← variables.md

2026-10-30

120 change(s) in the model market

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%)
• StreamLake: deepseek/deepseek-v4-pro completion price $1.91/M → $1.63/M (−14.6%)
• DekaLLM: deepseek/deepseek-v4-pro-0813 prompt price $1.08/M → $0.88/M (−18.5%)
• Relace: deepseek/deepseek-v4-pro-0813 completion price $8/M → $4/M (−50.0%)
• Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.45/M → $0.675/M (+50.0%)
• Sail Research: deepseek/deepseek-v4-pro-0813 completion price $0.8/M → $1.2/M (+50.0%)
• Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.45/M → $0.675/M (+50.0%)
• Sail Research: deepseek/deepseek-v4-pro-0813 completion price $0.8/M → $1.2/M (+50.0%)
• InferenceNet: deepseek/deepseek-v4.1-flash prompt price $0.103/M → $0.134/M (+30.1%)
• InferenceNet: deepseek/deepseek-v4.1-flash completion price $0.6/M → $0.51/M (−15.0%)
• InferenceNet: deepseek/deepseek-v4.1-flash prompt price $0.103/M → $0.134/M (+30.1%)
• InferenceNet: deepseek/deepseek-v4.1-flash completion price $0.6/M → $0.51/M (−15.0%)
• Morph: deepseek/deepseek-v4.1-flash prompt price $0.044/M → $0.031/M (−29.5%)
• Morph: deepseek/deepseek-v4.1-flash completion price $0.383/M → $0.27/M (−29.5%)
• OpenInference: deepseek/deepseek-v4.1-flash prompt price $0.014/M → $0.043/M (+207.1%)
• OpenInference: deepseek/deepseek-v4.1-flash completion price $1.76/M → $1.04/M (−40.9%)
• Decart: deepseek/deepseek-v4.1-flash-1017 prompt price $0.103/M → $0.123/M (+18.8%)
• Decart: deepseek/deepseek-v4.1-flash-1017 completion price $0.414/M → $0.492/M (+18.8%)
• Ionstream: deepseek/deepseek-v4.1-flash-1017 prompt price $0.15/M → $0.165/M (+10.0%)
• Ionstream: deepseek/deepseek-v4.1-flash-1017 completion price $0.45/M → $0.495/M (+10.0%)
• Morph: deepseek/deepseek-v4.1-flash-1017 prompt price $0.044/M → $0.031/M (−29.5%)
• Morph: deepseek/deepseek-v4.1-flash-1017 completion price $0.383/M → $0.27/M (−29.5%)
• OpenInference: deepseek/deepseek-v4.1-flash-1017 prompt price $0.021/M → $0.034/M (+59.9%)
• OpenInference: deepseek/deepseek-v4.1-flash-1017 completion price $1.8/M → $1.14/M (−36.7%)
• Reka: deepseek/deepseek-v4.1-flash-1017 prompt price $0.04/M → $0.06/M (+50.0%)
• Reka: deepseek/deepseek-v4.1-flash-1017 completion price $0.5/M → $0.6/M (+20.0%)
• Wafer: deepseek/deepseek-v4.1-flash-1017 prompt price $0.07/M → $0.066/M (−5.7%)
• PrimeIntellect: google/gemma-4-26b-a4b-it prompt price $0.1/M → $0.035/M (−65.0%)
• PrimeIntellect: google/gemma-4-26b-a4b-it completion price $0.3/M → $0.105/M (−65.0%)
• GMICloud: minimax/minimax-m3.1-flash prompt price $0.143/M → $0.112/M (−21.1%)
• GMICloud: minimax/minimax-m3.1-flash completion price $0.57/M → $0.45/M (−21.1%)
• SambaNova: minimax/minimax-m3.1-flash prompt price $0.15/M → $0.06/M (−60.0%)
• SambaNova: minimax/minimax-m3.1-flash completion price $0.6/M → $0.24/M (−60.0%)
• Mistral: mistralai/mistral-large-4-0 prompt price $1.36/M → $0.7/M (−48.5%)
• Mistral: mistralai/mistral-large-4-0 completion price $4.18/M → $2.1/M (−49.8%)
• Mistral: mistralai/mistral-large-4-0 prompt price $1.36/M → $0.7/M (−48.5%)
• Mistral: mistralai/mistral-large-4-0 completion price $4.18/M → $2.1/M (−49.8%)
• Mistral: mistralai/mistral-large-4-0 prompt price $1.5/M → $0.77/M (−48.5%)
• Mistral: mistralai/mistral-large-4-0 completion price $4.6/M → $2.31/M (−49.8%)
• Inceptron: moonshotai/kimi-k2.6 prompt price $0.624/M → $0.682/M (+9.4%)
• Decart: moonshotai/kimi-k3 prompt price $1.65/M → $1.95/M (+18.2%)
• Decart: moonshotai/kimi-k3 completion price $8.25/M → $9.75/M (+18.2%)
• InferenceNet: moonshotai/kimi-k3 prompt price $0.239/M → $0.18/M (−24.7%)
• InferenceNet: moonshotai/kimi-k3 completion price $10.8/M → $7.5/M (−30.6%)
• InferenceNet: moonshotai/kimi-k3 prompt price $0.239/M → $0.18/M (−24.7%)
• InferenceNet: moonshotai/kimi-k3 completion price $10.8/M → $7.5/M (−30.6%)
• Makora: moonshotai/kimi-k3 completion price $15/M → $13/M (−13.3%)
• Relace: moonshotai/kimi-k3 prompt price $0.182/M → $0.171/M (−6.2%)
• Relace: moonshotai/kimi-k3 completion price $9.34/M → $10.2/M (+8.7%)
• Wafer: moonshotai/kimi-k3 prompt price $0.33/M → $0.276/M (−16.4%)
• Wafer: moonshotai/kimi-k3 completion price $11.9/M → $9.94/M (−16.5%)
• Wafer: moonshotai/kimi-k3 prompt price $0.5/M → $0.161/M (−67.8%)
• Darkbloom: qwen/qwen3.8-27b completion price $2.2/M → $1.5/M (−31.8%)
• Tenstorrent: qwen/qwen3.8-27b completion price $1.5/M → $2/M (+33.3%)
• DeepInfra: xiaomi/mimo-v2.6-flash prompt price $0.126/M → $0.14/M (+11.1%)
• DeepInfra: xiaomi/mimo-v2.6-flash completion price $0.252/M → $0.28/M (+11.1%)
• Makora: xiaomi/mimo-v2.6-flash prompt price $0.13/M → $0.11/M (−15.4%)
• Relace: xiaomi/mimo-v2.6-flash prompt price $0.13/M → $0.087/M (−33.1%)
• Relace: xiaomi/mimo-v2.6-flash completion price $0.28/M → $0.187/M (−33.2%)
• Inceptron: z-ai/glm-5.2 prompt price $1.2/M → $1.4/M (+16.7%)
• Morph: z-ai/glm-5.2 prompt price $0.226/M → $0.086/M (−61.9%)
• Morph: z-ai/glm-5.2 completion price $2.21/M → $1.4/M (−36.6%)
• DekaLLM: z-ai/glm-5.3 prompt price $0.25/M → $0.18/M (−28.0%)
• Inceptron: z-ai/glm-5.3 prompt price $1.2/M → $1.4/M (+16.7%)
• Inceptron: z-ai/glm-5.3 completion price $2.2/M → $2.42/M (+10.0%)
• Makora: z-ai/glm-5.3 completion price $4.4/M → $3/M (−31.8%)
• Morph: z-ai/glm-5.3 prompt price $0.226/M → $0.086/M (−61.9%)
• Morph: z-ai/glm-5.3 completion price $2.21/M → $1.4/M (−36.6%)
• Morph: z-ai/glm-5.3-flash prompt price $0.138/M → $0.049/M (−64.5%)
• Morph: z-ai/glm-5.3-flash completion price $0.226/M → $0.35/M (+54.9%)
• OpenInference: z-ai/glm-5.3-flash prompt price $0.048/M → $0.025/M (−48.2%)
• Relace: z-ai/glm-5.3-flash prompt price $0.046/M → $0.024/M (−48.1%)
• Relace: z-ai/glm-5.3-flash completion price $0.074/M → $0.104/M (+40.4%)

provider context changes

• Nebius: deepseek/deepseek-v4-pro-0813 context length 979,000 → 1,048,576
• Nebius: deepseek/deepseek-v4.1-flash context length 1,048,000 → 1,048,576
• Nebius: z-ai/glm-5.3 context length 1,024,000 → 1,048,576

providers added

• Wafer now serves deepseek/deepseek-v4-flash-0731 (nvfp4, 1,048,576 ctx, $0.039/M in / $0.3/M out)
• Fireworks now serves meta/muse-spark-open (unknown, 1,048,576 ctx, $1.25/M in / $4.25/M out)
• Amazon Bedrock now serves openai/gpt-5.6-luna (unknown, 1,050,000 ctx, $0.2/M in / $1.2/M out)
• Amazon Bedrock now serves openai/gpt-5.6-sol (unknown, 1,050,000 ctx, $4/M in / $20/M out)
• Amazon Bedrock now serves openai/gpt-6-astra (unknown, 1,050,000 ctx, $10/M in / $50/M out)
• Amazon Bedrock now serves openai/gpt-6-sol (unknown, 1,050,000 ctx, $2/M in / $10/M out)
• Amazon Bedrock now serves openai/gpt-6.1-sol (unknown, 1,050,000 ctx, $2/M in / $10/M out)
• DeepInfra now serves openai/gpt-oss-120b (fp8, 131,072 ctx, $0.2/M in / $0.95/M out)
• Tenstorrent now serves qwen/qwen3-32b (fp8, 20,000 ctx, $0.14/M in / $0.4/M out)
• GMICloud now serves stepfun/step-5-preview (fp8, 1,048,576 ctx, $1/M in / $2.7/M out)

providers removed

• StreamLake no longer serves deepseek/deepseek-v3.1-terminus (was unknown)
• DeepInfra no longer serves gryphe/mythomax-l2-13b (was fp16)
• Together no longer serves meta/muse-glimmer-30b (was unknown)
• Nebius no longer serves minimax/minimax-m3.1-flash (was fp4)
• Nebius no longer serves nvidia/nemotron-3.5-super-vl (was bf16)

openrouter catalog snapshots 2026-10-29 → 2026-10-30 · schema 1 · generated 2026-10-30T11:24:10.432Z