← variables.md

2026-10-29

110 change(s) in the model market

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%)

model context changes

• nvidia/nemotron-3-super-120b-a12b: context length 262,144 → 1,048,576
• stepfun/step-5-preview: context length 1,048,576 → 1,000,000

provider price changes

• Inceptron: deepseek/deepseek-v4-flash-0731 completion price $0.495/M → $0.369/M (−25.5%)
• Reka: deepseek/deepseek-v4-flash-0731 prompt price $0.05/M → $0.1/M (+100.0%)
• Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.048/M → $0.057/M (+20.0%)
• Relace: deepseek/deepseek-v4-flash-0731 completion price $0.157/M → $0.134/M (−14.5%)
• Wafer: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.1/M (−28.6%)
• Relace: deepseek/deepseek-v4-pro-0813 prompt price $0.254/M → $0.103/M (−59.3%)
• Morph: deepseek/deepseek-v4.1-flash prompt price $0.063/M → $0.044/M (−30.2%)
• Morph: deepseek/deepseek-v4.1-flash completion price $0.548/M → $0.383/M (−30.1%)
• OpenInference: deepseek/deepseek-v4.1-flash prompt price $0.001/M → $0.014/M (+886.0%)
• OpenInference: deepseek/deepseek-v4.1-flash completion price $0.536/M → $1.76/M (+228.4%)
• AtlasCloud: deepseek/deepseek-v4.1-flash-1017 prompt price $0.135/M → $0.195/M (+44.4%)
• AtlasCloud: deepseek/deepseek-v4.1-flash-1017 completion price $0.54/M → $0.78/M (+44.4%)
• Decart: deepseek/deepseek-v4.1-flash-1017 prompt price $0.129/M → $0.103/M (−19.8%)
• Decart: deepseek/deepseek-v4.1-flash-1017 completion price $0.516/M → $0.414/M (−19.8%)
• Morph: deepseek/deepseek-v4.1-flash-1017 prompt price $0.063/M → $0.044/M (−30.2%)
• Morph: deepseek/deepseek-v4.1-flash-1017 completion price $0.548/M → $0.383/M (−30.1%)
• OpenInference: deepseek/deepseek-v4.1-flash-1017 prompt price $0.013/M → $0.021/M (+68.3%)
• Inceptron: moonshotai/kimi-k2.7-code prompt price $0.672/M → $0.56/M (−16.7%)
• Makora: moonshotai/kimi-k3 prompt price $0.65/M → $0.5/M (−23.1%)
• Morph: moonshotai/kimi-k3 prompt price $1.04/M → $1.28/M (+23.5%)
• Relace: moonshotai/kimi-k3 prompt price $0.16/M → $0.182/M (+13.6%)
• Relace: moonshotai/kimi-k3 completion price $8.1/M → $9.34/M (+15.3%)
• Wafer: moonshotai/kimi-k3 prompt price $0.159/M → $0.192/M (+20.8%)
• Wafer: moonshotai/kimi-k3 completion price $20/M → $15/M (−25.0%)
• Wafer: moonshotai/kimi-k3 prompt price $0.36/M → $0.33/M (−8.3%)
• Inceptron: z-ai/glm-5.2 prompt price $0.99/M → $1.2/M (+21.2%)
• Inceptron: z-ai/glm-5.2 completion price $4.32/M → $4.4/M (+1.9%)
• Morph: z-ai/glm-5.2 prompt price $0.203/M → $0.226/M (+11.3%)
• Relace: z-ai/glm-5.2 prompt price $0.013/M → $0.007/M (−51.1%)
• Relace: z-ai/glm-5.2 completion price $7.73/M → $7.91/M (+2.2%)
• Wafer: z-ai/glm-5.2 prompt price $0.014/M → $0.006/M (−57.1%)
• Baidu: z-ai/glm-5.3 prompt price $1.4/M → $0.28/M (−80.0%)
• Baidu: z-ai/glm-5.3 completion price $4.4/M → $0.88/M (−80.0%)
• Inceptron: z-ai/glm-5.3 completion price $3.5/M → $2.2/M (−37.1%)
• Morph: z-ai/glm-5.3 prompt price $0.203/M → $0.226/M (+11.3%)
• DigitalOcean: z-ai/glm-5.3-flash prompt price $0.131/M → $0.112/M (−14.3%)
• DigitalOcean: z-ai/glm-5.3-flash completion price $0.438/M → $0.375/M (−14.3%)
• Morph: z-ai/glm-5.3-flash prompt price $0.073/M → $0.138/M (+89.0%)
• Morph: z-ai/glm-5.3-flash completion price $0.322/M → $0.226/M (−29.8%)
• NextBit: z-ai/glm-5.3-flash prompt price $0.125/M → $0.12/M (−4.0%)
• NextBit: z-ai/glm-5.3-flash completion price $0.5/M → $0.48/M (−4.0%)
• OpenInference: z-ai/glm-5.3-flash prompt price $0.021/M → $0.048/M (+132.4%)
• OpenInference: z-ai/glm-5.3-flash completion price $0.052/M → $0.063/M (+21.1%)
• Reka: z-ai/glm-5.3-flash completion price $0.5/M → $0.3/M (−40.0%)
• Relace: z-ai/glm-5.3-flash prompt price $0.02/M → $0.046/M (+132.0%)
• Relace: z-ai/glm-5.3-flash completion price $0.124/M → $0.074/M (−40.1%)

provider context changes

• Crusoe: nvidia/nemotron-3-super-120b-a12b context length 262,144 → 1,048,576
• Crusoe: nvidia/nemotron-3.5-super-vl context length 262,144 → 1,048,576

providers added

• Amazon Bedrock now serves anthropic/claude-sonnet-5.5 (unknown, 1,000,000 ctx, $2.2/M in / $11/M out)
• Amazon Bedrock now serves anthropic/claude-sonnet-5.5 (unknown, 1,000,000 ctx, $2.2/M in / $11/M out)
• Wafer now serves deepseek/deepseek-v4-pro-0813 (mxfp4, 1,048,576 ctx, $0.115/M in / $4.3/M out)
• Wafer now serves deepseek/deepseek-v4.1-flash (mxfp4, 1,048,576 ctx, $0.045/M in / $0.5/M out)
• Cohere now serves deepseek/deepseek-v4.1-flash-1017 (unknown, 1,048,576 ctx, $0.195/M in / $0.66/M out)
• Mistral now serves deepseek/deepseek-v4.1-flash-1017 (fp8, 1,048,576 ctx, $0.3/M in / $1.2/M out)
• ModelRun now serves deepseek/deepseek-v4.1-flash-1017 (fp4, 1,048,576 ctx, $0.17/M in / $0.67/M out)
• Particle AI now serves deepseek/deepseek-v4.1-flash-1017 (unknown, 1,048,576 ctx, $0.25/M in / $1/M out)
• Venice now serves deepseek/deepseek-v4.1-flash-1017 (fp8, 1,000,000 ctx, $0.3/M in / $1.2/M out)
• Wafer now serves deepseek/deepseek-v4.1-flash-1017 (mxfp4, 1,048,576 ctx, $0.038/M in / $0.5/M out)
• Particle AI now serves z-ai/glm-5.3-flash (nvfp4, 1,048,576 ctx, $0.15/M in / $0.5/M out)
• Wafer now serves z-ai/glm-5.3-flash (nvfp4, 1,048,576 ctx, $0.054/M in / $0.2/M out)

providers removed

• Google no longer serves deepseek/deepseek-v3.2 (was unknown)
• Venice no longer serves deepseek/deepseek-v3.2 (was unknown)
• ModelRun no longer serves deepseek/deepseek-v4.1-flash (was fp4)
• Google no longer serves minimax/minimax-m2 (was unknown)
• Google no longer serves moonshotai/kimi-k2-thinking (was unknown)
• OpenAI no longer serves openai/gpt-4 (was unknown)
• OpenAI no longer serves openai/gpt-4-turbo (was unknown)
• OpenAI no longer serves openai/gpt-4.1-nano (was unknown)
• OpenAI no longer serves openai/gpt-4o-2024-05-13 (was unknown)
• Google no longer serves openai/gpt-oss-20b (was unknown)
• OpenAI no longer serves openai/o3-mini (was unknown)
• OpenAI no longer serves openai/o4-mini (was unknown)
• Google no longer serves qwen/qwen3-235b-a22b-2507 (was unknown)
• Tenstorrent no longer serves qwen/qwen3-32b (was fp8)
• Google no longer serves qwen/qwen3-coder (was unknown)
• Google no longer serves qwen/qwen3-next-80b-a3b-instruct (was unknown)
• DeepInfra no longer serves stepfun/step-5-preview (was fp8)
• Google no longer serves z-ai/glm-4.7 (was unknown)

openrouter catalog snapshots 2026-10-28 → 2026-10-29 · schema 1 · generated 2026-10-29T11:31:19.291Z