← variables.md

2026-10-21

136 change(s) in the model market

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%)
• z-ai/glm-5.3-flash: prompt price $0.047/M → $0.041/M (−12.5%)
• z-ai/glm-5.3-flash: completion price $0.16/M → $0.12/M (−25.0%)

provider price changes

• Inceptron: deepseek/deepseek-v4-flash-0731 completion price $0.4/M → $0.5/M (+25.0%)
• Reka: deepseek/deepseek-v4-flash-0731 prompt price $0.021/M → $0.05/M (+138.1%)
• Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.015/M → $0.048/M (+214.6%)
• Relace: deepseek/deepseek-v4-flash-0731 completion price $0.45/M → $0.157/M (−65.2%)
• Reka: deepseek/deepseek-v4-pro prompt price $1.2/M → $1.05/M (−12.5%)
• Reka: deepseek/deepseek-v4-pro completion price $2.4/M → $2.1/M (−12.5%)
• Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.896/M → $0.9/M (+0.4%)
• Sail Research: deepseek/deepseek-v4-pro-0813 completion price $0.582/M → $0.99/M (+70.1%)
• Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.896/M → $0.9/M (+0.4%)
• Sail Research: deepseek/deepseek-v4-pro-0813 completion price $0.582/M → $0.99/M (+70.1%)
• Morph: deepseek/deepseek-v4.1-flash prompt price $0.091/M → $0.187/M (+105.5%)
• OpenInference: deepseek/deepseek-v4.1-flash prompt price $0.056/M → $0.049/M (−12.5%)
• OpenInference: deepseek/deepseek-v4.1-flash completion price $0.12/M → $0.375/M (+212.5%)
• Morph: deepseek/deepseek-v4.1-flash-1017 prompt price $0.091/M → $0.187/M (+105.5%)
• Mistral: mistralai/mistral-large-4-0 prompt price $0.68/M → $1.36/M (+100.0%)
• Mistral: mistralai/mistral-large-4-0 completion price $2.09/M → $4.18/M (+100.0%)
• Mistral: mistralai/mistral-large-4-0 prompt price $0.68/M → $1.36/M (+100.0%)
• Mistral: mistralai/mistral-large-4-0 completion price $2.09/M → $4.18/M (+100.0%)
• Mistral: mistralai/mistral-large-4-0 prompt price $0.748/M → $1.5/M (+100.0%)
• Mistral: mistralai/mistral-large-4-0 completion price $2.3/M → $4.6/M (+100.0%)
• Inceptron: moonshotai/kimi-k2.6 prompt price $0.441/M → $0.472/M (+7.1%)
• Inceptron: moonshotai/kimi-k2.7-code prompt price $0.671/M → $0.672/M (+0.2%)
• Inceptron: moonshotai/kimi-k2.7-code completion price $3.35/M → $3.1/M (−7.5%)
• InferenceNet: moonshotai/kimi-k3 prompt price $2.24/M → $2.04/M (−8.9%)
• InferenceNet: moonshotai/kimi-k3 completion price $14.5/M → $13.2/M (−9.1%)
• Morph: moonshotai/kimi-k3 prompt price $0.935/M → $0.814/M (−12.9%)
• Parasail: moonshotai/kimi-k3 prompt price $3/M → $4.5/M (+50.0%)
• Parasail: moonshotai/kimi-k3 completion price $15/M → $22.5/M (+50.0%)
• Relace: moonshotai/kimi-k3 prompt price $0.8/M → $0.3/M (−62.5%)
• Relace: moonshotai/kimi-k3 completion price $3/M → $12/M (+300.0%)
• Sail Research: moonshotai/kimi-k3 completion price $9/M → $5.5/M (−38.9%)
• Sail Research: moonshotai/kimi-k3 completion price $9/M → $5.5/M (−38.9%)
• Wafer: moonshotai/kimi-k3 completion price $16/M → $24/M (+50.0%)
• BaseTen: reflection/beam-1.0-501b-a23b prompt price $1.3/M → $0.4/M (−69.2%)
• BaseTen: reflection/beam-1.0-501b-a23b completion price $4.3/M → $1.2/M (−72.1%)
• Relace: xiaomi/mimo-v2.6-flash prompt price $0.03/M → $0.1/M (+233.3%)
• Relace: xiaomi/mimo-v2.6-flash completion price $0.08/M → $0.24/M (+200.0%)
• Decart: z-ai/glm-5.2 prompt price $2.5/M → $1.2/M (−52.0%)
• Decart: z-ai/glm-5.2 completion price $9/M → $8/M (−11.1%)
• Morph: z-ai/glm-5.2 prompt price $0.179/M → $0.228/M (+27.4%)
• Decart: z-ai/glm-5.3 completion price $2.68/M → $2.71/M (+1.1%)
• Morph: z-ai/glm-5.3 prompt price $0.179/M → $0.228/M (+27.4%)
• Sail Research: z-ai/glm-5.3 prompt price $0.5/M → $0.75/M (+50.0%)
• Sail Research: z-ai/glm-5.3 completion price $1.5/M → $1/M (−33.6%)
• Sail Research: z-ai/glm-5.3 prompt price $0.5/M → $0.75/M (+50.0%)
• Sail Research: z-ai/glm-5.3 completion price $1.5/M → $1/M (−33.6%)
• DeepInfra: z-ai/glm-5.3-flash prompt price $0.075/M → $0.15/M (+100.0%)
• DeepInfra: z-ai/glm-5.3-flash completion price $0.25/M → $0.5/M (+100.0%)
• Inceptron: z-ai/glm-5.3-flash prompt price $0.1/M → $0.175/M (+75.0%)
• Morph: z-ai/glm-5.3-flash prompt price $0.148/M → $0.6/M (+305.4%)
• NextBit: z-ai/glm-5.3-flash completion price $0.4/M → $0.8/M (+100.0%)
• OpenInference: z-ai/glm-5.3-flash prompt price $0.047/M → $0.041/M (−12.5%)
• OpenInference: z-ai/glm-5.3-flash completion price $0.16/M → $0.12/M (−25.0%)
• Reka: z-ai/glm-5.3-flash prompt price $0.06/M → $0.1/M (+66.7%)
• Reka: z-ai/glm-5.3-flash completion price $1.6/M → $2.4/M (+50.0%)
• Relace: z-ai/glm-5.3-flash completion price $0.5/M → $0.16/M (−68.0%)
• Sail Research: z-ai/glm-5.3-flash prompt price $0.078/M → $0.09/M (+14.9%)
• Sail Research: z-ai/glm-5.3-flash completion price $0.3/M → $0.15/M (−50.0%)
• Sail Research: z-ai/glm-5.3-flash prompt price $0.078/M → $0.09/M (+14.9%)
• Sail Research: z-ai/glm-5.3-flash completion price $0.3/M → $0.15/M (−50.0%)
• Wafer: z-ai/glm-5.3-flash prompt price $0.059/M → $0.074/M (+25.4%)

provider context changes

• Reka: z-ai/glm-5.3 context length 262,144 → 1,048,576

providers added

• Crusoe now serves deepseek/deepseek-v4.1-flash (fp8, 1,048,576 ctx, $0.29/M in / $1.2/M out)
• Fireworks now serves deepseek/deepseek-v4.1-flash (unknown, 1,048,576 ctx, $0.21/M in / $0.84/M out)
• Google now serves deepseek/deepseek-v4.1-flash (unknown, 1,048,576 ctx, $0.3/M in / $1.2/M out)
• InferenceNet now serves deepseek/deepseek-v4.1-flash (fp8, 1,040,000 ctx, $0.103/M in / $0.715/M out)
• InferenceNet now serves deepseek/deepseek-v4.1-flash-1017 (fp8, 1,040,000 ctx, $0.08/M in / $0.5/M out)
• Novita now serves deepseek/deepseek-v4.1-flash-1017 (fp8, 1,048,576 ctx, $0.3/M in / $1.2/M out)
• OpenInference now serves deepseek/deepseek-v4.1-flash-1017 (fp4, 1,048,576 ctx, $0.049/M in / $0.375/M out)
• Phala now serves deepseek/deepseek-v4.1-flash-1017 (unknown, 1,048,576 ctx, $0.3/M in / $1.2/M out)
• Reka now serves deepseek/deepseek-v4.1-flash-1017 (unknown, 1,048,576 ctx, $0.15/M in / $0.6/M out)
• InferenceNet now serves inference-net/schematron-v2-small (bf16, 128,000 ctx, $0.05/M in / $0.23/M out)
• InferenceNet now serves inference-net/schematron-v2-turbo (bf16, 128,000 ctx, $0.03/M in / $0.15/M out)
• InferenceNet now serves moonshotai/kimi-k3 (fp4, 1,048,576 ctx, $0.239/M in / $11.9/M out)
• InferenceNet now serves moonshotai/kimi-k3 (fp4, 1,048,576 ctx, $2.24/M in / $14.5/M out)
• InferenceNet now serves stepfun/step-5-preview (fp4, 1,048,576 ctx, $1/M in / $2.7/M out)
• StreamLake now serves xiaomi/mimo-v2.6-pro (unknown, 1,000,000 ctx, $0.522/M in / $1.04/M out)
• InferenceNet now serves z-ai/glm-5.3 (fp4, 1,048,576 ctx, $0.08/M in / $4.38/M out)
• InferenceNet now serves z-ai/glm-5.3-flash (fp4, 1,048,576 ctx, $0.12/M in / $0.388/M out)

providers removed

• OpenInference no longer serves deepseek/deepseek-v4-flash (was fp4)
• OpenInference no longer serves deepseek/deepseek-v4-flash-0731 (was fp4)
• Fireworks no longer serves deepseek/deepseek-v4.1-flash (was unknown)
• Google no longer serves google/gemini-2.5-flash (was unknown)
• Google no longer serves google/gemini-2.5-flash (was unknown)
• Google no longer serves google/gemini-2.5-flash (was unknown)
• Google no longer serves google/gemini-2.5-flash (was unknown)
• Google no longer serves google/gemini-2.5-flash-lite (was unknown)
• Google no longer serves google/gemini-2.5-flash-lite (was unknown)
• Google no longer serves google/gemini-2.5-pro (was unknown)
• Google no longer serves google/gemini-2.5-pro (was unknown)
• Google no longer serves google/gemini-2.5-pro (was unknown)
• Google no longer serves google/gemini-2.5-pro (was unknown)
• Google no longer serves google/gemini-2.5-pro-preview (was unknown)
• Google no longer serves google/gemini-2.5-pro-preview (was unknown)
• Google no longer serves google/gemini-2.5-pro-preview (was unknown)
• Google no longer serves google/gemini-2.5-pro-preview (was unknown)
• Phala no longer serves moonshotai/kimi-k2.7-code (was unknown)
• Fireworks no longer serves moonshotai/kimi-k3 (was unknown)
• Venice no longer serves qwen/qwen3.5-9b (was fp8)
• Tenstorrent no longer serves qwen/qwen3.8-27b (was fp4)
• StreamLake no longer serves xiaomi/mimo-v2.5 (was unknown)
• Xiaomi no longer serves xiaomi/mimo-v2.5 (was fp8)
• StreamLake no longer serves xiaomi/mimo-v2.5-pro (was unknown)
• Xiaomi no longer serves xiaomi/mimo-v2.5-pro (was fp8)

openrouter catalog snapshots 2026-10-20 → 2026-10-21 · schema 1 · generated 2026-10-21T10:09:38.541Z