variables.md
the model market, diffed daily
Every day at 05:20 UTC this site snapshots the OpenRouter catalog — every model, every provider endpoint, prices, context windows, quantization labels — and diffs it against yesterday. What changed is published here as one-line facts. No commentary, no ranking.
Raw snapshots are retained from 2026-07-12 onward; every entry names the snapshot pair that produced it. The audience includes agents choosing a provider: every line is written to be quoted, and every page has a markdown twin.
Subscribe or poll:
rss ·
json feed ·
latest.json ·
latest (curl variables.md/changelog/latest speaks markdown)
2026-10-31 141 change(s)
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.031/M → $0.014/M (−54.5%)
- ~deepseek/deepseek-flash-latest: completion price $0.27/M → $0.144/M (−46.7%)
- ~deepseek/deepseek-pro-latest: completion price $4/M → $8/M (+100.0%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.039/M → $0.058/M (+48.6%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.3/M → $0.173/M (−42.4%)
- ~moonshotai/kimi-latest: prompt price $0.171/M → $0.15/M (−12.6%)
- ~moonshotai/kimi-latest: completion price $10.2/M → $7.15/M (−29.6%)
- ~z-ai/glm-flash-latest: prompt price $0.024/M → $0.016/M (−31.2%)
- ~z-ai/glm-flash-latest: completion price $0.104/M → $0.148/M (+41.9%)
- deepseek/deepseek-v3.2: prompt price $0.28/M → $0.26/M (−7.1%)
- deepseek/deepseek-v3.2: completion price $0.42/M → $0.38/M (−9.5%)
- deepseek/deepseek-v4-pro: prompt price $0.816/M → $1.6/M (+96.0%)
- deepseek/deepseek-v4-pro: completion price $1.63/M → $3.2/M (+96.0%)
- google/gemma-4-26b-a4b-it: prompt price $0.09/M → $0.068/M (−25.0%)
- google/gemma-4-26b-a4b-it: completion price $0.3/M → $0.225/M (−25.0%)
- minimax/minimax-m2.5: prompt price $0.3/M → $0.27/M (−10.0%)
- minimax/minimax-m2.5: completion price $1.2/M → $0.95/M (−20.8%)
- moonshotai/kimi-k2.7-code: prompt price $0.56/M → $0.6/M (+7.1%)
- moonshotai/kimi-k2.7-code: completion price $3.1/M → $3.5/M (+12.9%)
- particle-ai/particle-1: prompt price $0.25/M → $0.05/M (−80.0%)
- particle-ai/particle-1: completion price $1/M → $0.5/M (−50.0%)
- qwen/qwen3.6-27b: prompt price $0.32/M → $0.45/M (+40.6%)
- qwen/qwen3.6-27b: completion price $3.2/M → $2.7/M (−15.6%)
- qwen/qwen3.8-27b: prompt price $0.15/M → $0.04/M (−73.3%)
- qwen/qwen3.8-27b: completion price $1.88/M → $2.3/M (+22.7%)
- z-ai/glm-5.2: completion price $7/M → $6.8/M (−2.9%)
- z-ai/glm-5.3: prompt price $0.08/M → $0.07/M (−12.6%)
- z-ai/glm-5.3: completion price $3.6/M → $1.4/M (−61.1%)
- z-ai/glm-5.3-flash: prompt price $0.15/M → $0.016/M (−89.1%)
- z-ai/glm-5.3-flash: completion price $0.5/M → $0.148/M (−70.4%)
2026-10-30 120 change(s)
removed from the catalog
- Upstage: Solar Pro 3 (upstage/solar-pro-3) removed from the catalog
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.021/M → $0.031/M (+46.2%)
- ~deepseek/deepseek-flash-latest: completion price $1.8/M → $0.27/M (−85.0%)
- ~deepseek/deepseek-pro-latest: completion price $8/M → $4/M (−50.0%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.057/M → $0.039/M (−31.9%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.134/M → $0.3/M (+123.7%)
- ~moonshotai/kimi-latest: prompt price $0.182/M → $0.171/M (−6.2%)
- ~moonshotai/kimi-latest: completion price $9.34/M → $10.2/M (+8.7%)
- ~z-ai/glm-flash-latest: prompt price $0.046/M → $0.024/M (−48.1%)
- ~z-ai/glm-flash-latest: completion price $0.074/M → $0.104/M (+40.4%)
- deepseek/deepseek-v4-pro: prompt price $0.955/M → $0.816/M (−14.6%)
- deepseek/deepseek-v4-pro: completion price $1.91/M → $1.63/M (−14.6%)
- mistralai/mistral-large-4-0: prompt price $1.36/M → $0.7/M (−48.5%)
- mistralai/mistral-large-4-0: completion price $4.18/M → $2.1/M (−49.8%)
- moonshotai/kimi-k3: prompt price $0.239/M → $0.192/M (−19.7%)
- moonshotai/kimi-k3: completion price $10.8/M → $15/M (+38.9%)
- qwen/qwen3.6-27b: prompt price $0.45/M → $0.32/M (−28.9%)
- qwen/qwen3.6-27b: completion price $2.7/M → $3.2/M (+18.5%)
- qwen/qwen3.8-27b: prompt price $0.039/M → $0.15/M (+284.6%)
- qwen/qwen3.8-27b: completion price $1.25/M → $1.88/M (+50.0%)
- z-ai/glm-5.3: prompt price $0.07/M → $0.08/M (+14.4%)
- z-ai/glm-5.3: completion price $1.4/M → $3.6/M (+157.1%)
- z-ai/glm-5.3-flash: prompt price $0.046/M → $0.15/M (+228.2%)
- z-ai/glm-5.3-flash: completion price $0.074/M → $0.5/M (+573.9%)
model context changes
- stepfun/step-5-preview: context length 1,000,000 → 1,048,576
provider price changes
- Inceptron: deepseek/deepseek-v4-flash-0731 completion price $0.369/M → $0.44/M (+19.2%)
- Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.057/M → $0.04/M (−30.2%)
- Relace: deepseek/deepseek-v4-flash-0731 completion price $0.134/M → $0.16/M (+19.2%)
- Wafer: deepseek/deepseek-v4-flash-0731 prompt price $0.1/M → $0.13/M (+30.0%)
- StreamLake: deepseek/deepseek-v4-pro prompt price $0.955/M → $0.816/M (−14.6%)
2026-10-29 110 change(s)
added to the catalog
- Particle AI: Particle-1 (particle-ai/particle-1) added to the catalog: 1,048,576 ctx, $0.25/M in / $1/M out
removed from the catalog
- OpenAI: GPT-4 Turbo (openai/gpt-4-turbo) removed from the catalog
- OpenAI: o1 (openai/o1) removed from the catalog
- OpenAI: o1-pro (openai/o1-pro) removed from the catalog
- OpenAI: o3 Mini (openai/o3-mini) removed from the catalog
- OpenAI: o3 Mini High (openai/o3-mini-high) removed from the catalog
- OpenAI: o4 Mini (openai/o4-mini) removed from the catalog
- OpenAI: o4 Mini High (openai/o4-mini-high) removed from the catalog
- Qwen: Qwen3 Next 80B A3B Thinking (qwen/qwen3-next-80b-a3b-thinking) removed from the catalog
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.013/M → $0.021/M (+68.3%)
- ~deepseek/deepseek-pro-latest: prompt price $0.254/M → $0.103/M (−59.3%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.048/M → $0.057/M (+20.0%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.157/M → $0.134/M (−14.5%)
- ~moonshotai/kimi-latest: prompt price $0.159/M → $0.182/M (+14.7%)
- ~moonshotai/kimi-latest: completion price $20/M → $9.34/M (−53.3%)
- ~z-ai/glm-flash-latest: prompt price $0.02/M → $0.046/M (+132.0%)
- ~z-ai/glm-flash-latest: completion price $0.124/M → $0.074/M (−40.1%)
- deepseek/deepseek-v4.1-flash: prompt price $0.14/M → $0.045/M (−67.9%)
- deepseek/deepseek-v4.1-flash: completion price $0.42/M → $0.5/M (+19.0%)
- ibm-granite/granite-4.2-8b: completion price $0.25/M → $0.15/M (−40.0%)
- meta-llama/llama-3.1-8b-instruct: prompt price $0.02/M → $0.05/M (+150.0%)
- meta-llama/llama-3.1-8b-instruct: completion price $0.04/M → $0.08/M (+100.0%)
- moonshotai/kimi-k2.7-code: prompt price $0.672/M → $0.56/M (−16.7%)
- moonshotai/kimi-k3: prompt price $0.159/M → $0.239/M (+50.3%)
- moonshotai/kimi-k3: completion price $20/M → $10.8/M (−46.0%)
- 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 $0.014/M → $0.006/M (−57.1%)
- z-ai/glm-5.3-flash: prompt price $0.15/M → $0.046/M (−69.5%)
- z-ai/glm-5.3-flash: completion price $0.5/M → $0.074/M (−85.2%)
2026-10-28 93 change(s)
added to the catalog
- PrismML: Ternary Bonsai 2 9B (prism-ml/ternary-bonsai-2-9b) added to the catalog: 262,144 ctx, $0.08/M in / $0.13/M out
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.02/M → $0.013/M (−37.0%)
- ~deepseek/deepseek-flash-latest: completion price $1/M → $1.8/M (+80.0%)
- ~deepseek/deepseek-pro-latest: prompt price $0.243/M → $0.254/M (+4.7%)
- ~moonshotai/kimi-latest: prompt price $0.179/M → $0.159/M (−11.2%)
- ~moonshotai/kimi-latest: completion price $11.5/M → $20/M (+73.9%)
- ~z-ai/glm-flash-latest: prompt price $0.029/M → $0.02/M (−30.9%)
- ~z-ai/glm-flash-latest: completion price $0.092/M → $0.124/M (+34.1%)
- deepseek/deepseek-v4-flash: prompt price $0.05/M → $0.091/M (+82.0%)
- deepseek/deepseek-v4-flash: completion price $0.45/M → $0.182/M (−59.6%)
- meta-llama/llama-3.1-8b-instruct: prompt price $0.05/M → $0.02/M (−60.0%)
- meta-llama/llama-3.1-8b-instruct: completion price $0.08/M → $0.04/M (−50.0%)
- moonshotai/kimi-k2.7-code: prompt price $0.56/M → $0.672/M (+20.1%)
- moonshotai/kimi-k3: prompt price $0.179/M → $0.159/M (−11.2%)
- moonshotai/kimi-k3: completion price $11.5/M → $20/M (+73.9%)
- qwen/qwen3.6-27b: prompt price $0.32/M → $0.45/M (+40.6%)
- qwen/qwen3.6-27b: completion price $3.2/M → $2.7/M (−15.6%)
- qwen/qwen3.6-35b-a3b: completion price $0.95/M → $0.9/M (−5.3%)
- qwen/qwen3.8-27b: prompt price $0.2/M → $0.039/M (−80.5%)
- qwen/qwen3.8-27b: completion price $2.5/M → $1.25/M (−50.0%)
- z-ai/glm-5.1: prompt price $0.966/M → $1.4/M (+44.9%)
- z-ai/glm-5.1: completion price $3.04/M → $4.4/M (+44.9%)
- z-ai/glm-5.2: prompt price $0.034/M → $0.014/M (−58.9%)
model context changes
- inclusionai/ling-3.1-flash: context length 262,144 → 1,000,000
provider price changes
- Inceptron: deepseek/deepseek-v4-flash-0731 completion price $0.413/M → $0.495/M (+20.0%)
- Sail Research: deepseek/deepseek-v4-flash-0731 completion price $0.15/M → $0.3/M (+100.0%)
- Sail Research: deepseek/deepseek-v4-flash-0731 completion price $0.15/M → $0.3/M (+100.0%)
- Wafer: deepseek/deepseek-v4-flash-0731 prompt price $0.13/M → $0.14/M (+7.7%)
- SiliconFlow: deepseek/deepseek-v4-pro prompt price $1.5/M → $1/M (−33.4%)
- Relace: deepseek/deepseek-v4-pro-0813 prompt price $0.243/M → $0.254/M (+4.7%)
2026-10-27 145 change(s)
added to the catalog
- OpenAI: GPT-6.1 Terra (openai/gpt-6.1-terra) added to the catalog: 1,050,000 ctx, $1/M in / $5/M out
- OpenAI: GPT-6.1 Terra Pro (openai/gpt-6.1-terra-pro) added to the catalog: 1,050,000 ctx, $1/M in / $5/M out
- OpenAI: GPT-6.1 Terra Pro (batch) (openai/gpt-6.1-terra-pro:batch) added to the catalog: 1,050,000 ctx, $0.5/M in / $2.5/M out
- OpenAI: GPT-6.1 Terra (batch) (openai/gpt-6.1-terra:batch) added to the catalog: 1,050,000 ctx, $0.5/M in / $2.5/M out
removed from the catalog
- Arcee AI: Trinity Large Thinking (arcee-ai/trinity-large-thinking) removed from the catalog
- IBM: Granite 4.0 Micro (ibm-granite/granite-4.0-h-micro) removed from the catalog
- Mistral: Codestral 2508 (batch) (mistralai/codestral-2508:batch) removed from the catalog
- Mistral: Ministral 3 8B 2512 (batch) (mistralai/ministral-8b-2512:batch) removed from the catalog
- Mistral: Mistral Large 3 2512 (batch) (mistralai/mistral-large-2512:batch) removed from the catalog
- Mistral: Mistral Medium 3.1 (batch) (mistralai/mistral-medium-3.1:batch) removed from the catalog
- Mistral: Mistral Small 4 (batch) (mistralai/mistral-small-2603:batch) removed from the catalog
- NVIDIA: Nemotron 3 Super (free) (nvidia/nemotron-3-super-120b-a12b:free) removed from the catalog
model price changes
- ~deepseek/deepseek-pro-latest: prompt price $0.257/M → $0.243/M (−5.3%)
- ~moonshotai/kimi-latest: prompt price $0.152/M → $0.179/M (+17.8%)
- ~moonshotai/kimi-latest: completion price $20/M → $11.5/M (−42.5%)
- ~openai/gpt-terra-latest: prompt price $2/M → $1/M (−50.0%)
- ~openai/gpt-terra-latest: completion price $12/M → $5/M (−58.3%)
- ~z-ai/glm-flash-latest: prompt price $0.041/M → $0.029/M (−31.0%)
- ~z-ai/glm-flash-latest: completion price $0.076/M → $0.092/M (+21.8%)
- deepseek/deepseek-v4-flash: prompt price $0.091/M → $0.05/M (−45.1%)
- deepseek/deepseek-v4-flash: completion price $0.182/M → $0.45/M (+147.3%)
- deepseek/deepseek-v4-flash-0731: prompt price $0.44/M → $0.119/M (−73.0%)
- deepseek/deepseek-v4-flash-0731: completion price $1.32/M → $0.238/M (−82.0%)
- deepseek/deepseek-v4.1-flash: prompt price $0.02/M → $0.14/M (+600.0%)
- deepseek/deepseek-v4.1-flash: completion price $1/M → $0.42/M (−58.0%)
- google/gemma-3-4b-it: prompt price $0.04/M → $0.05/M (+25.0%)
- google/gemma-3-4b-it: completion price $0.05/M → $0.1/M (+100.0%)
- moonshotai/kimi-k2.7-code: prompt price $0.671/M → $0.56/M (−16.6%)
- moonshotai/kimi-k2.7-code: completion price $3.35/M → $3.1/M (−7.5%)
- moonshotai/kimi-k3: prompt price $0.152/M → $0.179/M (+17.8%)
2026-10-26 108 change(s)
model price changes
- ~deepseek/deepseek-pro-latest: prompt price $0.119/M → $0.257/M (+115.9%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.042/M → $0.048/M (+12.6%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.169/M → $0.157/M (−7.4%)
- ~moonshotai/kimi-latest: prompt price $0.15/M → $0.152/M (+1.3%)
- ~moonshotai/kimi-latest: completion price $16/M → $20/M (+25.0%)
- ~z-ai/glm-flash-latest: prompt price $0.051/M → $0.041/M (−19.5%)
- ~z-ai/glm-flash-latest: completion price $0.07/M → $0.076/M (+8.1%)
- ~z-ai/glm-latest: prompt price $0.07/M → $0.07/M (−0.6%)
- ~z-ai/glm-latest: completion price $4.38/M → $1.4/M (−68.1%)
- deepseek/deepseek-v4-flash-0731: prompt price $0.042/M → $0.44/M (+942.7%)
- deepseek/deepseek-v4-flash-0731: completion price $0.169/M → $1.32/M (+679.2%)
- deepseek/deepseek-v4-pro: prompt price $0.209/M → $0.955/M (+357.5%)
- deepseek/deepseek-v4-pro: completion price $0.418/M → $1.91/M (+357.5%)
- google/gemma-4-26b-a4b-it: prompt price $0.068/M → $0.09/M (+33.3%)
- google/gemma-4-26b-a4b-it: completion price $0.225/M → $0.3/M (+33.3%)
- moonshotai/kimi-k3: prompt price $0.239/M → $0.152/M (−36.4%)
- moonshotai/kimi-k3: completion price $10.8/M → $20/M (+85.2%)
- qwen/qwen3-30b-a3b-instruct-2507: prompt price $0.09/M → $0.1/M (+11.1%)
- 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 $0.25/M → $0.32/M (+28.0%)
- qwen/qwen3.6-27b: completion price $2/M → $3.2/M (+60.0%)
- z-ai/glm-5.3: prompt price $0.079/M → $0.07/M (−11.5%)
provider price changes
- Baidu: deepseek/deepseek-v4-flash prompt price $0.022/M → $0.14/M (+528.9%)
- Baidu: deepseek/deepseek-v4-flash completion price $0.045/M → $0.28/M (+528.9%)
- Relace: deepseek/deepseek-v4-flash prompt price $0.021/M → $0.05/M (+137.0%)
- StreamLake: deepseek/deepseek-v4-flash prompt price $0.028/M → $0.083/M (+195.0%)
- StreamLake: deepseek/deepseek-v4-flash completion price $0.056/M → $0.165/M (+195.0%)
- Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.044/M → $0.44/M (+890.1%)
- Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.133/M → $1.32/M (+890.1%)
2026-10-25 56 change(s)
added to the catalog
- LiquidAI: LFM2.5-2.6B (liquid/lfm-2.5-2.6b) added to the catalog: 128,000 ctx, $0.35/M in / $0.5/M out
removed from the catalog
- OpenAI: GPT-3.5 Turbo (openai/gpt-3.5-turbo) removed from the catalog
- OpenAI: GPT-3.5 Turbo Instruct (openai/gpt-3.5-turbo-instruct) removed from the catalog
- OpenAI: GPT-3.5 Turbo (batch) (openai/gpt-3.5-turbo:batch) removed from the catalog
model price changes
- ~moonshotai/kimi-latest: prompt price $0.19/M → $0.15/M (−21.1%)
- ~moonshotai/kimi-latest: completion price $8.94/M → $16/M (+79.0%)
- ~z-ai/glm-flash-latest: prompt price $0.018/M → $0.051/M (+193.1%)
- ~z-ai/glm-flash-latest: completion price $0.143/M → $0.07/M (−50.8%)
- ~z-ai/glm-latest: prompt price $0.075/M → $0.07/M (−6.3%)
- ~z-ai/glm-latest: completion price $4.3/M → $4.38/M (+2.1%)
- deepseek/deepseek-v4-flash-0731: prompt price $0.044/M → $0.042/M (−5.0%)
- deepseek/deepseek-v4-flash-0731: completion price $0.133/M → $0.169/M (+27.1%)
- deepseek/deepseek-v4-pro: prompt price $0.388/M → $0.209/M (−46.2%)
- deepseek/deepseek-v4-pro: completion price $0.777/M → $0.418/M (−46.2%)
- meta-llama/llama-3.2-3b-instruct: prompt price $0.051/M → $0.05/M (−1.8%)
- meta-llama/llama-3.2-3b-instruct: completion price $0.335/M → $0.33/M (−1.5%)
- minimax/minimax-m2.5: prompt price $0.27/M → $0.3/M (+11.1%)
- minimax/minimax-m2.5: completion price $0.95/M → $1.2/M (+26.3%)
quantization changes
- Wafer: minimax/minimax-m3.1-flash quantization unknown → nvfp4
provider price changes
- Baidu: deepseek/deepseek-v4-flash prompt price $0.044/M → $0.022/M (−48.9%)
- Baidu: deepseek/deepseek-v4-flash completion price $0.087/M → $0.045/M (−48.9%)
- Relace: deepseek/deepseek-v4-flash prompt price $0.041/M → $0.021/M (−48.9%)
- StreamLake: deepseek/deepseek-v4-flash prompt price $0.043/M → $0.028/M (−34.6%)
- StreamLake: deepseek/deepseek-v4-flash completion price $0.086/M → $0.056/M (−34.6%)
- Wafer: deepseek/deepseek-v4-flash prompt price $0.7/M → $0.6/M (−14.3%)
- Wafer: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.13/M (−7.1%)
- Baidu: deepseek/deepseek-v4-pro prompt price $0.397/M → $0.208/M (−47.7%)
- Baidu: deepseek/deepseek-v4-pro completion price $0.794/M → $0.416/M (−47.7%)
- StreamLake: deepseek/deepseek-v4-pro prompt price $0.388/M → $0.209/M (−46.2%)
- StreamLake: deepseek/deepseek-v4-pro completion price $0.777/M → $0.418/M (−46.2%)
2026-10-24 127 change(s)
added to the catalog
- MoonshotAI: Kimi K3.1 Pro (moonshotai/kimi-k3.1-pro) added to the catalog: 1,048,576 ctx, $2/M in / $10/M out
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.07/M → $0.02/M (−71.4%)
- ~deepseek/deepseek-flash-latest: completion price $0.5/M → $1/M (+100.0%)
- ~deepseek/deepseek-pro-latest: prompt price $0.257/M → $0.119/M (−53.7%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.048/M → $0.042/M (−11.2%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.157/M → $0.169/M (+8.0%)
- ~moonshotai/kimi-latest: prompt price $0.238/M → $0.19/M (−20.2%)
- ~moonshotai/kimi-latest: completion price $16/M → $8.94/M (−44.1%)
- ~z-ai/glm-flash-latest: prompt price $0.005/M → $0.018/M (+236.5%)
- ~z-ai/glm-flash-latest: completion price $0.199/M → $0.143/M (−28.2%)
- ~z-ai/glm-latest: prompt price $0.079/M → $0.075/M (−5.1%)
- ~z-ai/glm-latest: completion price $1.4/M → $4.3/M (+206.8%)
- deepseek/deepseek-v4-flash-0731: prompt price $0.44/M → $0.044/M (−89.9%)
- deepseek/deepseek-v4-flash-0731: completion price $1.32/M → $0.133/M (−89.9%)
- deepseek/deepseek-v4-pro: prompt price $0.955/M → $0.388/M (−59.3%)
- deepseek/deepseek-v4-pro: completion price $1.91/M → $0.777/M (−59.3%)
- deepseek/deepseek-v4.1-flash: prompt price $0.3/M → $0.02/M (−93.3%)
- deepseek/deepseek-v4.1-flash: completion price $1.2/M → $1/M (−16.7%)
- google/gemma-4-26b-a4b-it: prompt price $0.09/M → $0.068/M (−25.0%)
- google/gemma-4-26b-a4b-it: completion price $0.3/M → $0.225/M (−25.0%)
- moonshotai/kimi-k3: completion price $11.9/M → $10.8/M (−9.5%)
- z-ai/glm-5.3-flash: prompt price $0.005/M → $0.15/M (+2784.6%)
- z-ai/glm-5.3-flash: completion price $0.199/M → $0.5/M (+151.9%)
provider price changes
- Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.044/M (−68.9%)
- Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.087/M (−68.9%)
- Relace: deepseek/deepseek-v4-flash prompt price $0.05/M → $0.041/M (−17.4%)
- StreamLake: deepseek/deepseek-v4-flash prompt price $0.07/M → $0.043/M (−38.8%)
- StreamLake: deepseek/deepseek-v4-flash completion price $0.14/M → $0.086/M (−38.8%)
- Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.44/M → $0.044/M (−89.9%)
- Baidu: deepseek/deepseek-v4-flash-0731 completion price $1.32/M → $0.133/M (−89.9%)
2026-10-23 84 change(s)
added to the catalog
- MiniMax: MiniMax M3.1 Flash (minimax/minimax-m3.1-flash) added to the catalog: 1,048,576 ctx, $0.15/M in / $0.6/M out
removed from the catalog
- MiniMax: MiniMax M3.1 Flash (free) (minimax/minimax-m3.1-flash:free) removed from the catalog
model price changes
- ~deepseek/deepseek-pro-latest: prompt price $0.224/M → $0.257/M (+14.8%)
- ~z-ai/glm-flash-latest: completion price $0.193/M → $0.199/M (+2.8%)
- 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%)
- qwen/qwen3.5-9b: prompt price $0.08/M → $0.17/M (+112.5%)
- qwen/qwen3.5-9b: completion price $0.13/M → $0.25/M (+92.3%)
- qwen/qwen3.8-27b: prompt price $0.04/M → $0.2/M (+400.0%)
- qwen/qwen3.8-27b: completion price $1.35/M → $2.5/M (+85.2%)
- reflection/beam-1.0-501b-a23b: prompt price $0.3/M → $0.25/M (−16.7%)
- z-ai/glm-5.3-flash: completion price $0.193/M → $0.199/M (+2.8%)
provider price changes
- Phala: deepseek/deepseek-v4-flash-0731 prompt price $0.308/M → $0.44/M (+42.9%)
- Phala: deepseek/deepseek-v4-flash-0731 completion price $0.924/M → $1.32/M (+42.9%)
- Wafer: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.13/M (−7.1%)
- DekaLLM: deepseek/deepseek-v4-pro-0813 prompt price $0.88/M → $1.08/M (+22.7%)
- Phala: deepseek/deepseek-v4-pro-0813 prompt price $0.957/M → $1.45/M (+51.5%)
- Phala: deepseek/deepseek-v4-pro-0813 completion price $2.88/M → $4.36/M (+51.5%)
- Relace: deepseek/deepseek-v4-pro-0813 prompt price $0.224/M → $0.257/M (+14.8%)
- Wafer: deepseek/deepseek-v4-pro-0813 prompt price $0.25/M → $0.285/M (+14.0%)
- Wafer: deepseek/deepseek-v4-pro-0813 completion price $5/M → $4.3/M (−14.0%)
- DigitalOcean: deepseek/deepseek-v4.1-flash prompt price $0.225/M → $0.165/M (−26.7%)
- DigitalOcean: deepseek/deepseek-v4.1-flash completion price $0.9/M → $0.66/M (−26.7%)
- Morph: deepseek/deepseek-v4.1-flash prompt price $0.313/M → $0.132/M (−57.8%)
- Makora: deepseek/deepseek-v4.1-flash-1017 prompt price $0.3/M → $0.15/M (−50.0%)
- Morph: deepseek/deepseek-v4.1-flash-1017 prompt price $0.313/M → $0.132/M (−57.8%)
- Novita: deepseek/deepseek-v4.1-flash-1017 prompt price $0.3/M → $0.24/M (−20.0%)
- Novita: deepseek/deepseek-v4.1-flash-1017 completion price $1.2/M → $0.96/M (−20.0%)
- NextBit: google/gemma-3-12b-it prompt price $0.1/M → $0.075/M (−25.0%)
- NextBit: google/gemma-3-12b-it completion price $0.175/M → $0.15/M (−14.3%)
2026-10-22 95 change(s)
added to the catalog
- Recursive: Flint (free) (recursive/flint-v1.0:free) added to the catalog: 262,144 ctx, $0/M in / $0/M out
removed from the catalog
- Google: Gemini 2.5 Flash Lite (batch) (google/gemini-2.5-flash-lite:batch) removed from the catalog
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.049/M → $0.07/M (+42.9%)
- ~deepseek/deepseek-flash-latest: completion price $0.375/M → $0.5/M (+33.3%)
- ~deepseek/deepseek-pro-latest: prompt price $0.225/M → $0.224/M (−0.7%)
- ~moonshotai/kimi-latest: completion price $24/M → $16/M (−33.3%)
- ~z-ai/glm-flash-latest: prompt price $0.041/M → $0.005/M (−87.4%)
- ~z-ai/glm-flash-latest: completion price $0.12/M → $0.193/M (+60.8%)
- deepseek/deepseek-v4.1-flash: prompt price $0.049/M → $0.3/M (+512.2%)
- deepseek/deepseek-v4.1-flash: completion price $0.375/M → $1.2/M (+220.0%)
- moonshotai/kimi-k2.7-code: prompt price $0.672/M → $0.671/M (−0.2%)
- moonshotai/kimi-k2.7-code: completion price $3.1/M → $3.35/M (+8.1%)
- 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%)
- 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%)
- z-ai/glm-5.3-flash: prompt price $0.041/M → $0.005/M (−87.4%)
- z-ai/glm-5.3-flash: completion price $0.12/M → $0.193/M (+60.8%)
provider price changes
- StreamLake: deepseek/deepseek-v4-flash prompt price $0.083/M → $0.07/M (−15.3%)
- StreamLake: deepseek/deepseek-v4-flash completion price $0.165/M → $0.14/M (−15.3%)
- Inceptron: deepseek/deepseek-v4-flash-0731 prompt price $0.13/M → $0.11/M (−15.4%)
- Inceptron: deepseek/deepseek-v4-flash-0731 completion price $0.5/M → $0.413/M (−17.4%)
- Phala: deepseek/deepseek-v4-flash-0731 prompt price $0.44/M → $0.308/M (−30.0%)
- Phala: deepseek/deepseek-v4-flash-0731 completion price $1.32/M → $0.924/M (−30.0%)
- Phala: deepseek/deepseek-v4-pro-0813 prompt price $1.45/M → $0.957/M (−34.0%)
- Phala: deepseek/deepseek-v4-pro-0813 completion price $4.36/M → $2.88/M (−34.0%)
- Relace: deepseek/deepseek-v4-pro-0813 prompt price $0.225/M → $0.224/M (−0.7%)
- Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.9/M → $0.45/M (−50.0%)
- Sail Research: deepseek/deepseek-v4-pro-0813 completion price $0.99/M → $0.8/M (−19.2%)
- Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.9/M → $0.45/M (−50.0%)
2026-10-21 136 change(s)
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
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.07/M → $0.049/M (−30.0%)
- ~deepseek/deepseek-flash-latest: completion price $0.5/M → $0.375/M (−25.0%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.015/M → $0.048/M (+214.6%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.45/M → $0.157/M (−65.2%)
- ~moonshotai/kimi-latest: completion price $16/M → $24/M (+50.0%)
- ~z-ai/glm-flash-latest: prompt price $0.047/M → $0.041/M (−12.5%)
- ~z-ai/glm-flash-latest: completion price $0.16/M → $0.12/M (−25.0%)
- deepseek/deepseek-v4.1-flash: prompt price $0.056/M → $0.049/M (−12.5%)
- deepseek/deepseek-v4.1-flash: completion price $0.12/M → $0.375/M (+212.5%)
- mistralai/mistral-large-4-0: prompt price $0.68/M → $1.36/M (+100.0%)
- mistralai/mistral-large-4-0: completion price $2.09/M → $4.18/M (+100.0%)
- moonshotai/kimi-k2.7-code: prompt price $0.671/M → $0.672/M (+0.2%)
- moonshotai/kimi-k2.7-code: completion price $3.35/M → $3.1/M (−7.5%)
- nvidia/nemotron-3-super-120b-a12b: prompt price $0.08/M → $0.3/M (+275.0%)
- nvidia/nemotron-3-super-120b-a12b: completion price $0.45/M → $2.4/M (+433.3%)
- qwen/qwen3.5-35b-a3b: prompt price $0.15/M → $0.14/M (−6.7%)
- qwen/qwen3.5-9b: prompt price $0.1/M → $0.08/M (−20.0%)
- qwen/qwen3.5-9b: completion price $0.15/M → $0.13/M (−13.3%)
- xiaomi/mimo-v2.5: prompt price $0.14/M → $0.119/M (−15.0%)
- xiaomi/mimo-v2.5: completion price $0.28/M → $0.238/M (−15.0%)
- xiaomi/mimo-v2.5-pro: prompt price $0.435/M → $0.304/M (−30.0%)
- xiaomi/mimo-v2.5-pro: completion price $0.87/M → $0.609/M (−30.0%)
- z-ai/glm-5: prompt price $0.6/M → $1/M (+66.7%)
- z-ai/glm-5: completion price $1.92/M → $3.2/M (+66.7%)
- z-ai/glm-5.1: prompt price $0.966/M → $1.4/M (+44.9%)
- z-ai/glm-5.1: completion price $3.04/M → $4.4/M (+44.9%)
- z-ai/glm-5.2: prompt price $0.62/M → $0.034/M (−94.5%)
- z-ai/glm-5.2: completion price $2.42/M → $7/M (+189.3%)
2026-10-20 126 change(s)
added to the catalog
- Inception: Mercury 3 (inception/mercury-3) added to the catalog: 1,000,000 ctx, $0.1/M in / $0.35/M out
- MiniMax: MiniMax M3.1 Flash (free) (minimax/minimax-m3.1-flash:free) added to the catalog: 1,000,000 ctx, $0/M in / $0/M out
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.05/M → $0.07/M (+40.0%)
- ~deepseek/deepseek-flash-latest: completion price $0.15/M → $0.5/M (+233.3%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.004/M → $0.015/M (+285.2%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.12/M → $0.45/M (+275.0%)
- ~moonshotai/kimi-latest: completion price $13/M → $16/M (+23.1%)
- ~z-ai/glm-flash-latest: prompt price $0.048/M → $0.047/M (−1.9%)
- ~z-ai/glm-latest: prompt price $0.042/M → $0.079/M (+88.1%)
- ~z-ai/glm-latest: completion price $6/M → $1.4/M (−76.7%)
- deepseek/deepseek-chat: prompt price $0.32/M → $0.257/M (−19.6%)
- deepseek/deepseek-chat: completion price $0.89/M → $1.03/M (+15.6%)
- deepseek/deepseek-v4-flash-0731: prompt price $0.15/M → $0.44/M (+193.3%)
- deepseek/deepseek-v4-flash-0731: completion price $0.15/M → $1.32/M (+780.0%)
- deepseek/deepseek-v4.1-flash: prompt price $0.044/M → $0.056/M (+27.3%)
- deepseek/deepseek-v4.1-flash: completion price $0.08/M → $0.12/M (+50.0%)
- google/gemma-3-4b-it: prompt price $0.05/M → $0.04/M (−20.0%)
- google/gemma-3-4b-it: completion price $0.1/M → $0.05/M (−50.0%)
- nvidia/nemotron-3.5-super-vl: prompt price $0.1/M → $0.15/M (+50.0%)
- nvidia/nemotron-3.5-super-vl: completion price $0.4/M → $0.5/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/qwen3.6-35b-a3b: prompt price $0.15/M → $0.1/M (−33.3%)
- qwen/qwen3.6-35b-a3b: completion price $1/M → $0.95/M (−5.0%)
- qwen/qwen3.8-27b: prompt price $0.24/M → $0.04/M (−83.3%)
- qwen/qwen3.8-27b: completion price $2.2/M → $1.35/M (−38.6%)
- reflection/beam-1.0-501b-a23b: prompt price $1/M → $0.3/M (−70.0%)
- reflection/beam-1.0-501b-a23b: completion price $3/M → $1/M (−66.7%)
- upstage/solar-pro4: prompt price $0.09/M → $0.15/M (+66.7%)
- upstage/solar-pro4: completion price $0.36/M → $0.6/M (+66.7%)
2026-10-19 140 change(s)
removed from the catalog
- DeepSeek: R1 (deepseek/deepseek-r1) removed from the catalog
- WizardLM-2 8x22B (microsoft/wizardlm-2-8x22b) removed from the catalog
- Sao10K: Llama 3.3 Euryale 70B (sao10k/l3.3-euryale-70b) removed from the catalog
model price changes
- ~deepseek/deepseek-flash-latest: completion price $0.6/M → $0.15/M (−75.0%)
- ~deepseek/deepseek-pro-latest: prompt price $0.12/M → $0.225/M (+87.5%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.015/M → $0.004/M (−74.0%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.45/M → $0.12/M (−73.3%)
- ~moonshotai/kimi-latest: prompt price $0.27/M → $0.238/M (−11.9%)
- ~moonshotai/kimi-latest: completion price $14/M → $13/M (−7.1%)
- ~z-ai/glm-flash-latest: completion price $0.2/M → $0.16/M (−20.0%)
- ~z-ai/glm-latest: prompt price $0.063/M → $0.042/M (−33.5%)
- ~z-ai/glm-latest: completion price $4.4/M → $6/M (+36.4%)
- deepseek/deepseek-v4-flash-0731: prompt price $0.015/M → $0.15/M (+893.4%)
- deepseek/deepseek-v4-flash-0731: completion price $0.45/M → $0.15/M (−66.7%)
- deepseek/deepseek-v4-pro: prompt price $0.209/M → $0.955/M (+357.5%)
- deepseek/deepseek-v4-pro: completion price $0.418/M → $1.91/M (+357.5%)
- deepseek/deepseek-v4.1-flash: prompt price $0.065/M → $0.044/M (−32.1%)
- deepseek/deepseek-v4.1-flash: completion price $0.144/M → $0.08/M (−44.4%)
- google/gemma-4-26b-a4b-it: prompt price $0.068/M → $0.09/M (+33.3%)
- google/gemma-4-26b-a4b-it: completion price $0.225/M → $0.3/M (+33.3%)
- meta-llama/llama-3.2-3b-instruct: prompt price $0.05/M → $0.051/M (+1.8%)
- meta-llama/llama-3.2-3b-instruct: completion price $0.33/M → $0.335/M (+1.5%)
- moonshotai/kimi-k3: prompt price $0.304/M → $0.239/M (−21.4%)
- qwen/qwen3.5-27b: prompt price $0.26/M → $0.27/M (+3.8%)
- qwen/qwen3.5-27b: completion price $2.6/M → $2.16/M (−16.9%)
- 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-5.3: completion price $2.5/M → $1.4/M (−44.0%)
- z-ai/glm-5.3-flash: completion price $0.2/M → $0.16/M (−20.0%)
model context changes
- meta-llama/llama-4-maverick: context length 1,048,576 → 524,288
2026-10-18 85 change(s)
added to the catalog
- Pareto 26.10 (unbiased/pareto-26.10) added to the catalog: 1,048,576 ctx, $0.8/M in / $3.2/M out
model price changes
- ~deepseek/deepseek-flash-latest: prompt price $0.15/M → $0.05/M (−66.7%)
- ~deepseek/deepseek-pro-latest: prompt price $0.123/M → $0.12/M (−2.7%)
- ~deepseek/deepseek-pro-latest: completion price $0.559/M → $8/M (+1331.6%)
- ~deepseek/deepseek-v4-flash-latest: prompt price $0.01/M → $0.015/M (+55.7%)
- ~deepseek/deepseek-v4-flash-latest: completion price $0.297/M → $0.45/M (+51.5%)
- ~moonshotai/kimi-latest: completion price $14.2/M → $14/M (−1.6%)
- ~unbiased/pareto-latest: prompt price $2.5/M → $0.8/M (−68.0%)
- ~unbiased/pareto-latest: completion price $7.5/M → $3.2/M (−57.3%)
- ~z-ai/glm-flash-latest: prompt price $0.029/M → $0.048/M (+63.8%)
- ~z-ai/glm-flash-latest: completion price $0.418/M → $0.2/M (−52.2%)
- ~z-ai/glm-latest: prompt price $0.069/M → $0.063/M (−8.4%)
- ~z-ai/glm-latest: completion price $3.94/M → $4.4/M (+11.7%)
- deepseek/deepseek-v4-flash-0731: prompt price $0.01/M → $0.015/M (+55.7%)
- deepseek/deepseek-v4-flash-0731: completion price $0.297/M → $0.45/M (+51.5%)
- deepseek/deepseek-v4.1-flash: prompt price $0.15/M → $0.065/M (−56.8%)
- deepseek/deepseek-v4.1-flash: completion price $0.6/M → $0.144/M (−76.0%)
- google/gemma-3-27b-it: completion price $0.45/M → $0.35/M (−22.2%)
- qwen/qwen3-30b-a3b-instruct-2507: prompt price $0.1/M → $0.09/M (−10.0%)
- z-ai/glm-5.3: completion price $4.8/M → $2.5/M (−47.9%)
- z-ai/glm-5.3-flash: prompt price $0.029/M → $0.048/M (+63.8%)
- z-ai/glm-5.3-flash: completion price $0.418/M → $0.2/M (−52.2%)
model context changes
- ~unbiased/pareto-latest: context length 262,144 → 1,048,576
provider price changes
- Baidu: deepseek/deepseek-v4-flash prompt price $0.021/M → $0.014/M (−34.0%)
- Baidu: deepseek/deepseek-v4-flash completion price $0.043/M → $0.028/M (−34.0%)
- OpenInference: deepseek/deepseek-v4-flash prompt price $0.022/M → $0.011/M (−47.2%)
- OpenInference: deepseek/deepseek-v4-flash completion price $0.139/M → $0.024/M (−82.7%)
- Relace: deepseek/deepseek-v4-flash prompt price $0.022/M → $0.014/M (−34.0%)
- Relace: deepseek/deepseek-v4-flash completion price $0.139/M → $0.45/M (+224.2%)
- Wafer: deepseek/deepseek-v4-flash prompt price $0.58/M → $0.7/M (+20.7%)
$ curl variables.md — this site speaks markdown to your terminal.