita: deepseek/deepseek-v4-pro-0813 prompt price $1.06/M → $1.32/M (+25.0%) - Novita: deepseek/deepseek-v4-pro-0813 completion price $3.17/M → $3.96/M (+25.0%) - NextBit: google/gemma-4-26b-a4b-it prompt price $0.12/M → $0.1/M (−16.7%) - Venice: moonshotai/kimi-k2.5 prompt price $0.56/M → $0.532/M (−5.0%) - Venice: moonshotai/kimi-k2.5 completion price $3.5/M → $3.32/M (−5.0%) - Decart: moonshotai/kimi-k2.6 prompt price $0.549/M → $0.568/M (+3.5%) - Decart: moonshotai/kimi-k2.6 completion price $2.31/M → $3.33/M (+44.1%) - OpenAI: openai/gpt-5.6-luna prompt price $0.1/M → $0.2/M (+100.0%) - OpenAI: openai/gpt-5.6-luna completion price $0.6/M → $1.2/M (+100.0%) - OpenAI: openai/gpt-5.6-luna prompt price $0.05/M → $0.1/M (+100.0%) - OpenAI: openai/gpt-5.6-luna completion price $0.3/M → $0.6/M (+100.0%) - OpenAI: openai/gpt-5.6-luna prompt price $0.2/M → $0.4/M (+100.0%) - OpenAI: openai/gpt-5.6-luna completion price $1.2/M → $2.4/M (+100.0%) - OpenAI: openai/gpt-5.6-luna-pro prompt price $0.1/M → $0.2/M (+100.0%) - OpenAI: openai/gpt-5.6-luna-pro completion price $0.6/M → $1.2/M (+100.0%) - OpenAI: openai/gpt-5.6-luna-pro prompt price $0.05/M → $0.1/M (+100.0%) - OpenAI: openai/gpt-5.6-luna-pro completion price $0.3/M → $0.6/M (+100.0%) - OpenAI: openai/gpt-5.6-luna-pro prompt price $0.2/M → $0.4/M (+100.0%) - OpenAI: openai/gpt-5.6-luna-pro completion price $1.2/M → $2.4/M (+100.0%) - OpenAI: openai/gpt-5.6-sol prompt price $5/M → $2.5/M (−50.0%) - OpenAI: openai/gpt-5.6-sol completion price $30/M → $15/M (−50.0%) - OpenAI: openai/gpt-5.6-sol prompt price $2.5/M → $1.25/M (−50.0%) - OpenAI: openai/gpt-5.6-sol completion price $15/M → $7.5/M (−50.0%) - OpenAI: openai/gpt-5.6-sol prompt price $10/M → $5/M (−50.0%) - OpenAI: openai/gpt-5.6-sol completion price $60/M → $30/M (−50.0%) - OpenAI: openai/gpt-5.6-sol-pro prompt price $5/M → $2.5/M (−50.0%) - OpenAI: openai/gpt-5.6-sol-pro completion price $30/M → $15/M (−50.0%) - OpenAI: openai/gpt-5.6-sol-pro prompt price $2.5/M → $1.25/M (−50.0%) - OpenAI: openai/gpt-5.6-sol-pro completion price $15/M → $7.5/M (−50.0%) - OpenAI: openai/gpt-5.6-sol-pro prompt price $10/M → $5/M (−50.0%) - OpenAI: openai/gpt-5.6-sol-pro completion price $60/M → $30/M (−50.0%) - OpenAI: openai/gpt-5.6-terra prompt price $1/M → $2/M (+100.0%) - OpenAI: openai/gpt-5.6-terra completion price $6/M → $12/M (+100.0%) - OpenAI: openai/gpt-5.6-terra prompt price $0.5/M → $1/M (+100.0%) - OpenAI: openai/gpt-5.6-terra completion price $3/M → $6/M (+100.0%) - OpenAI: openai/gpt-5.6-terra prompt price $2/M → $4/M (+100.0%) - OpenAI: openai/gpt-5.6-terra completion price $12/M → $24/M (+100.0%) - OpenAI: openai/gpt-5.6-terra-pro prompt price $1/M → $2/M (+100.0%) - OpenAI: openai/gpt-5.6-terra-pro completion price $6/M → $12/M (+100.0%) - OpenAI: openai/gpt-5.6-terra-pro prompt price $0.5/M → $1/M (+100.0%) - OpenAI: openai/gpt-5.6-terra-pro completion price $3/M → $6/M (+100.0%) - OpenAI: openai/gpt-5.6-terra-pro prompt price $2/M → $4/M (+100.0%) - OpenAI: openai/gpt-5.6-terra-pro completion price $12/M → $24/M (+100.0%) - Mancer 2: openai/gpt-oss-120b prompt price $0.08/M → $0.085/M (+6.2%) - Decart: z-ai/glm-5.2 prompt price $0.768/M → $0.684/M (−10.9%) - Decart: z-ai/glm-5.2 completion price $2.56/M → $2.28/M (−10.9%) - StreamLake: z-ai/glm-5.2 prompt price $0.753/M → $0.56/M (−25.6%) - StreamLake: z-ai/glm-5.2 completion price $2.37/M → $1.76/M (−25.6%) - Cloudflare: deepseek/deepseek-v4-flash-0731 context length 1,048,576 → 1,310,720 - BaseTen: deepseek/deepseek-v4-pro context length 262,144 → 1,048,576 - Claude Platform on AWS now serves anthropic/claude-fable-5 (unknown, 1,000,000 ctx, $10/M in / $50/M out) - Claude Platform on AWS now serves anthropic/claude-opus-4.5 (unknown, 200,000 ctx, $5/M in / $25/M out) - Claude Platform on AWS now serves anthropic/claude-opus-4.6 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Claude Platform on AWS now serves anthropic/claude-opus-4.7 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Claude Platform on AWS now serves anthropic/claude-opus-4.8 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Claude Platform on AWS now serves anthropic/claude-sonnet-4.5 (unknown, 1,000,000 ctx, $3/M in / $15/M out) - Claude Platform on AWS now serves anthropic/claude-sonnet-4.6 (unknown, 1,000,000 ctx, $3/M in / $15/M out) - Claude Platform on AWS now serves anthropic/claude-sonnet-5 (unknown, 1,000,000 ctx, $2/M in / $10/M out) - Alibaba now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,000,000 ctx, $1.45/M in / $4.36/M out) - DigitalOcean now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Parasail now serves deepseek/deepseek-v4-pro-0813 (fp8, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Io Net now serves qwen/qwen3.8-27b (fp8, 262,100 ctx, $0.44/M in / $3.15/M out) - Venice now serves qwen/qwen3.8-27b (fp8, 262,144 ctx, $0.45/M in / $3.2/M out) - Amazon Bedrock no longer serves anthropic/claude-fable-5 (was unknown) - Anthropic no longer serves anthropic/claude-opus-4.5 (was unknown) - Anthropic no longer serves anthropic/claude-opus-4.6 (was unknown) - Anthropic no longer serves anthropic/claude-opus-4.7 (was unknown) - Anthropic no longer serves anthropic/claude-opus-4.8 (was unknown) - Amazon Bedrock no longer serves anthropic/claude-opus-5 (was unknown) - Amazon Bedrock no longer serves anthropic/claude-sonnet-4.5 (was unknown) - Anthropic no longer serves anthropic/claude-sonnet-4.5 (was unknown) - Anthropic no longer serves anthropic/claude-sonnet-4.6 (was unknown) - Amazon Bedrock no longer serves anthropic/claude-sonnet-5 (was unknown) - DeepInfra no longer serves deepseek/deepseek-v3.1-terminus (was fp4) - OpenInference no longer serves deepseek/deepseek-v4-flash-0731 (was fp4) - Crusoe no longer serves qwen/qwen3-235b-a22b-2507 (was bf16) - Cerebras no longer serves z-ai/glm-4.7 (was fp16) - Wafer no longer serves z-ai/glm-5.1 (was fp4) - ModelRun no longer serves z-ai/glm-5.2 (was fp4) - Wafer no longer serves z-ai/glm-5.2 (was fp4) https://variables.md/changelog/2026-08-17/ https://variables.md/changelog/2026-08-17/ Mon, 17 Aug 2026 05:50:56 GMT - Z.ai: GLM 5.2 (free) (z-ai/glm-5.2:free) added to the catalog: 128,000 ctx, $0/M in / $0/M out - ~deepseek/deepseek-v4-flash-latest: prompt price $0.067/M → $0.06/M (−10.1%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.134/M → $0.121/M (−10.1%) - ~moonshotai/kimi-latest: prompt price $2.8/M → $2.6/M (−7.1%) - ~moonshotai/kimi-latest: completion price $14/M → $13/M (−7.1%) - deepseek/deepseek-v4-flash: prompt price $0.063/M → $0.083/M (+31.4%) - deepseek/deepseek-v4-flash: completion price $0.126/M → $0.165/M (+31.4%) - deepseek/deepseek-v4-pro: prompt price $1.17/M → $0.66/M (−43.5%) - deepseek/deepseek-v4-pro: completion price $2.34/M → $1.98/M (−15.2%) - deepseek/deepseek-v4-pro-0813: prompt price $0.435/M → $0.66/M (+51.7%) - deepseek/deepseek-v4-pro-0813: completion price $0.87/M → $1.98/M (+127.6%) - google/gemma-4-26b-a4b-it: prompt price $0.12/M → $0.07/M (−41.7%) - google/gemma-4-26b-a4b-it: completion price $0.4/M → $0.34/M (−15.0%) - minimax/minimax-m1: prompt price $0.4/M → $0.55/M (+37.5%) - moonshotai/kimi-k2.6: prompt price $0.65/M → $0.95/M (+46.2%) - moonshotai/kimi-k2.6: completion price $3.41/M → $4/M (+17.3%) - nvidia/nemotron-3.5-lightning: prompt price $0.1/M → $0.08/M (−20.0%) - nvidia/nemotron-3.5-lightning: completion price $0.25/M → $0.2/M (−20.0%) - qwen/qwen2.5-vl-72b-instruct: prompt price $0.25/M → $0.8/M (+220.0%) - qwen/qwen2.5-vl-72b-instruct: completion price $0.75/M → $1/M (+33.3%) - qwen/qwen3-vl-235b-a22b-instruct: prompt price $0.26/M → $0.21/M (−19.2%) - qwen/qwen3-vl-235b-a22b-instruct: completion price $1.04/M → $1.9/M (+82.7%) - qwen/qwen3.6-27b: prompt price $0.3/M → $0.289/M (−3.7%) - qwen/qwen3.6-27b: completion price $2/M → $2.4/M (+20.0%) - qwen/qwen3.6-35b-a3b: prompt price $0.15/M → $0.14/M (−6.7%) - z-ai/glm-5.2: prompt price $0.308/M → $1.19/M (+286.4%) - z-ai/glm-5.2: completion price $0.968/M → $3.74/M (+286.4%) - Mancer 2: deepseek/deepseek-v4-flash quantization fp4 → fp8 - GMICloud: deepseek/deepseek-v3.2 prompt price $0.215/M → $0.209/M (−2.7%) - GMICloud: deepseek/deepseek-v3.2 completion price $0.318/M → $0.31/M (−2.7%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.063/M → $0.14/M (+122.2%) - Baidu: deepseek/deepseek-v4-flash completion price $0.126/M → $0.28/M (+122.2%) - Cloudflare: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.44/M (+214.3%) - Cloudflare: deepseek/deepseek-v4-flash completion price $0.28/M → $1.32/M (+371.4%) - DeepSeek: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.22/M (+57.1%) - DeepSeek: deepseek/deepseek-v4-flash completion price $0.28/M → $0.66/M (+135.7%) - GMICloud: deepseek/deepseek-v4-flash prompt price $0.07/M → $0.084/M (+20.0%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.14/M → $0.168/M (+20.0%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.15/M → $0.14/M (−6.7%) - Mancer 2: deepseek/deepseek-v4-flash completion price $0.5/M → $0.45/M (−10.0%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.063/M → $0.083/M (+31.4%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.126/M → $0.165/M (+31.4%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.067/M → $0.14/M (+108.3%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.134/M → $0.28/M (+108.3%) - Cloudflare: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.44/M (+214.3%) - Cloudflare: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $1.32/M (+371.4%) - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.068/M → $0.06/M (−10.7%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.135/M → $0.121/M (−10.7%) - DeepSeek: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.22/M (+57.1%) - DeepSeek: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.66/M (+135.7%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.07/M → $0.084/M (+20.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.14/M → $0.168/M (+20.0%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.15/M → $0.14/M (−6.7%) - Mancer 2: deepseek/deepseek-v4-flash-0731 completion price $0.5/M → $0.45/M (−10.0%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.067/M → $0.083/M (+23.2%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.134/M → $0.165/M (+23.2%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.406/M → $1.69/M (+316.7%) - Baidu: deepseek/deepseek-v4-pro completion price $0.811/M → $3.38/M (+316.7%) - DeepSeek: deepseek/deepseek-v4-pro prompt price $0.435/M → $0.66/M (+51.7%) - DeepSeek: deepseek/deepseek-v4-pro completion price $0.87/M → $1.98/M (+127.6%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.609/M → $0.696/M (+14.3%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.22/M → $1.39/M (+14.3%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.397/M → $0.694/M (+74.9%) - StreamLake: deepseek/deepseek-v4-pro completion price $0.794/M → $1.39/M (+74.9%) - DeepSeek: deepseek/deepseek-v4-pro-0813 prompt price $0.435/M → $0.66/M (+51.7%) - DeepSeek: deepseek/deepseek-v4-pro-0813 completion price $0.87/M → $1.98/M (+127.6%) - Phala: meta/muse-glimmer-30b prompt price $0.35/M → $0.3/M (−14.3%) - Phala: meta/muse-glimmer-30b completion price $1.5/M → $1.2/M (−20.0%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.541/M → $0.95/M (+75.4%) - Baidu: moonshotai/kimi-k2.6 completion price $2.28/M → $4/M (+75.4%) - Sail Research: moonshotai/kimi-k3 prompt price $3/M → $2.6/M (−13.3%) - Sail Research: moonshotai/kimi-k3 completion price $15/M → $13/M (−13.3%) - Mancer 2: openai/gpt-oss-120b prompt price $0.085/M → $0.08/M (−5.9%) - Baidu: tencent/hy3 prompt price $0.125/M → $0.132/M (+5.3%) - Baidu: tencent/hy3 completion price $0.502/M → $0.528/M (+5.3%) - Baidu: z-ai/glm-5.1 prompt price $0.896/M → $1.4/M (+56.3%) - Baidu: z-ai/glm-5.1 completion price $2.82/M → $4.4/M (+56.3%) - Baidu: z-ai/glm-5.2 prompt price $0.322/M → $1.4/M (+334.8%) - Baidu: z-ai/glm-5.2 completion price $1.01/M → $4.4/M (+334.8%) - Novita: z-ai/glm-5.2 prompt price $0.339/M → $0.741/M (+118.6%) - Novita: z-ai/glm-5.2 completion price $1.06/M → $2.33/M (+118.6%) - StreamLake: z-ai/glm-5.2 prompt price $0.308/M → $0.753/M (+144.5%) - StreamLake: z-ai/glm-5.2 completion price $0.968/M → $2.37/M (+144.5%) - Relace now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.105/M in / $0.21/M out) - Phala now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Chutes now serves qwen/qwen3.8-27b (fp8, 262,144 ctx, $0.4/M in / $3/M out) https://variables.md/changelog/2026-08-16/ https://variables.md/changelog/2026-08-16/ Sun, 16 Aug 2026 05:43:47 GMT - Dots Studio: Dots3-Note Preview (free) (dots-studio/dots-3-note-preview:free) added to the catalog: 512,000 ctx, $0/M in / $0/M out - ~deepseek/deepseek-v4-flash-latest: prompt price $0.078/M → $0.067/M (−14.3%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.157/M → $0.134/M (−14.3%) - deepseek/deepseek-v4-flash: prompt price $0.077/M → $0.063/M (−18.2%) - deepseek/deepseek-v4-flash: completion price $0.154/M → $0.126/M (−18.2%) - minimax/minimax-m1: prompt price $0.55/M → $0.4/M (−27.3%) - qwen/qwen-plus-2025-07-28:thinking: prompt price $0.4/M → $0.26/M (−35.0%) - qwen/qwen-plus-2025-07-28:thinking: completion price $1.2/M → $0.78/M (−35.0%) - qwen/qwen3-30b-a3b: prompt price $0.12/M → $0.13/M (+8.3%) - qwen/qwen3-30b-a3b: completion price $0.5/M → $0.52/M (+4.0%) - qwen/qwen3.6-27b: prompt price $0.6/M → $0.3/M (−50.0%) - qwen/qwen3.6-27b: completion price $3.6/M → $2/M (−44.4%) - tencent/hy3-preview: prompt price $0.063/M → $0.18/M (+185.7%) - tencent/hy3-preview: completion price $0.21/M → $0.6/M (+185.7%) - z-ai/glm-5.2: prompt price $0.49/M → $0.308/M (−37.1%) - z-ai/glm-5.2: completion price $1.54/M → $0.968/M (−37.1%) - Alibaba: qwen/qwen-plus-2025-07-28 quantization fp8 → unknown - GMICloud: deepseek/deepseek-v3.2 prompt price $0.29/M → $0.215/M (−26.0%) - GMICloud: deepseek/deepseek-v3.2 completion price $0.43/M → $0.318/M (−26.0%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.077/M → $0.063/M (−18.2%) - Baidu: deepseek/deepseek-v4-flash completion price $0.154/M → $0.126/M (−18.2%) - GMICloud: deepseek/deepseek-v4-flash prompt price $0.091/M → $0.07/M (−23.1%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.182/M → $0.14/M (−23.1%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.175/M → $0.15/M (−14.3%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.077/M → $0.063/M (−18.2%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.154/M → $0.126/M (−18.2%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.078/M → $0.067/M (−14.3%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.157/M → $0.134/M (−14.3%) - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.081/M → $0.068/M (−16.7%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.162/M → $0.135/M (−16.7%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.091/M → $0.07/M (−23.1%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.182/M → $0.14/M (−23.1%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.175/M → $0.15/M (−14.3%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.078/M → $0.067/M (−14.3%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.157/M → $0.134/M (−14.3%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.422/M → $0.406/M (−4.0%) - Baidu: deepseek/deepseek-v4-pro completion price $0.845/M → $0.811/M (−4.0%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.696/M → $0.609/M (−12.5%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.39/M → $1.22/M (−12.5%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.414/M → $0.397/M (−4.1%) - StreamLake: deepseek/deepseek-v4-pro completion price $0.828/M → $0.794/M (−4.1%) - Novita: deepseek/deepseek-v4-pro-0813 prompt price $1.32/M → $1.06/M (−20.0%) - Novita: deepseek/deepseek-v4-pro-0813 completion price $3.96/M → $3.17/M (−20.0%) - GMICloud: minimax/minimax-m2.7 prompt price $0.27/M → $0.24/M (−11.1%) - GMICloud: minimax/minimax-m2.7 completion price $1.08/M → $0.96/M (−11.1%) - Baidu: tencent/hy3 prompt price $0.128/M → $0.125/M (−2.1%) - Baidu: tencent/hy3 completion price $0.512/M → $0.502/M (−2.1%) - GMICloud: tencent/hy3 prompt price $0.129/M → $0.126/M (−2.2%) - GMICloud: tencent/hy3 completion price $0.534/M → $0.522/M (−2.2%) - GMICloud: tencent/hy3-preview prompt price $0.063/M → $0.18/M (+185.7%) - GMICloud: tencent/hy3-preview completion price $0.21/M → $0.6/M (+185.7%) - GMICloud: xiaomi/mimo-v2.5 prompt price $0.14/M → $0.119/M (−15.0%) - GMICloud: xiaomi/mimo-v2.5 completion price $0.28/M → $0.238/M (−15.0%) - GMICloud: xiaomi/mimo-v2.5-pro prompt price $0.435/M → $0.304/M (−30.0%) - GMICloud: xiaomi/mimo-v2.5-pro completion price $0.87/M → $0.609/M (−30.0%) - GMICloud: z-ai/glm-5 prompt price $1/M → $0.6/M (−40.0%) - GMICloud: z-ai/glm-5 completion price $3.2/M → $1.92/M (−40.0%) - Baidu: z-ai/glm-5.1 prompt price $0.952/M → $0.896/M (−5.9%) - Baidu: z-ai/glm-5.1 completion price $2.99/M → $2.82/M (−5.9%) - GMICloud: z-ai/glm-5.1 prompt price $1.4/M → $0.91/M (−35.0%) - GMICloud: z-ai/glm-5.1 completion price $4.4/M → $2.86/M (−35.0%) - Baidu: z-ai/glm-5.2 prompt price $0.49/M → $0.322/M (−34.3%) - Baidu: z-ai/glm-5.2 completion price $1.54/M → $1.01/M (−34.3%) - DigitalOcean: z-ai/glm-5.2 prompt price $0.63/M → $0.7/M (+11.1%) - DigitalOcean: z-ai/glm-5.2 completion price $1.98/M → $2.2/M (+11.1%) - Novita: z-ai/glm-5.2 prompt price $0.56/M → $0.339/M (−39.5%) - Novita: z-ai/glm-5.2 completion price $1.76/M → $1.06/M (−39.5%) - StreamLake: z-ai/glm-5.2 prompt price $0.49/M → $0.308/M (−37.1%) - StreamLake: z-ai/glm-5.2 completion price $1.54/M → $0.968/M (−37.1%) - Together now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Relace no longer serves deepseek/deepseek-v4-flash-0731 (was fp4) - Darkbloom no longer serves qwen/qwen3.6-35b-a3b (was unknown) https://variables.md/changelog/2026-08-15/ https://variables.md/changelog/2026-08-15/ Sat, 15 Aug 2026 05:41:52 GMT - Qwen: Qwen3.8 27B (qwen/qwen3.8-27b) added to the catalog: 262,144 ctx, $0.45/M in / $3.2/M out - ~deepseek/deepseek-v4-flash-latest: prompt price $0.08/M → $0.078/M (−2.2%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.252/M → $0.157/M (−37.9%) - deepseek/deepseek-v4-flash: prompt price $0.14/M → $0.077/M (−45.1%) - deepseek/deepseek-v4-flash: completion price $0.28/M → $0.154/M (−45.1%) - meta-llama/llama-4-maverick: completion price $0.696/M → $0.8/M (+14.9%) - moonshotai/kimi-k2.6: prompt price $0.95/M → $0.65/M (−31.6%) - moonshotai/kimi-k2.6: completion price $4/M → $3.41/M (−14.7%) - moonshotai/kimi-k2.7-code: prompt price $0.67/M → $0.71/M (+6.0%) - moonshotai/kimi-k2.7-code: completion price $3.4/M → $3.5/M (+2.9%) - qwen/qwen3.5-35b-a3b: prompt price $0.25/M → $0.225/M (−10.0%) - qwen/qwen3.5-35b-a3b: completion price $1.25/M → $1.8/M (+44.0%) - qwen/qwen3.5-397b-a17b: prompt price $0.5/M → $0.39/M (−22.0%) - qwen/qwen3.5-397b-a17b: completion price $3.6/M → $2.34/M (−35.0%) - z-ai/glm-4.6: prompt price $0.5/M → $0.55/M (+10.0%) - z-ai/glm-4.6: completion price $2/M → $2.2/M (+10.0%) - z-ai/glm-5: prompt price $0.95/M → $0.6/M (−36.8%) - z-ai/glm-5: completion price $2.55/M → $1.92/M (−24.7%) - z-ai/glm-5.1: prompt price $1.4/M → $0.966/M (−31.0%) - z-ai/glm-5.1: completion price $4.4/M → $3.04/M (−31.0%) - z-ai/glm-5.2: prompt price $0.63/M → $0.49/M (−22.2%) - z-ai/glm-5.2: completion price $1.98/M → $1.54/M (−22.2%) - qwen/qwen3.8-2.4t-a95b: context length 1,010,000 → 1,048,576 - DeepInfra: deepseek/deepseek-v4-flash quantization fp4 → fp8 - DeepInfra: deepseek/deepseek-v4-flash-0731 quantization fp4 → fp8 - DeepInfra: deepseek/deepseek-v4-pro quantization fp4 → fp8 - Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.077/M (−45.0%) - Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.154/M (−45.0%) - GMICloud: deepseek/deepseek-v4-flash prompt price $0.087/M → $0.091/M (+4.8%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.174/M → $0.182/M (+4.8%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.087/M → $0.077/M (−11.3%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.173/M → $0.154/M (−11.3%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.078/M (−44.0%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.157/M (−44.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.084/M → $0.091/M (+8.3%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.168/M → $0.182/M (+8.3%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.105/M → $0.078/M (−25.5%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.21/M → $0.157/M (−25.5%) - Baidu: deepseek/deepseek-v4-pro prompt price $1.69/M → $0.422/M (−75.0%) - Baidu: deepseek/deepseek-v4-pro completion price $3.38/M → $0.845/M (−75.0%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.522/M → $0.696/M (+33.3%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.04/M → $1.39/M (+33.3%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.522/M → $0.414/M (−20.7%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.04/M → $0.828/M (−20.7%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.95/M → $0.541/M (−43.0%) - Baidu: moonshotai/kimi-k2.6 completion price $4/M → $2.28/M (−43.0%) - Decart: moonshotai/kimi-k2.6 prompt price $0.587/M → $0.549/M (−6.3%) - Decart: moonshotai/kimi-k2.6 completion price $2.47/M → $2.31/M (−6.3%) - Io Net: qwen/qwen3.6-35b-a3b prompt price $0.29/M → $0.19/M (−34.5%) - Io Net: qwen/qwen3.6-35b-a3b completion price $1.89/M → $1.19/M (−37.0%) - Baidu: tencent/hy3 prompt price $0.132/M → $0.128/M (−3.0%) - Baidu: tencent/hy3 completion price $0.528/M → $0.512/M (−3.0%) - GMICloud: z-ai/glm-5 prompt price $0.6/M → $1/M (+66.7%) - GMICloud: z-ai/glm-5 completion price $1.92/M → $3.2/M (+66.7%) - Baidu: z-ai/glm-5.1 prompt price $1.4/M → $0.952/M (−32.0%) - Baidu: z-ai/glm-5.1 completion price $4.4/M → $2.99/M (−32.0%) - GMICloud: z-ai/glm-5.1 prompt price $0.98/M → $1.4/M (+42.9%) - GMICloud: z-ai/glm-5.1 completion price $3.08/M → $4.4/M (+42.9%) - Baidu: z-ai/glm-5.2 prompt price $1.4/M → $0.49/M (−65.0%) - Baidu: z-ai/glm-5.2 completion price $4.4/M → $1.54/M (−65.0%) - Novita: z-ai/glm-5.2 prompt price $0.741/M → $0.56/M (−24.4%) - Novita: z-ai/glm-5.2 completion price $2.33/M → $1.76/M (−24.4%) - StreamLake: z-ai/glm-5.2 prompt price $0.753/M → $0.49/M (−34.9%) - StreamLake: z-ai/glm-5.2 completion price $2.37/M → $1.54/M (−34.9%) - Cloudflare: deepseek/deepseek-v4-flash-0731 context length 384,000 → 1,048,576 - Azure now serves anthropic/claude-opus-4.8 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Azure now serves anthropic/claude-opus-5 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Azure now serves anthropic/claude-sonnet-5 (unknown, 1,000,000 ctx, $2/M in / $10/M out) - Azure now serves deepseek/deepseek-v4-flash (unknown, 1,048,576 ctx, $0.21/M in / $0.56/M out) - Azure now serves deepseek/deepseek-v4-pro (unknown, 1,048,576 ctx, $1.91/M in / $3.83/M out) - BaseTen now serves deepseek/deepseek-v4-pro-0813 (fp4, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Novita now serves deepseek/deepseek-v4-pro-0813 (fp8, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Azure now serves openai/gpt-5.4 (unknown, 1,050,000 ctx, $2.75/M in / $16.5/M out) - Azure now serves openai/gpt-5.4-mini (unknown, 400,000 ctx, $0.825/M in / $4.95/M out) - Azure now serves openai/gpt-5.4-nano (unknown, 400,000 ctx, $0.22/M in / $1.38/M out) - Azure now serves openai/gpt-5.5 (unknown, 1,050,000 ctx, $5.5/M in / $33/M out) - Azure now serves openai/gpt-5.6-luna (unknown, 1,050,000 ctx, $0.22/M in / $1.32/M out) - Azure now serves openai/gpt-5.6-sol (unknown, 1,050,000 ctx, $5.5/M in / $33/M out) - Azure now serves openai/gpt-5.6-terra (unknown, 1,050,000 ctx, $2.2/M in / $13.2/M out) - Darkbloom now serves qwen/qwen3.6-35b-a3b (unknown, 262,144 ctx, $0.08/M in / $0.75/M out) - SiliconFlow now serves qwen/qwen3.8-2.4t-a95b (fp8, 1,048,576 ctx, $2/M in / $6/M out) - Venice now serves qwen/qwen3.8-2.4t-a95b (unknown, 262,144 ctx, $2.5/M in / $7.5/M out) - ModelRun now serves z-ai/glm-5.2 (fp4, 163,840 ctx, $2.2/M in / $6.8/M out) - Ambient no longer serves deepseek/deepseek-v4-flash (was fp4) - Fireworks no longer serves deepseek/deepseek-v4-flash (was unknown) - Cloudflare no longer serves deepseek/deepseek-v4-pro (was unknown) - Fireworks no longer serves moonshotai/kimi-k3 (was unknown) - Parasail no longer serves moonshotai/kimi-k3 (was fp4) https://variables.md/changelog/2026-08-14/ https://variables.md/changelog/2026-08-14/ Fri, 14 Aug 2026 06:42:43 GMT - Google: Gemini 3.7 Flash (google/gemini-3.7-flash) added to the catalog: 1,048,576 ctx, $0.375/M in / $1.88/M out - Google: Gemini 3.7 Flash (batch) (google/gemini-3.7-flash:batch) added to the catalog: 1,048,576 ctx, $0.188/M in / $0.938/M out - inclusionAI: Ling 3.0 Tiny (free) (inclusionai/ling-3.0-tiny:free) removed from the catalog - ~google/gemini-flash-latest: prompt price $1.5/M → $0.375/M (−75.0%) - ~google/gemini-flash-latest: completion price $7.5/M → $1.88/M (−75.0%) - deepseek/deepseek-v4-flash-0731: prompt price $0.08/M → $0.14/M (+75.0%) - deepseek/deepseek-v4-flash-0731: completion price $0.18/M → $0.28/M (+55.6%) - google/gemini-3.6-flash: prompt price $1.5/M → $0.75/M (−50.0%) - google/gemini-3.6-flash: completion price $7.5/M → $3.75/M (−50.0%) - google/gemini-3.6-flash:batch: prompt price $0.75/M → $0.375/M (−50.0%) - google/gemini-3.6-flash:batch: completion price $3.75/M → $1.88/M (−50.0%) - qwen/qwen3-next-80b-a3b-instruct: prompt price $0.09/M → $0.1/M (+11.1%) - qwen/qwen3-vl-30b-a3b-instruct: prompt price $0.15/M → $0.13/M (−13.3%) - qwen/qwen3-vl-30b-a3b-instruct: completion price $0.6/M → $0.52/M (−13.3%) - z-ai/glm-5.2: prompt price $0.5/M → $0.63/M (+26.0%) - z-ai/glm-5.2: completion price $3.15/M → $1.98/M (−37.1%) - deepseek/deepseek-r1: context length 163,840 → 64,000 - nvidia/nemotron-3.5-lightning: context length 1,048,576 → 1,000,000 - qwen/qwen3.8-2.4t-a95b: context length 1,000,000 → 1,010,000 - StreamLake: minimax/minimax-m3 quantization unknown → fp8 - Phala: z-ai/glm-5.2 quantization unknown → fp8 - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.091/M → $0.084/M (−7.7%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.182/M → $0.168/M (−7.7%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.592/M → $0.522/M (−11.8%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.18/M → $1.04/M (−11.8%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.59/M → $0.522/M (−11.5%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.18/M → $1.04/M (−11.5%) - Google: google/gemini-3.6-flash prompt price $1.5/M → $0.75/M (−50.0%) - Google: google/gemini-3.6-flash completion price $7.5/M → $3.75/M (−50.0%) - Google: google/gemini-3.6-flash prompt price $0.75/M → $0.375/M (−50.0%) - Google: google/gemini-3.6-flash completion price $3.75/M → $1.88/M (−50.0%) - Google: google/gemini-3.6-flash prompt price $2.7/M → $1.35/M (−50.0%) - Google: google/gemini-3.6-flash completion price $13.5/M → $6.75/M (−50.0%) - Google: google/gemini-3.6-flash prompt price $1.65/M → $0.825/M (−50.0%) - Google: google/gemini-3.6-flash completion price $8.25/M → $4.13/M (−50.0%) - Google AI Studio: google/gemini-3.6-flash prompt price $1.5/M → $0.75/M (−50.0%) - Google AI Studio: google/gemini-3.6-flash completion price $7.5/M → $3.75/M (−50.0%) - Google AI Studio: google/gemini-3.6-flash prompt price $0.75/M → $0.375/M (−50.0%) - Google AI Studio: google/gemini-3.6-flash completion price $3.75/M → $1.88/M (−50.0%) - Google AI Studio: google/gemini-3.6-flash prompt price $2.7/M → $1.35/M (−50.0%) - Google AI Studio: google/gemini-3.6-flash completion price $13.5/M → $6.75/M (−50.0%) - GMICloud: minimax/minimax-m2.7 prompt price $0.3/M → $0.27/M (−10.0%) - GMICloud: minimax/minimax-m2.7 completion price $1.2/M → $1.08/M (−10.0%) - StreamLake: minimax/minimax-m3 prompt price $0.6/M → $0.3/M (−50.0%) - StreamLake: minimax/minimax-m3 completion price $2.4/M → $1.2/M (−50.0%) - Decart: moonshotai/kimi-k2.6 prompt price $0.59/M → $0.587/M (−0.6%) - Decart: moonshotai/kimi-k2.6 completion price $3.4/M → $2.47/M (−27.4%) - Decart: z-ai/glm-5.2 prompt price $0.72/M → $0.768/M (+6.7%) - Decart: z-ai/glm-5.2 completion price $2.4/M → $2.56/M (+6.7%) - StreamLake: z-ai/glm-5.2 prompt price $0.753/M → $0.753/M (+0.0%) - StreamLake: z-ai/glm-5.2 completion price $2.37/M → $2.37/M (+0.0%) - DeepInfra: nvidia/nemotron-3.5-lightning context length 1,048,576 → 262,144 - Together: qwen/qwen3.8-2.4t-a95b context length 262,144 → 1,010,000 - Amazon Bedrock now serves anthropic/claude-haiku-4.5 (unknown, 200,000 ctx, $1.1/M in / $5.5/M out) - Amazon Bedrock now serves anthropic/claude-opus-4.6 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Amazon Bedrock now serves anthropic/claude-opus-4.8 (unknown, 1,000,000 ctx, $5.5/M in / $27.5/M out) - Amazon Bedrock now serves anthropic/claude-sonnet-4.6 (unknown, 1,000,000 ctx, $3.3/M in / $16.5/M out) - Cloudflare now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Fireworks now serves deepseek/deepseek-v4-pro-0813 (unknown, 1,048,576 ctx, $1.32/M in / $3.96/M out) - GMICloud now serves deepseek/deepseek-v4-pro-0813 (fp8, 1,048,575 ctx, $1.22/M in / $2.44/M out) - SiliconFlow now serves deepseek/deepseek-v4-pro-0813 (fp8, 1,048,576 ctx, $1.32/M in / $3.96/M out) - Phala now serves meta/muse-glimmer-30b (unknown, 131,072 ctx, $0.35/M in / $1.5/M out) - Nebius now serves minimax/minimax-m2.5 (fp4, 8,000 ctx, $0.3/M in / $1.2/M out) - ModelRun now serves minimax/minimax-m3 (fp4, 1,048,576 ctx, $0.75/M in / $3/M out) - Parasail now serves moonshotai/kimi-k3 (fp4, 1,048,576 ctx, $3/M in / $15/M out) - Alibaba now serves qwen/qwen3.8-2.4t-a95b (unknown, 1,000,000 ctx, $2/M in / $6/M out) - Amazon Bedrock no longer serves anthropic/claude-opus-4.6 (was unknown) - Azure no longer serves deepseek/deepseek-r1 (was unknown) https://variables.md/changelog/2026-08-13/ https://variables.md/changelog/2026-08-13/ Thu, 13 Aug 2026 06:45:26 GMT - ByteDance Seed: Seed 2.1 Turbo (bytedance-seed/seed-2-1-turbo) added to the catalog: 262,144 ctx, $0.5/M in / $2.5/M out - DeepSeek: DeepSeek V4 Pro 0813 (deepseek/deepseek-v4-pro-0813) added to the catalog: 1,048,576 ctx, $0.435/M in / $0.87/M out - Qwen: Qwen3.8 2.4T A95B (qwen/qwen3.8-2.4t-a95b) added to the catalog: 1,000,000 ctx, $2/M in / $6/M out - SpaceXAI: Grok 4.6 (x-ai/grok-4.6) added to the catalog: 500,000 ctx, $2/M in / $6/M out - deepseek/deepseek-v4-pro: prompt price $0.632/M → $1.17/M (+84.9%) - deepseek/deepseek-v4-pro: completion price $1.26/M → $2.34/M (+84.9%) - moonshotai/kimi-k2.7-code: prompt price $0.7/M → $0.67/M (−4.3%) - moonshotai/kimi-k2.7-code: completion price $3.5/M → $3.4/M (−2.9%) - qwen/qwen3.5-35b-a3b: prompt price $0.14/M → $0.25/M (+78.6%) - qwen/qwen3.5-35b-a3b: completion price $1/M → $1.25/M (+25.0%) - z-ai/glm-4.6: prompt price $0.55/M → $0.5/M (−9.1%) - z-ai/glm-4.6: completion price $2.2/M → $2/M (−9.1%) - anthracite-org/magnum-v4-72b: context length 16,384 → 32,768 - nvidia/nemotron-3.5-lightning: context length 262,144 → 1,048,576 - OpenInference: deepseek/deepseek-v4-flash-0731 quantization fp8 → fp4 - StreamLake: deepseek/deepseek-v4-flash-0731 quantization unknown → fp8 - GMICloud: deepseek/deepseek-v4-flash prompt price $0.088/M → $0.087/M (−1.6%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.176/M → $0.174/M (−1.6%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.088/M → $0.087/M (−1.6%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.176/M → $0.173/M (−1.6%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.112/M → $0.091/M (−18.8%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.224/M → $0.182/M (−18.8%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.661/M → $0.592/M (−10.5%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.32/M → $1.18/M (−10.5%) - Novita: deepseek/deepseek-v4-pro prompt price $0.632/M → $1.17/M (+84.9%) - Novita: deepseek/deepseek-v4-pro completion price $1.26/M → $2.34/M (+84.9%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.609/M → $0.59/M (−3.1%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.22/M → $1.18/M (−3.1%) - ModelRun: google/gemma-4-31b-it prompt price $0.25/M → $0.75/M (+200.0%) - ModelRun: google/gemma-4-31b-it completion price $0.65/M → $1/M (+53.8%) - Inceptron: moonshotai/kimi-k2.7-code prompt price $0.7/M → $0.67/M (−4.3%) - Inceptron: moonshotai/kimi-k2.7-code completion price $3.5/M → $3.4/M (−2.9%) - DeepInfra: nvidia/nemotron-3.5-lightning prompt price $0.05/M → $0.08/M (+60.0%) - Io Net: qwen/qwen3.6-27b prompt price $0.31/M → $0.39/M (+25.8%) - Io Net: qwen/qwen3.6-27b completion price $2.19/M → $2.89/M (+32.0%) - GMICloud: z-ai/glm-5.2 prompt price $0.924/M → $0.742/M (−19.7%) - GMICloud: z-ai/glm-5.2 completion price $2.9/M → $2.33/M (−19.7%) - Novita: z-ai/glm-5.2 prompt price $0.752/M → $0.741/M (−1.5%) - Novita: z-ai/glm-5.2 completion price $2.36/M → $2.33/M (−1.5%) - Mancer 2: anthracite-org/magnum-v4-72b context length 16,384 → 32,768 - OpenInference: deepseek/deepseek-v4-flash-0731 context length 1,048,576 → 262,144 - DeepInfra: nvidia/nemotron-3.5-lightning context length 28,672 → 1,048,576 - Google now serves anthropic/claude-sonnet-4.6 (unknown, 1,000,000 ctx, $3.3/M in / $16.5/M out) - Sail Research now serves deepseek/deepseek-v4-flash (fp4, 1,048,576 ctx, $0.09/M in / $0.18/M out) - Relace now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.14/M in / $0.28/M out) - CoreWeave now serves minimax/minimax-m3 (fp4, 262,144 ctx, $0.23/M in / $0.96/M out) - StreamLake now serves minimax/minimax-m3 (unknown, 1,000,000 ctx, $0.6/M in / $2.4/M out) - Phala now serves moonshotai/kimi-k3 (unknown, 1,048,576 ctx, $3/M in / $15/M out) - Venice now serves nvidia/nemotron-3.5-lightning (fp4, 1,000,000 ctx, $0.1/M in / $0.25/M out) - SambaNova no longer serves minimax/minimax-m2.7 (was unknown) https://variables.md/changelog/2026-08-12/ https://variables.md/changelog/2026-08-12/ Wed, 12 Aug 2026 06:42:40 GMT - ByteDance Seed: Seed-2.0-Code (bytedance-seed/seed-2.0-code) added to the catalog: 262,144 ctx, $0.5/M in / $3/M out - LiquidAI: LFM2.5-2.6B (free) (liquid/lfm-2.5-2.6b:free) added to the catalog: 128,000 ctx, $0/M in / $0/M out - NVIDIA: Nemotron 3.5 Lightning (nvidia/nemotron-3.5-lightning) added to the catalog: 262,144 ctx, $0.1/M in / $0.25/M out - NVIDIA: Nemotron 3.5 Lightning (free) (nvidia/nemotron-3.5-lightning:free) added to the catalog: 1,000,000 ctx, $0/M in / $0/M out - deepseek/deepseek-v3.1-terminus: completion price $1/M → $0.95/M (−5.0%) - deepseek/deepseek-v4-pro: prompt price $0.651/M → $0.632/M (−3.0%) - deepseek/deepseek-v4-pro: completion price $1.3/M → $1.26/M (−3.0%) - openai/gpt-oss-120b: prompt price $0.037/M → $0.03/M (−18.9%) - qwen/qwen3-vl-235b-a22b-instruct: prompt price $0.21/M → $0.26/M (+23.8%) - qwen/qwen3-vl-235b-a22b-instruct: completion price $1.9/M → $1.04/M (−45.3%) - z-ai/glm-4.6: prompt price $0.5/M → $0.55/M (+10.0%) - z-ai/glm-4.6: completion price $2/M → $2.2/M (+10.0%) - z-ai/glm-5.2: prompt price $0.76/M → $0.5/M (−34.2%) - z-ai/glm-5.2: completion price $2.42/M → $3.15/M (+30.2%) - AtlasCloud: deepseek/deepseek-v4-flash-0731 quantization fp8 → fp4 - Cloudflare: deepseek/deepseek-v4-flash-0731 quantization fp8 → unknown - Morph: deepseek/deepseek-v4-flash-0731 quantization unknown → bf16 - SambaNova: meta-llama/llama-3.3-70b-instruct quantization bf16 → unknown - Together: meta-llama/llama-3.3-70b-instruct quantization fp8 → unknown - Morph: minimax/minimax-m3 quantization unknown → fp4 - Ambient: moonshotai/kimi-k2.7-code quantization int4 → unknown - Morph: moonshotai/kimi-k3 quantization unknown → fp4 - Morph: moonshotai/kimi-k3 quantization unknown → fp4 - Wafer: moonshotai/kimi-k3 quantization fp8 → unknown - Morph: morph/morph-v3-large quantization unknown → fp8 - Nex AGI: nex-agi/nex-n2-mini quantization fp8 → unknown - Together: qwen/qwen-2.5-7b-instruct quantization fp8 → unknown - Alibaba: qwen/qwen-plus quantization fp8 → unknown - Alibaba: qwen/qwen3-14b quantization fp8 → unknown - Alibaba: qwen/qwen3-235b-a22b quantization fp8 → unknown - Alibaba: qwen/qwen3-235b-a22b-2507 quantization fp8 → unknown - Alibaba: qwen/qwen3-235b-a22b-thinking-2507 quantization fp8 → unknown - Alibaba: qwen/qwen3-30b-a3b quantization fp8 → unknown - Alibaba: qwen/qwen3-30b-a3b-instruct-2507 quantization fp8 → unknown - Alibaba: qwen/qwen3-30b-a3b-thinking-2507 quantization fp8 → unknown - Alibaba: qwen/qwen3-8b quantization fp8 → unknown - Alibaba: qwen/qwen3-coder quantization fp8 → unknown - Alibaba: qwen/qwen3-coder-30b-a3b-instruct quantization fp8 → unknown - Alibaba: qwen/qwen3-coder-flash quantization fp8 → unknown - Alibaba: qwen/qwen3-coder-plus quantization fp8 → unknown - Alibaba: qwen/qwen3-max quantization fp8 → unknown - Alibaba: qwen/qwen3-max-thinking quantization fp8 → unknown - Alibaba: qwen/qwen3-next-80b-a3b-instruct quantization fp8 → unknown - Alibaba: qwen/qwen3-next-80b-a3b-thinking quantization fp8 → unknown - Alibaba: qwen/qwen3-vl-235b-a22b-instruct quantization fp8 → unknown - Alibaba: qwen/qwen3-vl-235b-a22b-thinking quantization fp8 → unknown - Alibaba: qwen/qwen3-vl-30b-a3b-instruct quantization fp8 → unknown - Alibaba: qwen/qwen3-vl-30b-a3b-thinking quantization fp8 → unknown - Alibaba: qwen/qwen3-vl-32b-instruct quantization fp8 → unknown - Alibaba: qwen/qwen3-vl-8b-instruct quantization fp8 → unknown - Alibaba: qwen/qwen3-vl-8b-thinking quantization fp8 → unknown - Alibaba: qwen/qwen3.5-122b-a10b quantization fp8 → unknown - Alibaba: qwen/qwen3.5-27b quantization fp8 → unknown - Alibaba: qwen/qwen3.5-35b-a3b quantization fp8 → unknown - Alibaba: qwen/qwen3.5-397b-a17b quantization fp8 → unknown - Alibaba: qwen/qwen3.5-flash-02-23 quantization fp8 → unknown - Alibaba: qwen/qwen3.5-plus-02-15 quantization fp8 → unknown - Alibaba: qwen/qwen3.5-plus-20260420 quantization fp8 → unknown - Alibaba: qwen/qwen3.6-27b quantization fp8 → unknown - Morph: qwen/qwen3.6-27b quantization unknown → fp4 - Alibaba: qwen/qwen3.6-flash quantization fp8 → unknown - Alibaba: qwen/qwen3.6-max-preview quantization fp8 → unknown - Alibaba: qwen/qwen3.6-plus quantization fp8 → unknown - Alibaba: qwen/qwen3.7-max quantization fp8 → unknown - Alibaba: qwen/qwen3.7-plus quantization fp8 → unknown - Upstage: upstage/solar-pro-3 quantization fp4 → unknown - Upstage: upstage/solar-pro4 quantization bf16 → unknown - Morph: z-ai/glm-5.2 quantization unknown → fp4 - GMICloud: deepseek/deepseek-v4-flash prompt price $0.094/M → $0.088/M (−6.0%) - GMICloud: deepseek/deepseek-v4-flash completion price $0.188/M → $0.176/M (−6.0%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.09/M → $0.088/M (−2.0%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.18/M → $0.176/M (−2.0%) - Decart: deepseek/deepseek-v4-flash-0731 prompt price $0.09/M → $0.081/M (−10.0%) - Decart: deepseek/deepseek-v4-flash-0731 completion price $0.18/M → $0.162/M (−10.0%) - Novita: deepseek/deepseek-v4-pro prompt price $0.651/M → $0.632/M (−3.0%) - Novita: deepseek/deepseek-v4-pro completion price $1.3/M → $1.26/M (−3.0%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.65/M → $0.609/M (−6.2%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.3/M → $1.22/M (−6.2%) - Ambient: moonshotai/kimi-k2.7-code prompt price $0.7/M → $0.69/M (−1.4%) - Ambient: moonshotai/kimi-k2.7-code completion price $3.5/M → $3.49/M (−0.3%) - Decart: z-ai/glm-5.2 completion price $2.1/M → $2.4/M (+14.3%) - DigitalOcean: z-ai/glm-5.2 prompt price $1.4/M → $0.63/M (−55.0%) - DigitalOcean: z-ai/glm-5.2 completion price $4.4/M → $1.98/M (−55.0%) - Novita: z-ai/glm-5.2 prompt price $0.938/M → $0.752/M (−19.9%) - Novita: z-ai/glm-5.2 completion price $2.95/M → $2.36/M (−19.9%) - Phala: z-ai/glm-5.2 completion price $3.56/M → $3/M (−15.8%) - AtlasCloud: deepseek/deepseek-v4-flash-0731 context length 262,144 → 1,048,576 - Nebius: nvidia/nemotron-3-super-120b-a12b context length 262,144 → 8,000 - Nebius: qwen/qwen3-next-80b-a3b-thinking context length 128,000 → 8,000 - Inceptron now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.13/M in / $0.28/M out) - OpenInference now serves deepseek/deepseek-v4-flash-0731 (fp8, 1,048,576 ctx, $0.08/M in / $0.18/M out) - Google now serves google/gemini-3.6-flash (unknown, 1,048,576 ctx, $1.65/M in / $8.25/M out) - DeepInfra now serves google/gemma-4-31b-it (fp8, 131,072 ctx, $0.27/M in / $0.76/M out) - DeepInfra now serves meta/muse-glimmer-30b (bf16, 131,072 ctx, $0.3/M in / $1.2/M out) - Fireworks now serves meta/muse-glimmer-30b (unknown, 131,072 ctx, $0.35/M in / $1.5/M out) - Morph no longer serves deepseek/deepseek-v4-flash (was unknown) - OpenInference no longer serves deepseek/deepseek-v4-flash (was fp8) - Sail Research no longer serves deepseek/deepseek-v4-flash (was fp4) - Ionstream no longer serves deepseek/deepseek-v4-flash-0731 (was fp4) - Alibaba no longer serves qwen/qwen3-32b (was fp8) - Venice no longer serves xiaomi/mimo-v2.5 (was fp8) - Phala no longer serves z-ai/glm-5 (was unknown) https://variables.md/changelog/2026-08-11/ https://variables.md/changelog/2026-08-11/ Tue, 11 Aug 2026 06:04:29 GMT - Meta: Muse Glimmer 30B (meta/muse-glimmer-30b) added to the catalog: 131,072 ctx, $0.35/M in / $1.5/M out - Sakana: Sakana Namazu (sakana/sakana-namazu) added to the catalog: 262,144 ctx, $0.95/M in / $4/M out - Upstage: Solar Pro 4 (upstage/solar-pro4) added to the catalog: 524,288 ctx, $0.03/M in / $0.12/M out - OpenAI: GPT-5.3 Chat (openai/gpt-5.3-chat) removed from the catalog - deepseek/deepseek-v4-flash-0731: prompt price $0.09/M → $0.08/M (−11.1%) - deepseek/deepseek-v4-pro: prompt price $0.435/M → $0.651/M (+49.7%) - deepseek/deepseek-v4-pro: completion price $0.87/M → $1.3/M (+49.7%) - qwen/qwen3-coder-30b-a3b-instruct: completion price $0.27/M → $0.28/M (+3.7%) - qwen/qwen3.5-397b-a17b: prompt price $0.39/M → $0.5/M (+28.2%) - qwen/qwen3.5-397b-a17b: completion price $2.34/M → $3.6/M (+53.8%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.094/M → $0.09/M (−4.1%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.187/M → $0.18/M (−4.1%) - DeepInfra: deepseek/deepseek-v4-flash-0731 prompt price $0.09/M → $0.08/M (−11.1%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.112/M → $0.105/M (−6.1%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.224/M → $0.21/M (−6.1%) - Novita: deepseek/deepseek-v4-pro prompt price $0.6/M → $0.651/M (+8.6%) - Novita: deepseek/deepseek-v4-pro completion price $1.2/M → $1.3/M (+8.6%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.591/M → $0.65/M (+9.9%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.18/M → $1.3/M (+9.9%) - ModelRun: google/gemma-4-31b-it prompt price $0.22/M → $0.25/M (+13.6%) - ModelRun: google/gemma-4-31b-it completion price $0.55/M → $0.65/M (+18.2%) - Azure: openai/gpt-5.6-luna prompt price $1/M → $0.2/M (−80.0%) - Azure: openai/gpt-5.6-luna completion price $6/M → $1.2/M (−80.0%) - Azure: openai/gpt-5.6-luna prompt price $1.1/M → $0.22/M (−80.0%) - Azure: openai/gpt-5.6-luna completion price $6.6/M → $1.32/M (−80.0%) - Azure: openai/gpt-5.6-luna-pro prompt price $1/M → $0.2/M (−80.0%) - Azure: openai/gpt-5.6-luna-pro completion price $6/M → $1.2/M (−80.0%) - Azure: openai/gpt-5.6-luna-pro prompt price $1.1/M → $0.22/M (−80.0%) - Azure: openai/gpt-5.6-luna-pro completion price $6.6/M → $1.32/M (−80.0%) - Azure: openai/gpt-5.6-terra prompt price $2.5/M → $2/M (−20.0%) - Azure: openai/gpt-5.6-terra completion price $15/M → $12/M (−20.0%) - Azure: openai/gpt-5.6-terra prompt price $2.75/M → $2.2/M (−20.0%) - Azure: openai/gpt-5.6-terra completion price $16.5/M → $13.2/M (−20.0%) - Azure: openai/gpt-5.6-terra-pro prompt price $2.5/M → $2/M (−20.0%) - Azure: openai/gpt-5.6-terra-pro completion price $15/M → $12/M (−20.0%) - Azure: openai/gpt-5.6-terra-pro prompt price $2.75/M → $2.2/M (−20.0%) - Azure: openai/gpt-5.6-terra-pro completion price $16.5/M → $13.2/M (−20.0%) - Decart: z-ai/glm-5.2 completion price $1.8/M → $2.1/M (+16.7%) - Novita: z-ai/glm-5.2 prompt price $0.419/M → $0.938/M (+124.1%) - Novita: z-ai/glm-5.2 completion price $1.32/M → $2.95/M (+124.1%) - Sail Research: z-ai/glm-5.2 prompt price $0.9/M → $0.5/M (−44.4%) - StreamLake: z-ai/glm-5.2 prompt price $0.42/M → $0.753/M (+79.3%) - StreamLake: z-ai/glm-5.2 completion price $1.32/M → $2.37/M (+79.3%) - Sail Research: deepseek/deepseek-v4-flash-0731 context length 1,048,576 → 262,144 - Sail Research now serves deepseek/deepseek-v4-flash (fp4, 1,048,576 ctx, $0.09/M in / $0.18/M out) - Sail Research now serves moonshotai/kimi-k3 (fp4, 974,842 ctx, $3/M in / $15/M out) - Ionstream no longer serves google/gemma-4-26b-a4b-it (was bf16) - OpenAI no longer serves openai/gpt-5.2-chat (was unknown) - Ionstream no longer serves qwen/qwen3-coder-next (was fp8) - NextBit no longer serves qwen/qwen3.5-35b-a3b (was fp8) https://variables.md/changelog/2026-08-10/ https://variables.md/changelog/2026-08-10/ Mon, 10 Aug 2026 06:42:28 GMT - deepseek/deepseek-v3.2: prompt price $0.26/M → $0.269/M (+3.5%) - deepseek/deepseek-v3.2: completion price $0.38/M → $0.4/M (+5.3%) - google/gemma-4-26b-a4b-it: prompt price $0.07/M → $0.12/M (+71.4%) - google/gemma-4-26b-a4b-it: completion price $0.34/M → $0.4/M (+17.6%) - gryphe/mythomax-l2-13b: prompt price $0.08/M → $0.06/M (−25.0%) - gryphe/mythomax-l2-13b: completion price $0.11/M → $0.06/M (−45.5%) - meta-llama/llama-4-maverick: completion price $0.8/M → $0.696/M (−13.0%) - moonshotai/kimi-k2.6: prompt price $0.58/M → $0.95/M (+63.9%) - moonshotai/kimi-k2.6: completion price $2.44/M → $4/M (+63.9%) - nvidia/nemotron-3-super-120b-a12b: prompt price $0.3/M → $0.085/M (−71.7%) - nvidia/nemotron-3-super-120b-a12b: completion price $0.9/M → $0.4/M (−55.6%) - qwen/qwen3-14b: prompt price $0.227/M → $0.12/M (−47.3%) - qwen/qwen3-14b: completion price $0.91/M → $0.24/M (−73.6%) - z-ai/glm-5.1: prompt price $0.952/M → $1.4/M (+47.1%) - z-ai/glm-5.1: completion price $2.99/M → $4.4/M (+47.1%) - z-ai/glm-5.2: prompt price $0.098/M → $0.76/M (+675.5%) - z-ai/glm-5.2: completion price $0.308/M → $2.42/M (+685.7%) - Baidu: deepseek/deepseek-v3.2 prompt price $0.207/M → $0.28/M (+35.1%) - Baidu: deepseek/deepseek-v3.2 completion price $0.311/M → $0.42/M (+35.1%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.069/M → $0.14/M (+104.1%) - Baidu: deepseek/deepseek-v4-flash completion price $0.137/M → $0.28/M (+104.1%) - DigitalOcean: deepseek/deepseek-v4-flash prompt price $0.084/M → $0.068/M (−19.2%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.068/M → $0.094/M (+36.8%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.137/M → $0.187/M (+36.8%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.09/M → $0.14/M (+56.3%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.179/M → $0.28/M (+56.3%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.112/M (−20.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.224/M (−20.0%) - Io Net: deepseek/deepseek-v4-flash-0731 prompt price $0.16/M → $0.149/M (−6.9%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.112/M → $0.112/M (−0.1%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.224/M → $0.224/M (−0.1%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.422/M → $1.69/M (+300.0%) - Baidu: deepseek/deepseek-v4-pro completion price $0.845/M → $3.38/M (+300.0%) - Cloudflare: deepseek/deepseek-v4-pro prompt price $1.17/M → $1.15/M (−1.5%) - Cloudflare: deepseek/deepseek-v4-pro completion price $2.34/M → $2.55/M (+9.2%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.11/M → $0.591/M (+439.0%) - StreamLake: deepseek/deepseek-v4-pro completion price $0.219/M → $1.18/M (+439.0%) - DeepInfra: inclusionai/ling-3.0-flash prompt price $0.03/M → $0.06/M (+100.0%) - DeepInfra: inclusionai/ling-3.0-flash completion price $0.07/M → $0.18/M (+157.1%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.58/M → $0.95/M (+63.9%) - Baidu: moonshotai/kimi-k2.6 completion price $2.44/M → $4/M (+63.9%) - StreamLake: moonshotai/kimi-k2.6 prompt price $0.674/M → $0.598/M (−11.3%) - StreamLake: moonshotai/kimi-k2.6 completion price $2.84/M → $2.52/M (−11.3%) - Mancer 2: openai/gpt-oss-120b prompt price $0.09/M → $0.085/M (−5.6%) - Baidu: z-ai/glm-5.1 prompt price $0.952/M → $1.4/M (+47.1%) - Baidu: z-ai/glm-5.1 completion price $2.99/M → $4.4/M (+47.1%) - Baidu: z-ai/glm-5.2 prompt price $0.112/M → $1.4/M (+1150.0%) - Baidu: z-ai/glm-5.2 completion price $0.352/M → $4.4/M (+1150.0%) - Novita: z-ai/glm-5.2 prompt price $0.22/M → $0.419/M (+90.4%) - Novita: z-ai/glm-5.2 completion price $0.691/M → $1.32/M (+90.4%) - StreamLake: z-ai/glm-5.2 prompt price $0.098/M → $0.42/M (+328.6%) - StreamLake: z-ai/glm-5.2 completion price $0.308/M → $1.32/M (+328.6%) - Cloudflare: deepseek/deepseek-v4-pro context length 393,216 → 1,048,576 - Decart now serves deepseek/deepseek-v4-flash-0731 (fp4, 262,144 ctx, $0.09/M in / $0.18/M out) - Sail Research now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.09/M in / $0.18/M out) https://variables.md/changelog/2026-08-09/ https://variables.md/changelog/2026-08-09/ Sun, 09 Aug 2026 05:58:06 GMT - ~deepseek/deepseek-v4-flash-latest: prompt price $0.09/M → $0.08/M (−11.1%) - ~deepseek/deepseek-v4-flash-latest: completion price $0.18/M → $0.252/M (+40.0%) - ~moonshotai/kimi-latest: prompt price $2.5/M → $2.8/M (+12.0%) - minimax/minimax-m2.7: prompt price $0.27/M → $0.3/M (+11.1%) - minimax/minimax-m2.7: completion price $1.08/M → $1.2/M (+11.1%) - nvidia/nemotron-3-super-120b-a12b: prompt price $0.085/M → $0.3/M (+252.9%) - nvidia/nemotron-3-super-120b-a12b: completion price $0.4/M → $0.9/M (+125.0%) - qwen/qwen3.6-35b-a3b: prompt price $0.14/M → $0.15/M (+7.1%) - z-ai/glm-5.2: prompt price $0.318/M → $0.098/M (−69.2%) - z-ai/glm-5.2: completion price $0.999/M → $0.308/M (−69.2%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.2/M → $0.175/M (−12.5%) - Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.09/M (−36.0%) - Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.179/M (−36.0%) - DigitalOcean: deepseek/deepseek-v4-flash-0731 prompt price $0.126/M → $0.08/M (−36.5%) - Ionstream: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.21/M (+50.0%) - Ionstream: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.42/M (+50.0%) - StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.112/M (−20.0%) - StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.224/M (−20.0%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.304/M → $0.422/M (+38.9%) - Baidu: deepseek/deepseek-v4-pro completion price $0.608/M → $0.845/M (+38.9%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.295/M → $0.11/M (−62.9%) - StreamLake: deepseek/deepseek-v4-pro completion price $0.591/M → $0.219/M (−62.9%) - DeepInfra: inclusionai/ling-3.0-flash prompt price $0.075/M → $0.03/M (−60.0%) - DeepInfra: inclusionai/ling-3.0-flash completion price $0.22/M → $0.07/M (−68.2%) - Morph: moonshotai/kimi-k3 prompt price $2.5/M → $2.8/M (+12.0%) - Baidu: z-ai/glm-5.2 prompt price $0.322/M → $0.112/M (−65.2%) - Baidu: z-ai/glm-5.2 completion price $1.01/M → $0.352/M (−65.2%) - Novita: z-ai/glm-5.2 prompt price $0.33/M → $0.22/M (−33.5%) - Novita: z-ai/glm-5.2 completion price $1.04/M → $0.691/M (−33.5%) - StreamLake: z-ai/glm-5.2 prompt price $0.318/M → $0.098/M (−69.2%) - StreamLake: z-ai/glm-5.2 completion price $0.999/M → $0.308/M (−69.2%) - BaseTen: z-ai/glm-5.2 context length 524,288 → 1,048,576 - Wafer now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,048,576 ctx, $0.28/M in / $0.56/M out) - DeepInfra now serves moonshotai/kimi-k3 (bf16, 1,048,576 ctx, $2.85/M in / $14.3/M out) - Wafer no longer serves deepseek/deepseek-v4-flash-0731 (was unknown) - Wafer no longer serves moonshotai/kimi-k3 (was fp8) https://variables.md/changelog/2026-08-08/ https://variables.md/changelog/2026-08-08/ Sat, 08 Aug 2026 05:56:33 GMT - deepseek/deepseek-v3.2: prompt price $0.269/M → $0.26/M (−3.3%) - deepseek/deepseek-v3.2: completion price $0.4/M → $0.38/M (−5.0%) - deepseek/deepseek-v4-flash: prompt price $0.088/M → $0.14/M (+58.7%) - deepseek/deepseek-v4-flash: completion price $0.176/M → $0.28/M (+58.7%) - moonshotai/kimi-k2.6: prompt price $0.589/M → $0.58/M (−1.6%) - moonshotai/kimi-k2.6: completion price $2.48/M → $2.44/M (−1.6%) - nvidia/nemotron-3-super-120b-a12b: prompt price $0.3/M → $0.085/M (−71.7%) - nvidia/nemotron-3-super-120b-a12b: completion price $0.9/M → $0.4/M (−55.6%) - thinkingmachines/inkling: prompt price $1/M → $0.95/M (−5.0%) - z-ai/glm-5.2: prompt price $0.687/M → $0.318/M (−53.8%) - z-ai/glm-5.2: completion price $2.16/M → $0.999/M (−53.8%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.088/M → $0.069/M (−22.2%) - Baidu: deepseek/deepseek-v4-flash completion price $0.176/M → $0.137/M (−22.2%) - OpenInference: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.07/M (−50.0%) - OpenInference: deepseek/deepseek-v4-flash completion price $0.28/M → $0.18/M (−35.7%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.088/M → $0.068/M (−22.3%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.176/M → $0.137/M (−22.3%) - DigitalOcean: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.126/M (−10.0%) - DigitalOcean: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.252/M (−10.0%) - Baidu: deepseek/deepseek-v4-pro prompt price $1.23/M → $0.304/M (−75.3%) - Baidu: deepseek/deepseek-v4-pro completion price $2.47/M → $0.608/M (−75.3%) - CoreWeave: deepseek/deepseek-v4-pro prompt price $1.74/M → $1.15/M (−33.9%) - CoreWeave: deepseek/deepseek-v4-pro completion price $3.48/M → $2.55/M (−26.7%) - Novita: deepseek/deepseek-v4-pro prompt price $1.17/M → $0.6/M (−48.7%) - Novita: deepseek/deepseek-v4-pro completion price $2.34/M → $1.2/M (−48.7%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.652/M → $0.295/M (−54.7%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.3/M → $0.591/M (−54.7%) - OpenInference: google/gemma-4-31b-it prompt price $0.1/M → $0.08/M (−20.0%) - Mancer 2: gryphe/mythomax-l2-13b prompt price $0.45/M → $0.4/M (−11.1%) - Mancer 2: gryphe/mythomax-l2-13b completion price $0.65/M → $0.6/M (−7.7%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.589/M → $0.58/M (−1.6%) - Baidu: moonshotai/kimi-k2.6 completion price $2.48/M → $2.44/M (−1.6%) - DigitalOcean: moonshotai/kimi-k3 prompt price $3/M → $2.85/M (−5.0%) - DigitalOcean: moonshotai/kimi-k3 completion price $15/M → $14.3/M (−5.0%) - GMICloud: xiaomi/mimo-v2.5 prompt price $0.112/M → $0.14/M (+25.0%) - GMICloud: xiaomi/mimo-v2.5 completion price $0.224/M → $0.28/M (+25.0%) - GMICloud: xiaomi/mimo-v2.5-pro prompt price $0.348/M → $0.435/M (+25.0%) - GMICloud: xiaomi/mimo-v2.5-pro completion price $0.696/M → $0.87/M (+25.0%) - Baidu: z-ai/glm-5.2 prompt price $1.18/M → $0.322/M (−72.6%) - Baidu: z-ai/glm-5.2 completion price $3.7/M → $1.01/M (−72.6%) - DigitalOcean: z-ai/glm-5.2 prompt price $0.7/M → $1.4/M (+100.0%) - DigitalOcean: z-ai/glm-5.2 completion price $2.2/M → $4.4/M (+100.0%) - Novita: z-ai/glm-5.2 prompt price $0.687/M → $0.33/M (−51.9%) - Novita: z-ai/glm-5.2 completion price $2.16/M → $1.04/M (−51.9%) - StreamLake: z-ai/glm-5.2 prompt price $0.689/M → $0.318/M (−53.9%) - StreamLake: z-ai/glm-5.2 completion price $2.16/M → $0.999/M (−53.9%) - DigitalOcean: deepseek/deepseek-v4-pro context length 262,144 → 1,048,576 - Wafer now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,048,576 ctx, $0.28/M in / $0.56/M out) - Google now serves google/gemini-3.1-flash-lite (unknown, 1,048,576 ctx, $0.275/M in / $1.65/M out) - Google now serves google/gemini-3.5-flash (unknown, 1,048,576 ctx, $1.65/M in / $9.9/M out) - Google now serves google/gemini-3.5-flash-lite (unknown, 1,048,576 ctx, $0.33/M in / $2.75/M out) - AkashML now serves openai/gpt-oss-120b (bf16, 131,072 ctx, $0.037/M in / $0.49/M out) - Azure no longer serves openai/gpt-5.3-chat (was unknown) https://variables.md/changelog/2026-08-07/ https://variables.md/changelog/2026-08-07/ Fri, 07 Aug 2026 06:19:19 GMT - Anthropic: Claude Fable 5 (batch) (anthropic/claude-fable-5:batch) added to the catalog: 1,000,000 ctx, $5/M in / $25/M out - Anthropic: Claude Haiku 4.5 (batch) (anthropic/claude-haiku-4.5:batch) added to the catalog: 200,000 ctx, $0.5/M in / $2.5/M out - Anthropic: Claude Opus 4.1 (batch) (anthropic/claude-opus-4.1:batch) added to the catalog: 200,000 ctx, $7.5/M in / $37.5/M out - Anthropic: Claude Opus 4.5 (batch) (anthropic/claude-opus-4.5:batch) added to the catalog: 200,000 ctx, $2.5/M in / $12.5/M out - Anthropic: Claude Opus 4.6 (batch) (anthropic/claude-opus-4.6:batch) added to the catalog: 1,000,000 ctx, $2.5/M in / $12.5/M out - Anthropic: Claude Opus 4.7 (batch) (anthropic/claude-opus-4.7:batch) added to the catalog: 1,000,000 ctx, $2.5/M in / $12.5/M out - Anthropic: Claude Opus 4.8 (batch) (anthropic/claude-opus-4.8:batch) added to the catalog: 1,000,000 ctx, $2.5/M in / $12.5/M out - Claude Opus 5 (batch) (anthropic/claude-opus-5:batch) added to the catalog: 1,000,000 ctx, $2.5/M in / $12.5/M out - Anthropic: Claude Sonnet 4.5 (batch) (anthropic/claude-sonnet-4.5:batch) added to the catalog: 1,000,000 ctx, $1.5/M in / $7.5/M out - Anthropic: Claude Sonnet 4.6 (batch) (anthropic/claude-sonnet-4.6:batch) added to the catalog: 1,000,000 ctx, $1.5/M in / $7.5/M out - Anthropic: Claude Sonnet 5 (batch) (anthropic/claude-sonnet-5:batch) added to the catalog: 1,000,000 ctx, $1/M in / $5/M out - Google: Gemini 2.5 Flash Lite (batch) (google/gemini-2.5-flash-lite:batch) added to the catalog: 1,048,576 ctx, $0.05/M in / $0.2/M out - Google: Gemini 2.5 Flash (batch) (google/gemini-2.5-flash:batch) added to the catalog: 1,048,576 ctx, $0.15/M in / $1.25/M out - Google: Gemini 2.5 Pro (batch) (google/gemini-2.5-pro:batch) added to the catalog: 1,048,576 ctx, $0.625/M in / $5/M out - Google: Gemini 3 Flash Preview (batch) (google/gemini-3-flash-preview:batch) added to the catalog: 1,048,576 ctx, $0.25/M in / $1.5/M out - Google: Gemini 3.1 Flash Lite (batch) (google/gemini-3.1-flash-lite:batch) added to the catalog: 1,048,576 ctx, $0.125/M in / $0.75/M out - Google: Gemini 3.1 Pro Preview (batch) (google/gemini-3.1-pro-preview:batch) added to the catalog: 1,048,576 ctx, $1/M in / $6/M out - Google: Gemini 3.5 Flash Lite (batch) (google/gemini-3.5-flash-lite:batch) added to the catalog: 1,048,576 ctx, $0.15/M in / $1.25/M out - Google: Gemini 3.5 Flash (batch) (google/gemini-3.5-flash:batch) added to the catalog: 1,048,576 ctx, $0.75/M in / $4.5/M out - Google: Gemini 3.6 Flash (batch) (google/gemini-3.6-flash:batch) added to the catalog: 1,048,576 ctx, $0.75/M in / $3.75/M out - inclusionAI: Ling 3.0 Tiny (free) (inclusionai/ling-3.0-tiny:free) added to the catalog: 262,144 ctx, $0/M in / $0/M out - MiniMax: MiniMax M3 (batch) (minimax/minimax-m3:batch) added to the catalog: 524,288 ctx, $0.15/M in / $0.6/M out - MoonshotAI: Kimi K2.7 Code (batch) (moonshotai/kimi-k2.7-code:batch) added to the catalog: 262,144 ctx, $0.475/M in / $2/M out - NVIDIA: Nemotron 3 Ultra (batch) (nvidia/nemotron-3-ultra-550b-a55b:batch) added to the catalog: 512,288 ctx, $0.3/M in / $1.8/M out - OpenAI: GPT-3.5 Turbo (batch) (openai/gpt-3.5-turbo:batch) added to the catalog: 16,385 ctx, $0.25/M in / $0.75/M out - OpenAI: GPT-4 Turbo (batch) (openai/gpt-4-turbo:batch) added to the catalog: 128,000 ctx, $5/M in / $15/M out - OpenAI: GPT-4.1 Mini (batch) (openai/gpt-4.1-mini:batch) added to the catalog: 1,047,576 ctx, $0.2/M in / $0.8/M out - OpenAI: GPT-4.1 Nano (batch) (openai/gpt-4.1-nano:batch) added to the catalog: 1,047,576 ctx, $0.05/M in / $0.2/M out - OpenAI: GPT-4.1 (batch) (openai/gpt-4.1:batch) added to the catalog: 1,047,576 ctx, $1/M in / $4/M out - OpenAI: GPT-4o-mini (batch) (openai/gpt-4o-mini:batch) added to the catalog: 128,000 ctx, $0.075/M in / $0.3/M out - OpenAI: GPT-4o (batch) (openai/gpt-4o:batch) added to the catalog: 128,000 ctx, $1.25/M in / $5/M out - OpenAI: GPT-5 Codex (batch) (openai/gpt-5-codex:batch) added to the catalog: 400,000 ctx, $0.625/M in / $5/M out - OpenAI: GPT-5 Mini (batch) (openai/gpt-5-mini:batch) added to the catalog: 400,000 ctx, $0.125/M in / $1/M out - OpenAI: GPT-5 Nano (batch) (openai/gpt-5-nano:batch) added to the catalog: 400,000 ctx, $0.025/M in / $0.2/M out - OpenAI: GPT-5 Pro (batch) (openai/gpt-5-pro:batch) added to the catalog: 400,000 ctx, $7.5/M in / $60/M out - OpenAI: GPT-5 (batch) (openai/gpt-5:batch) added to the catalog: 400,000 ctx, $0.625/M in / $5/M out - OpenAI: GPT-5.1 (batch) (openai/gpt-5.1:batch) added to the catalog: 400,000 ctx, $0.625/M in / $5/M out - OpenAI: GPT-5.2 Pro (batch) (openai/gpt-5.2-pro:batch) added to the catalog: 400,000 ctx, $10.5/M in / $84/M out - OpenAI: GPT-5.2 (batch) (openai/gpt-5.2:batch) added to the catalog: 400,000 ctx, $0.875/M in / $7/M out - OpenAI: GPT-5.4 Mini (batch) (openai/gpt-5.4-mini:batch) added to the catalog: 400,000 ctx, $0.375/M in / $2.25/M out - OpenAI: GPT-5.4 Nano (batch) (openai/gpt-5.4-nano:batch) added to the catalog: 400,000 ctx, $0.1/M in / $0.625/M out - OpenAI: GPT-5.4 Pro (batch) (openai/gpt-5.4-pro:batch) added to the catalog: 1,050,000 ctx, $15/M in / $90/M out - OpenAI: GPT-5.4 (batch) (openai/gpt-5.4:batch) added to the catalog: 1,050,000 ctx, $1.25/M in / $7.5/M out - OpenAI: GPT-5.5 Pro (batch) (openai/gpt-5.5-pro:batch) added to the catalog: 1,050,000 ctx, $15/M in / $90/M out - OpenAI: GPT-5.5 (batch) (openai/gpt-5.5:batch) added to the catalog: 1,050,000 ctx, $2.5/M in / $15/M out - OpenAI: GPT-5.6 Luna Pro (batch) (openai/gpt-5.6-luna-pro:batch) added to the catalog: 1,050,000 ctx, $0.1/M in / $0.6/M out - OpenAI: GPT-5.6 Luna (batch) (openai/gpt-5.6-luna:batch) added to the catalog: 1,050,000 ctx, $0.1/M in / $0.6/M out - OpenAI: GPT-5.6 Sol Pro (batch) (openai/gpt-5.6-sol-pro:batch) added to the catalog: 1,050,000 ctx, $2.5/M in / $15/M out - OpenAI: GPT-5.6 Sol (batch) (openai/gpt-5.6-sol:batch) added to the catalog: 1,050,000 ctx, $2.5/M in / $15/M out - OpenAI: GPT-5.6 Terra Pro (batch) (openai/gpt-5.6-terra-pro:batch) added to the catalog: 1,050,000 ctx, $1/M in / $6/M out - OpenAI: GPT-5.6 Terra (batch) (openai/gpt-5.6-terra:batch) added to the catalog: 1,050,000 ctx, $1/M in / $6/M out - OpenAI: o1-pro (batch) (openai/o1-pro:batch) added to the catalog: 200,000 ctx, $75/M in / $300/M out - OpenAI: o1 (batch) (openai/o1:batch) added to the catalog: 200,000 ctx, $7.5/M in / $30/M out - OpenAI: o3 Mini High (batch) (openai/o3-mini-high:batch) added to the catalog: 200,000 ctx, $0.55/M in / $2.2/M out - OpenAI: o3 Mini (batch) (openai/o3-mini:batch) added to the catalog: 200,000 ctx, $0.55/M in / $2.2/M out - OpenAI: o3 Pro (batch) (openai/o3-pro:batch) added to the catalog: 200,000 ctx, $10/M in / $40/M out - OpenAI: o3 (batch) (openai/o3:batch) added to the catalog: 200,000 ctx, $1/M in / $4/M out - OpenAI: o4 Mini High (batch) (openai/o4-mini-high:batch) added to the catalog: 200,000 ctx, $0.55/M in / $2.2/M out - OpenAI: o4 Mini (batch) (openai/o4-mini:batch) added to the catalog: 200,000 ctx, $0.55/M in / $2.2/M out - Thinking Machines: Inkling (batch) (thinkingmachines/inkling:batch) added to the catalog: 524,288 ctx, $0.5/M in / $2.02/M out - Z.ai: GLM 5.2 (batch) (z-ai/glm-5.2:batch) added to the catalog: 512,000 ctx, $0.7/M in / $2.2/M out - Ling-3.0-flash (free) (inclusionai/ling-3.0-flash:free) removed from the catalog - ~moonshotai/kimi-latest: prompt price $2.9/M → $2.5/M (−13.8%) - inclusionai/ling-3.0-flash: prompt price $0.075/M → $0.021/M (−72.0%) - inclusionai/ling-3.0-flash: completion price $0.22/M → $0.063/M (−71.4%) - nvidia/nemotron-3-super-120b-a12b: prompt price $0.085/M → $0.3/M (+252.9%) - nvidia/nemotron-3-super-120b-a12b: completion price $0.4/M → $0.9/M (+125.0%) - qwen/qwen3-vl-235b-a22b-thinking: prompt price $0.98/M → $0.4/M (−59.2%) - qwen/qwen3-vl-235b-a22b-thinking: completion price $3.95/M → $4/M (+1.3%) - qwen/qwen3.5-122b-a10b: prompt price $0.26/M → $0.29/M (+11.5%) - qwen/qwen3.5-122b-a10b: completion price $2.08/M → $2.4/M (+15.4%) - thinkingmachines/inkling-small: prompt price $0.5/M → $0.45/M (−10.0%) - z-ai/glm-5.2: prompt price $0.76/M → $0.687/M (−9.6%) - z-ai/glm-5.2: completion price $2.42/M → $2.16/M (−10.7%) - inclusionai/ling-3.0-flash: context length 131,072 → 262,144 - DeepInfra: minimax/minimax-m3 prompt price $0.3/M → $0.28/M (−6.7%) - DeepInfra: minimax/minimax-m3 completion price $1.2/M → $1.1/M (−8.3%) - DeepInfra: moonshotai/kimi-k2.7-code prompt price $0.74/M → $0.68/M (−8.1%) - DeepInfra: moonshotai/kimi-k2.7-code completion price $3.5/M → $3.4/M (−2.9%) - Morph: moonshotai/kimi-k3 prompt price $2.9/M → $2.5/M (−13.8%) - Mancer 2: openai/gpt-oss-120b prompt price $0.1/M → $0.09/M (−10.0%) - Mancer 2: z-ai/glm-4.7 prompt price $0.7/M → $0.6/M (−14.3%) - Decart: z-ai/glm-5.2 prompt price $0.6/M → $0.72/M (+20.0%) - Decart: z-ai/glm-5.2 completion price $1.5/M → $1.8/M (+20.0%) - Novita: z-ai/glm-5.2 prompt price $0.699/M → $0.687/M (−1.6%) - Novita: z-ai/glm-5.2 completion price $2.2/M → $2.16/M (−1.6%) - Phala: z-ai/glm-5.2 prompt price $1.26/M → $1.13/M (−10.0%) - Phala: z-ai/glm-5.2 completion price $3.96/M → $3.56/M (−10.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.7/M → $0.689/M (−1.6%) - StreamLake: z-ai/glm-5.2 completion price $2.2/M → $2.16/M (−1.6%) - DigitalOcean now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,048,576 ctx, $0.14/M in / $0.28/M out) - StreamLake now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,024,000 ctx, $0.14/M in / $0.28/M out) - Novita now serves inclusionai/ling-3.0-flash (unknown, 262,144 ctx, $0.021/M in / $0.063/M out) - Anthropic no longer serves anthropic/claude-opus-4.1 (was unknown) - Azure no longer serves anthropic/claude-opus-4.1 (was unknown) - Sail Research no longer serves deepseek/deepseek-v4-flash (was fp4) - Sail Research no longer serves deepseek/deepseek-v4-flash-0731 (was fp4) https://variables.md/changelog/2026-08-06/ https://variables.md/changelog/2026-08-06/ Thu, 06 Aug 2026 07:49:11 GMT - Ling-3.0-flash (inclusionai/ling-3.0-flash) added to the catalog: 131,072 ctx, $0.075/M in / $0.22/M out - Meta: Muse Spark 1.2 (meta/muse-spark-1.2) added to the catalog: 1,048,576 ctx, $1.25/M in / $4.25/M out - deepseek/deepseek-v4-flash: prompt price $0.14/M → $0.088/M (−37.0%) - deepseek/deepseek-v4-flash: completion price $0.28/M → $0.176/M (−37.0%) - minimax/minimax-m2.5: prompt price $0.15/M → $0.22/M (+46.7%) - moonshotai/kimi-k2.7-code: prompt price $0.73/M → $0.7/M (−4.1%) - qwen/qwen3-235b-a22b-2507: prompt price $0.15/M → $0.09/M (−39.8%) - qwen/qwen3-235b-a22b-2507: completion price $0.598/M → $0.55/M (−8.0%) - qwen/qwen3.6-27b: prompt price $0.289/M → $0.6/M (+107.6%) - qwen/qwen3.6-27b: completion price $2.4/M → $3.6/M (+50.0%) - z-ai/glm-5.1: prompt price $0.966/M → $0.952/M (−1.4%) - z-ai/glm-5.1: completion price $3.04/M → $2.99/M (−1.4%) - upstage/solar-pro-3: context length 128,000 → 131,072 - Upstage: upstage/solar-pro-3 quantization unknown → fp4 - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.126/M → $0.14/M (+11.1%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.252/M → $0.28/M (+11.1%) - Cloudflare: deepseek/deepseek-v4-pro prompt price $1.74/M → $1.17/M (−32.9%) - Cloudflare: deepseek/deepseek-v4-pro completion price $3.48/M → $2.34/M (−32.9%) - NextBit: google/gemma-4-26b-a4b-it completion price $0.3/M → $0.4/M (+33.3%) - Inceptron: minimax/minimax-m2.5 prompt price $0.15/M → $0.22/M (+46.7%) - Ambient: moonshotai/kimi-k2.7-code prompt price $0.73/M → $0.7/M (−4.1%) - DigitalOcean: xiaomi/mimo-v2.5-pro prompt price $0.8/M → $0.4/M (−50.0%) - DigitalOcean: xiaomi/mimo-v2.5-pro completion price $3/M → $1.5/M (−50.0%) - Inceptron: z-ai/glm-5.2 prompt price $0.94/M → $0.75/M (−20.2%) - Novita: z-ai/glm-5.2 prompt price $0.7/M → $0.699/M (−0.2%) - Novita: z-ai/glm-5.2 completion price $2.2/M → $2.2/M (−0.2%) - Sail Research: z-ai/glm-5.2 prompt price $1/M → $0.9/M (−10.0%) - Sail Research: z-ai/glm-5.2 completion price $3.5/M → $3.15/M (−10.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.699/M → $0.7/M (+0.2%) - StreamLake: z-ai/glm-5.2 completion price $2.2/M → $2.2/M (+0.2%) - Novita: meta-llama/llama-3.3-70b-instruct context length 6,000 → 12,288 - Upstage: upstage/solar-pro-3 context length 128,000 → 131,072 - CoreWeave now serves deepseek/deepseek-v4-flash-0731 (fp8, 262,144 ctx, $0.13/M in / $0.28/M out) - Sail Research now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.09/M in / $0.18/M out) - DeepInfra now serves inclusionai/ling-3.0-flash (bf16, 131,072 ctx, $0.075/M in / $0.22/M out) - Mancer 2 now serves z-ai/glm-4.7 (fp4, 131,072 ctx, $0.7/M in / $2.5/M out) - Phala no longer serves minimax/minimax-m2.5 (was unknown) - Chutes no longer serves z-ai/glm-5.2 (was fp4) https://variables.md/changelog/2026-08-05/ https://variables.md/changelog/2026-08-05/ Wed, 05 Aug 2026 07:49:20 GMT - minimax/minimax-m2.7: prompt price $0.25/M → $0.27/M (+8.0%) - minimax/minimax-m2.7: completion price $1/M → $1.08/M (+8.0%) - mistralai/mistral-small-3.2-24b-instruct: prompt price $0.075/M → $0.094/M (+25.0%) - mistralai/mistral-small-3.2-24b-instruct: completion price $0.2/M → $0.25/M (+25.0%) - qwen/qwen2.5-vl-72b-instruct: prompt price $0.8/M → $0.25/M (−68.8%) - qwen/qwen2.5-vl-72b-instruct: completion price $1/M → $0.75/M (−25.0%) - DigitalOcean: deepseek/deepseek-v3.2 prompt price $0.425/M → $0.25/M (−41.2%) - DigitalOcean: deepseek/deepseek-v3.2 completion price $1.36/M → $0.8/M (−41.2%) - DigitalOcean: deepseek/deepseek-v4-flash prompt price $0.112/M → $0.084/M (−25.0%) - DigitalOcean: deepseek/deepseek-v4-flash completion price $0.224/M → $0.168/M (−25.0%) - Io Net: deepseek/deepseek-v4-flash-0731 prompt price $0.17/M → $0.16/M (−5.9%) - Io Net: deepseek/deepseek-v4-flash-0731 completion price $0.33/M → $0.32/M (−3.0%) - Mancer 2: deepseek/deepseek-v4-flash-0731 prompt price $0.25/M → $0.175/M (−30.0%) - Mancer 2: deepseek/deepseek-v4-flash-0731 completion price $1/M → $0.5/M (−50.0%) - DigitalOcean: deepseek/deepseek-v4-pro prompt price $1.39/M → $0.87/M (−37.5%) - DigitalOcean: deepseek/deepseek-v4-pro completion price $2.78/M → $1.74/M (−37.5%) - NextBit: google/gemma-4-26b-a4b-it completion price $0.4/M → $0.3/M (−25.0%) - DigitalOcean: meta-llama/llama-4-maverick prompt price $0.25/M → $0.2/M (−20.0%) - DigitalOcean: meta-llama/llama-4-maverick completion price $0.87/M → $0.696/M (−20.0%) - Io Net: mistralai/mistral-nemo prompt price $0.043/M → $0.042/M (−2.1%) - Io Net: mistralai/mistral-nemo completion price $0.165/M → $0.16/M (−3.0%) - Chutes: moonshotai/kimi-k2.6 prompt price $0.66/M → $0.58/M (−12.1%) - Chutes: moonshotai/kimi-k2.6 completion price $3.5/M → $3.4/M (−2.9%) - StreamLake: moonshotai/kimi-k2.6 prompt price $0.855/M → $0.674/M (−21.1%) - StreamLake: moonshotai/kimi-k2.6 completion price $3.6/M → $2.84/M (−21.1%) - Inceptron: moonshotai/kimi-k2.7-code prompt price $0.72/M → $0.7/M (−2.8%) - DigitalOcean: nvidia/nemotron-3-super-120b-a12b prompt price $0.21/M → $0.165/M (−21.4%) - DigitalOcean: nvidia/nemotron-3-super-120b-a12b completion price $0.455/M → $0.358/M (−21.4%) - DigitalOcean: openai/gpt-oss-120b prompt price $0.07/M → $0.055/M (−21.4%) - DigitalOcean: openai/gpt-oss-120b completion price $0.49/M → $0.385/M (−21.4%) - Ionstream: qwen/qwen3-coder-next prompt price $0.11/M → $0.16/M (+45.5%) - DigitalOcean: qwen/qwen3.5-397b-a17b prompt price $0.385/M → $0.302/M (−21.4%) - DigitalOcean: qwen/qwen3.5-397b-a17b completion price $2.45/M → $1.93/M (−21.4%) - Io Net: qwen/qwen3.6-27b prompt price $0.27/M → $0.31/M (+14.8%) - Io Net: qwen/qwen3.6-27b completion price $1.89/M → $2.19/M (+15.9%) - DigitalOcean: xiaomi/mimo-v2.5-pro prompt price $0.6/M → $0.8/M (+33.3%) - DigitalOcean: z-ai/glm-5.2 prompt price $1.05/M → $0.7/M (−33.3%) - DigitalOcean: z-ai/glm-5.2 completion price $4.4/M → $2.2/M (−50.0%) - Novita: z-ai/glm-5.2 prompt price $0.584/M → $0.7/M (+19.9%) - Novita: z-ai/glm-5.2 completion price $1.83/M → $2.2/M (+19.9%) - StreamLake: z-ai/glm-5.2 prompt price $0.582/M → $0.699/M (+20.0%) - StreamLake: z-ai/glm-5.2 completion price $1.83/M → $2.2/M (+20.0%) - DigitalOcean: deepseek/deepseek-v4-flash context length 262,144 → 1,048,576 - Wafer: moonshotai/kimi-k3 context length 912,384 → 1,048,576 - Google now serves anthropic/claude-haiku-4.5 (unknown, 200,000 ctx, $1.1/M in / $5.5/M out) - Amazon Bedrock now serves anthropic/claude-opus-4.7 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Google now serves anthropic/claude-opus-4.7 (unknown, 1,000,000 ctx, $5.5/M in / $27.5/M out) - Google now serves anthropic/claude-opus-4.8 (unknown, 1,000,000 ctx, $5.5/M in / $27.5/M out) - Amazon Bedrock now serves anthropic/claude-opus-5 (unknown, 1,000,000 ctx, $5.5/M in / $27.5/M out) - Google now serves anthropic/claude-opus-5 (unknown, 1,000,000 ctx, $5.5/M in / $27.5/M out) - Google now serves anthropic/claude-sonnet-5 (unknown, 1,000,000 ctx, $2.2/M in / $11/M out) - Sail Research now serves deepseek/deepseek-v4-flash (fp4, 1,048,576 ctx, $0.09/M in / $0.18/M out) - AkashML now serves deepseek/deepseek-v4-flash-0731 (fp8, 131,072 ctx, $0.14/M in / $0.28/M out) - Baidu now serves deepseek/deepseek-v4-flash-0731 (fp8, 1,048,576 ctx, $0.14/M in / $0.28/M out) - BaseTen now serves deepseek/deepseek-v4-flash-0731 (fp8, 1,048,576 ctx, $0.13/M in / $0.26/M out) - Morph now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,048,576 ctx, $0.139/M in / $0.278/M out) - Baidu now serves tencent/hy3 (fp8, 262,144 ctx, $0.132/M in / $0.528/M out) - Amazon Bedrock no longer serves anthropic/claude-opus-4.7 (was unknown) - Google no longer serves anthropic/claude-sonnet-4.6 (was unknown) - AkashML no longer serves deepseek/deepseek-v4-flash (was fp8) - CoreWeave no longer serves minimax/minimax-m2.5 (was fp8) - Mara no longer serves minimax/minimax-m2.5 (was unknown) - Parasail no longer serves minimax/minimax-m2.5 (was fp8) - Fireworks no longer serves moonshotai/kimi-k2.7-code (was unknown) - Friendli no longer serves qwen/qwen3-235b-a22b-2507 (was unknown) - CoreWeave no longer serves qwen/qwen3-coder (was bf16) - Parasail no longer serves z-ai/glm-5 (was fp8) - CoreWeave no longer serves z-ai/glm-5.1 (was fp8) - Ionstream no longer serves z-ai/glm-5.2 (was fp4) https://variables.md/changelog/2026-08-04/ https://variables.md/changelog/2026-08-04/ Tue, 04 Aug 2026 07:48:02 GMT - Qwen: Qwen3.8 Max (qwen/qwen3.8-max) added to the catalog: 1,000,000 ctx, $2/M in / $6/M out - gryphe/mythomax-l2-13b: prompt price $0.06/M → $0.08/M (+33.3%) - gryphe/mythomax-l2-13b: completion price $0.06/M → $0.11/M (+83.3%) - meta-llama/llama-3.3-70b-instruct: prompt price $0.13/M → $0.1/M (−23.1%) - meta-llama/llama-3.3-70b-instruct: completion price $0.4/M → $0.32/M (−20.0%) - moonshotai/kimi-k2.6: prompt price $0.6/M → $0.589/M (−1.8%) - moonshotai/kimi-k2.6: completion price $3.41/M → $2.48/M (−27.3%) - qwen/qwen3-coder-30b-a3b-instruct: completion price $0.28/M → $0.27/M (−3.6%) - qwen/qwen3-next-80b-a3b-instruct: prompt price $0.1/M → $0.09/M (−10.0%) - qwen/qwen3-vl-30b-a3b-instruct: prompt price $0.13/M → $0.15/M (+15.4%) - qwen/qwen3-vl-30b-a3b-instruct: completion price $0.52/M → $0.6/M (+15.4%) - qwen/qwen3.5-122b-a10b: prompt price $0.4/M → $0.26/M (−35.0%) - qwen/qwen3.5-122b-a10b: completion price $3.2/M → $2.08/M (−35.0%) - qwen/qwen3.6-27b: prompt price $0.3/M → $0.289/M (−3.7%) - qwen/qwen3.6-27b: completion price $2/M → $2.4/M (+20.0%) - z-ai/glm-5.2: prompt price $1.19/M → $0.76/M (−36.1%) - z-ai/glm-5.2: completion price $3.74/M → $2.42/M (−35.3%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.088/M → $0.088/M (−0.2%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.176/M → $0.176/M (−0.2%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.126/M (−10.0%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.252/M (−10.0%) - Io Net: deepseek/deepseek-v4-flash-0731 prompt price $0.18/M → $0.17/M (−5.6%) - Io Net: deepseek/deepseek-v4-flash-0731 completion price $0.34/M → $0.33/M (−2.9%) - GMICloud: deepseek/deepseek-v4-pro prompt price $0.679/M → $0.661/M (−2.6%) - GMICloud: deepseek/deepseek-v4-pro completion price $1.36/M → $1.32/M (−2.6%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.67/M → $0.652/M (−2.6%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.34/M → $1.3/M (−2.6%) - NextBit: google/gemma-4-26b-a4b-it prompt price $0.15/M → $0.12/M (−20.0%) - NextBit: google/gemma-4-26b-a4b-it completion price $0.45/M → $0.4/M (−11.1%) - Io Net: qwen/qwen3.6-27b prompt price $0.28/M → $0.27/M (−3.6%) - Io Net: qwen/qwen3.6-27b completion price $1.99/M → $1.89/M (−5.0%) - Io Net: qwen/qwen3.6-35b-a3b prompt price $0.324/M → $0.29/M (−10.6%) - Io Net: qwen/qwen3.6-35b-a3b completion price $2.09/M → $1.89/M (−9.6%) - Venice: qwen/qwen3.6-35b-a3b prompt price $0.1/M → $0.098/M (−2.0%) - Venice: qwen/qwen3.6-35b-a3b completion price $1/M → $0.95/M (−5.0%) - Baidu: z-ai/glm-5.2 prompt price $0.756/M → $1.18/M (+55.6%) - Baidu: z-ai/glm-5.2 completion price $2.38/M → $3.7/M (+55.6%) - Decart: z-ai/glm-5.2 prompt price $0.72/M → $0.6/M (−16.7%) - Decart: z-ai/glm-5.2 completion price $1.8/M → $1.5/M (−16.7%) - Novita: z-ai/glm-5.2 prompt price $0.746/M → $0.584/M (−21.8%) - Novita: z-ai/glm-5.2 completion price $2.35/M → $1.83/M (−21.8%) - StreamLake: z-ai/glm-5.2 prompt price $0.748/M → $0.582/M (−22.1%) - StreamLake: z-ai/glm-5.2 completion price $2.35/M → $1.83/M (−22.1%) - Phala now serves deepseek/deepseek-v4-flash (unknown, 1,048,576 ctx, $0.2/M in / $0.4/M out) - Ambient now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.14/M in / $0.28/M out) - Ionstream now serves deepseek/deepseek-v4-flash-0731 (fp4, 1,048,576 ctx, $0.14/M in / $0.28/M out) - Phala now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,048,576 ctx, $0.2/M in / $0.4/M out) - Together now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,048,576 ctx, $0.14/M in / $0.28/M out) - Venice now serves deepseek/deepseek-v4-flash-0731 (unknown, 1,000,000 ctx, $0.175/M in / $0.35/M out) - Chutes now serves moonshotai/kimi-k3 (mxfp4, 1,048,576 ctx, $3/M in / $15/M out) - Ionstream no longer serves deepseek/deepseek-v4-flash (was fp4) - Groq no longer serves moonshotai/kimi-k2-0905 (was unknown) - Io Net no longer serves xiaomi/mimo-v2.5 (was fp8) https://variables.md/changelog/2026-08-03/ https://variables.md/changelog/2026-08-03/ Mon, 03 Aug 2026 08:42:35 GMT - qwen/qwen3-235b-a22b-2507: prompt price $0.09/M → $0.15/M (+66.1%) - qwen/qwen3-235b-a22b-2507: completion price $0.55/M → $0.598/M (+8.7%) - qwen/qwen3-vl-235b-a22b-thinking: prompt price $0.4/M → $0.98/M (+145.0%) - qwen/qwen3-vl-235b-a22b-thinking: completion price $4/M → $3.95/M (−1.2%) - qwen/qwen3.5-122b-a10b: prompt price $0.26/M → $0.4/M (+53.8%) - qwen/qwen3.5-122b-a10b: completion price $2.08/M → $3.2/M (+53.8%) - z-ai/glm-5.2: prompt price $0.326/M → $1.19/M (+264.8%) - z-ai/glm-5.2: completion price $1.03/M → $3.74/M (+264.8%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.087/M → $0.088/M (+1.6%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.174/M → $0.176/M (+1.6%) - GMICloud: deepseek/deepseek-v4-flash-0731 prompt price $0.133/M → $0.14/M (+5.3%) - GMICloud: deepseek/deepseek-v4-flash-0731 completion price $0.266/M → $0.28/M (+5.3%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.49/M → $1.23/M (+151.7%) - Baidu: deepseek/deepseek-v4-pro completion price $0.98/M → $2.47/M (+151.7%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.523/M → $0.67/M (+28.0%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.05/M → $1.34/M (+28.0%) - Decart: moonshotai/kimi-k2.6 prompt price $0.66/M → $0.59/M (−10.6%) - Mancer 2: openai/gpt-oss-120b prompt price $0.06/M → $0.1/M (+66.7%) - DeepInfra: thinkingmachines/inkling prompt price $1/M → $0.95/M (−5.0%) - Baidu: z-ai/glm-5.2 prompt price $0.322/M → $0.756/M (+134.8%) - Baidu: z-ai/glm-5.2 completion price $1.01/M → $2.38/M (+134.8%) - Novita: z-ai/glm-5.2 prompt price $0.326/M → $0.746/M (+128.8%) - Novita: z-ai/glm-5.2 completion price $1.03/M → $2.35/M (+128.8%) - Phala: z-ai/glm-5.2 prompt price $1.4/M → $1.26/M (−10.0%) - Phala: z-ai/glm-5.2 completion price $4.4/M → $3.96/M (−10.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.328/M → $0.748/M (+128.2%) - StreamLake: z-ai/glm-5.2 completion price $1.03/M → $2.35/M (+128.2%) - Morph now serves moonshotai/kimi-k3 (unknown, 1,048,576 ctx, $6/M in / $22.5/M out) - Wafer now serves moonshotai/kimi-k3 (fp8, 1,048,576 ctx, $4.5/M in / $22.5/M out) - Crusoe now serves z-ai/glm-5.2 (fp8, 1,048,576 ctx, $1.4/M in / $4.4/M out) https://variables.md/changelog/2026-08-02/ https://variables.md/changelog/2026-08-02/ Sun, 02 Aug 2026 07:41:13 GMT - DeepSeek V4 Flash Latest (~deepseek/deepseek-v4-flash-latest) added to the catalog: 1,048,576 ctx, $0.09/M in / $0.18/M out - deepseek/deepseek-v4-flash-0731: prompt price $0.14/M → $0.09/M (−35.7%) - deepseek/deepseek-v4-flash-0731: completion price $0.28/M → $0.18/M (−35.7%) - z-ai/glm-5.2: prompt price $0.76/M → $0.326/M (−57.1%) - z-ai/glm-5.2: completion price $2.39/M → $1.03/M (−57.1%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.091/M → $0.088/M (−3.1%) - Baidu: deepseek/deepseek-v4-flash completion price $0.182/M → $0.176/M (−3.1%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.09/M → $0.087/M (−3.1%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.179/M → $0.174/M (−3.1%) - Baidu: deepseek/deepseek-v4-pro prompt price $0.625/M → $0.49/M (−21.6%) - Baidu: deepseek/deepseek-v4-pro completion price $1.25/M → $0.98/M (−21.6%) - StreamLake: deepseek/deepseek-v4-pro prompt price $0.67/M → $0.523/M (−21.9%) - StreamLake: deepseek/deepseek-v4-pro completion price $1.34/M → $1.05/M (−21.9%) - DeepInfra: thinkingmachines/inkling-small prompt price $0.5/M → $0.45/M (−10.0%) - Baidu: z-ai/glm-5.2 prompt price $0.91/M → $0.322/M (−64.6%) - Baidu: z-ai/glm-5.2 completion price $2.86/M → $1.01/M (−64.6%) - Novita: z-ai/glm-5.2 prompt price $0.759/M → $0.326/M (−57.0%) - Novita: z-ai/glm-5.2 completion price $2.38/M → $1.03/M (−57.0%) - StreamLake: z-ai/glm-5.2 prompt price $0.76/M → $0.328/M (−56.9%) - StreamLake: z-ai/glm-5.2 completion price $2.39/M → $1.03/M (−56.9%) - Io Net now serves deepseek/deepseek-v4-flash-0731 (fp8, 262,100 ctx, $0.18/M in / $0.34/M out) - Mancer 2 now serves deepseek/deepseek-v4-flash-0731 (fp8, 1,048,576 ctx, $0.25/M in / $1/M out) - Novita now serves deepseek/deepseek-v4-flash-0731 (fp8, 1,048,576 ctx, $0.14/M in / $0.28/M out) - Io Net no longer serves deepseek/deepseek-v4-flash (was fp8) - Wafer no longer serves moonshotai/kimi-k3 (was fp8) https://variables.md/changelog/2026-08-01/ https://variables.md/changelog/2026-08-01/ Sat, 01 Aug 2026 07:38:05 GMT - DeepSeek: DeepSeek V4 Flash 0731 (deepseek/deepseek-v4-flash-0731) added to the catalog: 1,048,576 ctx, $0.14/M in / $0.28/M out - Thinking Machines: Inkling Small (thinkingmachines/inkling-small) added to the catalog: 524,288 ctx, $0.5/M in / $1.2/M out - Anthropic: Claude Fable 5 (batch) (anthropic/claude-fable-5:batch) removed from the catalog - Anthropic: Claude Haiku 4.5 (batch) (anthropic/claude-haiku-4.5:batch) removed from the catalog - Anthropic: Claude Opus 4.1 (batch) (anthropic/claude-opus-4.1:batch) removed from the catalog - Anthropic: Claude Opus 4.5 (batch) (anthropic/claude-opus-4.5:batch) removed from the catalog - Anthropic: Claude Opus 4.6 (batch) (anthropic/claude-opus-4.6:batch) removed from the catalog - Anthropic: Claude Opus 4.7 (batch) (anthropic/claude-opus-4.7:batch) removed from the catalog - Anthropic: Claude Opus 4.8 (batch) (anthropic/claude-opus-4.8:batch) removed from the catalog - Anthropic: Claude Sonnet 4.5 (batch) (anthropic/claude-sonnet-4.5:batch) removed from the catalog - Anthropic: Claude Sonnet 5 (batch) (anthropic/claude-sonnet-5:batch) removed from the catalog - Google: Gemini 2.5 Flash Lite (batch) (google/gemini-2.5-flash-lite:batch) removed from the catalog - Google: Gemini 2.5 Flash (batch) (google/gemini-2.5-flash:batch) removed from the catalog - Google: Gemini 2.5 Pro (batch) (google/gemini-2.5-pro:batch) removed from the catalog - Google: Gemini 3 Flash Preview (batch) (google/gemini-3-flash-preview:batch) removed from the catalog - Google: Gemini 3.1 Flash Lite (batch) (google/gemini-3.1-flash-lite:batch) removed from the catalog - Google: Gemini 3.1 Pro Preview (batch) (google/gemini-3.1-pro-preview:batch) removed from the catalog - Google: Gemini 3.5 Flash Lite (batch) (google/gemini-3.5-flash-lite:batch) removed from the catalog - Google: Gemini 3.5 Flash (batch) (google/gemini-3.5-flash:batch) removed from the catalog - Google: Gemini 3.6 Flash (batch) (google/gemini-3.6-flash:batch) removed from the catalog - MiniMax: MiniMax M3 (batch) (minimax/minimax-m3:batch) removed from the catalog - Mistral: Devstral 2 2512 (mistralai/devstral-2512) removed from the catalog - OpenAI: GPT-5 Mini (batch) (openai/gpt-5-mini:batch) removed from the catalog - OpenAI: GPT-5 Nano (batch) (openai/gpt-5-nano:batch) removed from the catalog - OpenAI: GPT-5 (batch) (openai/gpt-5:batch) removed from the catalog - OpenAI: GPT-5.1 Chat (openai/gpt-5.1-chat) removed from the catalog - OpenAI: GPT-5.1 (batch) (openai/gpt-5.1:batch) removed from the catalog - OpenAI: GPT-5.2 (batch) (openai/gpt-5.2:batch) removed from the catalog - OpenAI: GPT-5.4 Mini (batch) (openai/gpt-5.4-mini:batch) removed from the catalog - OpenAI: GPT-5.4 Nano (batch) (openai/gpt-5.4-nano:batch) removed from the catalog - OpenAI: GPT-5.4 (batch) (openai/gpt-5.4:batch) removed from the catalog - OpenAI: GPT-5.5 (batch) (openai/gpt-5.5:batch) removed from the catalog - mistralai/mistral-small-3.2-24b-instruct: prompt price $0.1/M → $0.075/M (−25.0%) - mistralai/mistral-small-3.2-24b-instruct: completion price $0.3/M → $0.2/M (−33.3%) - moonshotai/kimi-k2.6: prompt price $0.95/M → $0.6/M (−36.8%) - moonshotai/kimi-k2.6: completion price $4/M → $3.41/M (−14.7%) - qwen/qwen3-coder-30b-a3b-instruct: completion price $0.27/M → $0.28/M (+3.7%) - qwen/qwen3-vl-30b-a3b-instruct: prompt price $0.15/M → $0.13/M (−13.3%) - qwen/qwen3-vl-30b-a3b-instruct: completion price $0.6/M → $0.52/M (−13.3%) - z-ai/glm-5.2: prompt price $1.19/M → $0.76/M (−36.1%) - z-ai/glm-5.2: completion price $3.74/M → $2.39/M (−36.1%) - Baidu: deepseek/deepseek-v3.2 prompt price $0.28/M → $0.207/M (−26.0%) - Baidu: deepseek/deepseek-v3.2 completion price $0.42/M → $0.311/M (−26.0%) - Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.091/M (−35.0%) - Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.182/M (−35.0%) - Mancer 2: deepseek/deepseek-v4-flash prompt price $0.15/M → $0.2/M (+33.3%) - StreamLake: deepseek/deepseek-v4-flash prompt price $0.092/M → $0.09/M (−3.0%) - StreamLake: deepseek/deepseek-v4-flash completion price $0.185/M → $0.179/M (−3.0%) - Baidu: deepseek/deepseek-v4-pro prompt price $1.69/M → $0.625/M (−63.0%) - Baidu: deepseek/deepseek-v4-pro completion price $3.38/M → $1.25/M (−63.0%) - Baidu: moonshotai/kimi-k2.6 prompt price $0.95/M → $0.589/M (−38.0%) - Baidu: moonshotai/kimi-k2.6 completion price $4/M → $2.48/M (−38.0%) - Venice: z-ai/glm-4.7-flash prompt price $0.125/M → $0.06/M (−52.0%) - Venice: z-ai/glm-4.7-flash completion price $0.5/M → $0.4/M (−20.0%) - Baidu: z-ai/glm-5.1 prompt price $1.4/M → $0.952/M (−32.0%) - Baidu: z-ai/glm-5.1 completion price $4.4/M → $2.99/M (−32.0%) - Baidu: z-ai/glm-5.2 prompt price $1.4/M → $0.91/M (−35.0%) - Baidu: z-ai/glm-5.2 completion price $4.4/M → $2.86/M (−35.0%) - Decart: z-ai/glm-5.2 prompt price $0.6/M → $0.72/M (+20.0%) - Decart: z-ai/glm-5.2 completion price $1.25/M → $1.8/M (+44.0%) - Novita: z-ai/glm-5.2 prompt price $0.965/M → $0.759/M (−21.3%) - Novita: z-ai/glm-5.2 completion price $3.03/M → $2.38/M (−21.3%) - StreamLake: z-ai/glm-5.2 prompt price $1.19/M → $0.76/M (−36.1%) - StreamLake: z-ai/glm-5.2 completion price $3.74/M → $2.39/M (−36.1%) - AkashML: deepseek/deepseek-v4-flash context length 1,048,576 → 131,072 - Ambient: z-ai/glm-5.2 context length 101,376 → 202,752 - Azure now serves anthropic/claude-haiku-4.5 (unknown, 200,000 ctx, $1/M in / $5/M out) - Azure now serves anthropic/claude-opus-4.1 (unknown, 200,000 ctx, $15/M in / $75/M out) - Azure now serves anthropic/claude-opus-4.5 (unknown, 200,000 ctx, $5/M in / $25/M out) - Azure now serves anthropic/claude-opus-4.6 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Azure now serves anthropic/claude-opus-4.7 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Azure now serves anthropic/claude-opus-4.8 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Azure now serves anthropic/claude-opus-5 (unknown, 1,000,000 ctx, $5/M in / $25/M out) - Azure now serves anthropic/claude-sonnet-4.5 (unknown, 200,000 ctx, $3/M in / $15/M out) - Azure now serves anthropic/claude-sonnet-4.6 (unknown, 1,000,000 ctx, $3/M in / $15/M out) - Azure now serves anthropic/claude-sonnet-5 (unknown, 1,000,000 ctx, $2/M in / $10/M out) - Parasail now serves mistralai/mistral-nemo (fp8, 131,072 ctx, $0.03/M in / $0.03/M out) - Amazon Bedrock now serves moonshotai/kimi-k2.5 (unknown, 262,144 ctx, $0.6/M in / $3/M out) - ModelRun now serves moonshotai/kimi-k2.7-code (fp4, 262,144 ctx, $0.85/M in / $3.75/M out) - Parasail now serves sao10k/l3-lunaris-8b (bf16, 8,192 ctx, $0.04/M in / $0.05/M out) - Wafer now serves z-ai/glm-5.2 (fp4, 1,048,576 ctx, $1.26/M in / $3.96/M out) - Azure no longer serves anthropic/claude-haiku-4.5 (was unknown) - Azure no longer serves anthropic/claude-opus-4.1 (was unknown) - Azure no longer serves anthropic/claude-opus-4.5 (was unknown) - Azure no longer serves anthropic/claude-opus-4.6 (was unknown) - Azure no longer serves anthropic/claude-opus-4.7 (was unknown) - Azure no longer serves anthropic/claude-opus-4.8 (was unknown) - Azure no longer serves anthropic/claude-opus-5 (was unknown) - Azure no longer serves anthropic/claude-sonnet-4.5 (was unknown) - Azure no longer serves anthropic/claude-sonnet-4.6 (was unknown) - Azure no longer serves anthropic/claude-sonnet-5 (was unknown) - Mistral no longer serves mistralai/mistral-nemo (was unknown) - Mistral no longer serves mistralai/mistral-small-3.2-24b-instruct (was unknown) - ModelRun no longer serves moonshotai/kimi-k2.6 (was fp4) - Nebius no longer serves moonshotai/kimi-k2.7-code (was fp4) - Wafer no longer serves z-ai/glm-5.2 (was fp4)