← variables.md

2026-10-17

161 change(s) in the model market

added to the catalog

• DeepSeek: DeepSeek V4.1 Flash 1017 (deepseek/deepseek-v4.1-flash-1017) added to the catalog: 1,048,576 ctx, $0.15/M in / $0.6/M out
• Elorian: Glimpse (elorian/glimpse) added to the catalog: 262,144 ctx, $0.6/M in / $3/M out
• Qwen: Qwen3.7 Plus (batch) (qwen/qwen3.7-plus:batch) added to the catalog: 262,144 ctx, $0.23/M in / $0.92/M out
• Reflection: Beam 1.0 501B A23B (reflection/beam-1.0-501b-a23b) added to the catalog: 1,048,576 ctx, $1/M in / $3/M out
• XingChen: Xing4.0 29B A4B (free) (xingchen-agi/xing4.0-29b-a4b:free) added to the catalog: 262,144 ctx, $0/M in / $0/M out

model price changes

• ~deepseek/deepseek-flash-latest: prompt price $0.036/M → $0.15/M (+316.7%)
• ~deepseek/deepseek-flash-latest: completion price $0.684/M → $0.6/M (−12.3%)
• ~deepseek/deepseek-pro-latest: prompt price $0.25/M → $0.123/M (−50.7%)
• ~deepseek/deepseek-pro-latest: completion price $5/M → $0.559/M (−88.8%)
• ~deepseek/deepseek-v4-flash-latest: prompt price $0.013/M → $0.01/M (−26.0%)
• ~deepseek/deepseek-v4-flash-latest: completion price $1.28/M → $0.297/M (−76.8%)
• ~moonshotai/kimi-latest: prompt price $0.294/M → $0.27/M (−8.2%)
• ~moonshotai/kimi-latest: completion price $24/M → $14.2/M (−40.7%)
• ~z-ai/glm-flash-latest: prompt price $0.021/M → $0.029/M (+36.9%)
• ~z-ai/glm-flash-latest: completion price $0.723/M → $0.418/M (−42.2%)
• ~z-ai/glm-latest: prompt price $0.061/M → $0.069/M (+13.5%)
• ~z-ai/glm-latest: completion price $4.4/M → $3.94/M (−10.5%)
• deepseek/deepseek-chat: prompt price $0.257/M → $0.32/M (+24.3%)
• deepseek/deepseek-chat: completion price $1.03/M → $0.89/M (−13.5%)
• deepseek/deepseek-v3.2: prompt price $0.259/M → $0.28/M (+8.1%)
• deepseek/deepseek-v3.2: completion price $0.8/M → $0.42/M (−47.5%)
• deepseek/deepseek-v4-flash-0731: prompt price $0.013/M → $0.01/M (−26.0%)
• deepseek/deepseek-v4-flash-0731: completion price $1.28/M → $0.297/M (−76.8%)
• deepseek/deepseek-v4-pro: prompt price $0.955/M → $0.209/M (−78.1%)
• deepseek/deepseek-v4-pro: completion price $1.91/M → $0.418/M (−78.1%)
• deepseek/deepseek-v4-pro-0813: prompt price $1.32/M → $0.66/M (−50.0%)
• deepseek/deepseek-v4-pro-0813: completion price $3.96/M → $1.98/M (−50.0%)
• deepseek/deepseek-v4.1-flash: prompt price $0.036/M → $0.15/M (+316.7%)
• deepseek/deepseek-v4.1-flash: completion price $0.684/M → $0.6/M (−12.3%)
• deepseek/deepseek-v4.1-flash:batch: prompt price $0.112/M → $0.05/M (−55.4%)
• deepseek/deepseek-v4.1-flash:batch: completion price $0.336/M → $0.15/M (−55.4%)
• 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%)
• meta-llama/llama-4-scout: prompt price $0.18/M → $0.1/M (−44.4%)
• meta-llama/llama-4-scout: completion price $0.59/M → $0.3/M (−49.2%)
• nvidia/nemotron-3.5-super-vl: prompt price $0.15/M → $0.1/M (−33.3%)
• nvidia/nemotron-3.5-super-vl: completion price $0.5/M → $0.4/M (−20.0%)
• z-ai/glm-4.7: prompt price $0.6/M → $0.54/M (−10.0%)
• z-ai/glm-4.7: completion price $2.2/M → $1.98/M (−10.0%)
• z-ai/glm-5.2: prompt price $0.037/M → $0.62/M (+1575.7%)
• z-ai/glm-5.2: completion price $9/M → $2.42/M (−73.1%)
• z-ai/glm-5.3-flash: prompt price $0.021/M → $0.029/M (+36.9%)
• z-ai/glm-5.3-flash: completion price $0.723/M → $0.418/M (−42.2%)

provider price changes

• Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.021/M (−84.7%)
• Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.043/M (−84.7%)
• OpenInference: deepseek/deepseek-v4-flash prompt price $0.045/M → $0.022/M (−52.2%)
• OpenInference: deepseek/deepseek-v4-flash completion price $1.15/M → $0.139/M (−88.0%)
• Relace: deepseek/deepseek-v4-flash prompt price $0.05/M → $0.022/M (−57.0%)
• Relace: deepseek/deepseek-v4-flash completion price $1.28/M → $0.139/M (−89.2%)
• StreamLake: deepseek/deepseek-v4-flash prompt price $0.083/M → $0.028/M (−66.1%)
• StreamLake: deepseek/deepseek-v4-flash completion price $0.165/M → $0.056/M (−66.1%)
• Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.44/M → $0.06/M (−86.4%)
• Baidu: deepseek/deepseek-v4-flash-0731 completion price $1.32/M → $0.18/M (−86.4%)
• Inceptron: deepseek/deepseek-v4-flash-0731 completion price $0.599/M → $0.598/M (−0.3%)
• OpenInference: deepseek/deepseek-v4-flash-0731 prompt price $0.012/M → $0.01/M (−17.7%)
• OpenInference: deepseek/deepseek-v4-flash-0731 completion price $1.15/M → $0.297/M (−74.2%)
• Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.013/M → $0.01/M (−26.0%)
• Relace: deepseek/deepseek-v4-flash-0731 completion price $1.28/M → $0.297/M (−76.8%)
• Sail Research: deepseek/deepseek-v4-flash-0731 prompt price $0.019/M → $0.1/M (+426.3%)
• Sail Research: deepseek/deepseek-v4-flash-0731 completion price $0.42/M → $0.3/M (−28.6%)
• StreamLake: deepseek/deepseek-v4-flash-0731 prompt price $0.132/M → $0.088/M (−33.3%)
• StreamLake: deepseek/deepseek-v4-flash-0731 completion price $0.396/M → $0.264/M (−33.3%)
• Baidu: deepseek/deepseek-v4-pro prompt price $1.69/M → $0.177/M (−89.5%)
• Baidu: deepseek/deepseek-v4-pro completion price $3.38/M → $0.355/M (−89.5%)
• Relace: deepseek/deepseek-v4-pro prompt price $0.9/M → $0.167/M (−81.4%)
• Relace: deepseek/deepseek-v4-pro completion price $3/M → $0.461/M (−84.6%)
• StreamLake: deepseek/deepseek-v4-pro prompt price $0.955/M → $0.209/M (−78.1%)
• StreamLake: deepseek/deepseek-v4-pro completion price $1.91/M → $0.418/M (−78.1%)
• Baidu: deepseek/deepseek-v4-pro-0813 prompt price $1.32/M → $0.133/M (−89.9%)
• Baidu: deepseek/deepseek-v4-pro-0813 completion price $3.96/M → $0.4/M (−89.9%)
• DeepSeek: deepseek/deepseek-v4-pro-0813 prompt price $1.32/M → $0.66/M (−50.0%)
• DeepSeek: deepseek/deepseek-v4-pro-0813 completion price $3.96/M → $1.98/M (−50.0%)
• Relace: deepseek/deepseek-v4-pro-0813 prompt price $0.6/M → $0.123/M (−79.4%)
• Relace: deepseek/deepseek-v4-pro-0813 completion price $3.8/M → $0.559/M (−85.3%)
• Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.896/M → $0.448/M (−50.0%)
• Sail Research: deepseek/deepseek-v4-pro-0813 completion price $0.99/M → $1.16/M (+17.6%)
• Sail Research: deepseek/deepseek-v4-pro-0813 prompt price $0.896/M → $0.448/M (−50.0%)
• Sail Research: deepseek/deepseek-v4-pro-0813 completion price $0.99/M → $1.16/M (+17.6%)
• Wafer: deepseek/deepseek-v4-pro-0813 completion price $5/M → $2.5/M (−50.0%)
• AtlasCloud: deepseek/deepseek-v4.1-flash prompt price $0.3/M → $0.135/M (−55.0%)
• AtlasCloud: deepseek/deepseek-v4.1-flash completion price $1.2/M → $0.54/M (−55.0%)
• DeepSeek: deepseek/deepseek-v4.1-flash prompt price $0.3/M → $0.15/M (−50.0%)
• DeepSeek: deepseek/deepseek-v4.1-flash completion price $1.2/M → $0.6/M (−50.0%)
• DigitalOcean: deepseek/deepseek-v4.1-flash prompt price $0.225/M → $0.195/M (−13.3%)
• DigitalOcean: deepseek/deepseek-v4.1-flash completion price $0.9/M → $0.78/M (−13.3%)
• InferenceNet: deepseek/deepseek-v4.1-flash prompt price $0.1/M → $0.103/M (+3.0%)
• InferenceNet: deepseek/deepseek-v4.1-flash completion price $0.76/M → $0.715/M (−5.9%)
• Morph: deepseek/deepseek-v4.1-flash prompt price $0.04/M → $0.036/M (−10.0%)
• Morph: deepseek/deepseek-v4.1-flash completion price $0.7/M → $0.55/M (−21.4%)
• OpenInference: deepseek/deepseek-v4.1-flash prompt price $0.036/M → $0.019/M (−47.8%)
• OpenInference: deepseek/deepseek-v4.1-flash completion price $0.684/M → $0.625/M (−8.7%)
• Relace: deepseek/deepseek-v4.1-flash prompt price $0.2/M → $0.019/M (−90.6%)
• Relace: deepseek/deepseek-v4.1-flash completion price $0.6/M → $0.625/M (+4.1%)
• Makora: google/gemma-4-26b-a4b-it completion price $0.28/M → $0.18/M (−35.7%)
• NextBit: google/gemma-4-26b-a4b-it prompt price $0.09/M → $0.068/M (−25.0%)
• NextBit: google/gemma-4-26b-a4b-it completion price $0.3/M → $0.225/M (−25.0%)
• DeepInfra: inclusionai/ling-3.1-flash prompt price $0.21/M → $0.3/M (+42.9%)
• DeepInfra: inclusionai/ling-3.1-flash completion price $0.63/M → $0.9/M (+42.9%)
• Baidu: moonshotai/kimi-k2.6 prompt price $0.95/M → $0.432/M (−54.5%)
• Baidu: moonshotai/kimi-k2.6 completion price $4/M → $1.82/M (−54.5%)
• Inceptron: moonshotai/kimi-k2.6 prompt price $0.441/M → $0.432/M (−2.0%)
• Morph: moonshotai/kimi-k3 prompt price $1/M → $0.3/M (−70.0%)
• Parasail: moonshotai/kimi-k3 prompt price $2.6/M → $3/M (+15.4%)
• Parasail: moonshotai/kimi-k3 completion price $13/M → $15/M (+15.4%)
• Relace: moonshotai/kimi-k3 prompt price $0.35/M → $0.27/M (−22.9%)
• Relace: moonshotai/kimi-k3 completion price $14/M → $14.2/M (+1.6%)
• Sail Research: moonshotai/kimi-k3 prompt price $0.84/M → $0.504/M (−40.0%)
• Sail Research: moonshotai/kimi-k3 completion price $13.5/M → $8.1/M (−40.0%)
• Wafer: moonshotai/kimi-k3 prompt price $0.294/M → $0.28/M (−4.8%)
• Wafer: moonshotai/kimi-k3 prompt price $0.36/M → $0.5/M (+38.9%)
• CoreWeave: nvidia/nemotron-3.5-super-vl completion price $0.75/M → $0.5/M (−33.3%)
• DeepInfra: nvidia/nemotron-3.5-super-vl prompt price $0.2/M → $0.1/M (−50.0%)
• DeepInfra: nvidia/nemotron-3.5-super-vl completion price $1/M → $0.4/M (−60.0%)
• Wafer: qwen/qwen3.8-27b prompt price $0.2/M → $0.04/M (−80.0%)
• Wafer: qwen/qwen3.8-27b completion price $6/M → $2.3/M (−61.7%)
• Baidu: z-ai/glm-5.1 prompt price $1.4/M → $0.965/M (−31.1%)
• Baidu: z-ai/glm-5.1 completion price $4.4/M → $3.03/M (−31.1%)
• Baidu: z-ai/glm-5.2 prompt price $1.4/M → $0.189/M (−86.5%)
• Baidu: z-ai/glm-5.2 completion price $4.4/M → $0.594/M (−86.5%)
• Inceptron: z-ai/glm-5.2 completion price $2.52/M → $1.04/M (−58.8%)
• Relace: z-ai/glm-5.2 prompt price $0.035/M → $0.024/M (−31.3%)
• Relace: z-ai/glm-5.2 completion price $6/M → $2.37/M (−60.4%)
• StreamLake: z-ai/glm-5.2 prompt price $0.613/M → $0.556/M (−9.4%)
• StreamLake: z-ai/glm-5.2 completion price $1.93/M → $1.75/M (−9.4%)
• Wafer: z-ai/glm-5.2 prompt price $0.037/M → $0.034/M (−7.8%)
• Wafer: z-ai/glm-5.2 completion price $9/M → $7/M (−22.2%)
• Baidu: z-ai/glm-5.3 prompt price $1.4/M → $0.599/M (−57.2%)
• Baidu: z-ai/glm-5.3 completion price $4.4/M → $1.88/M (−57.2%)
• Inceptron: z-ai/glm-5.3 completion price $2.2/M → $1.5/M (−31.6%)
• InferenceNet: z-ai/glm-5.3 completion price $4.66/M → $4.38/M (−5.9%)
• Morph: z-ai/glm-5.3 prompt price $0.109/M → $0.08/M (−26.6%)
• Relace: z-ai/glm-5.3 prompt price $0.061/M → $0.069/M (+13.5%)
• Relace: z-ai/glm-5.3 completion price $4.4/M → $3.94/M (−10.5%)
• Sail Research: z-ai/glm-5.3 prompt price $0.15/M → $0.5/M (+233.3%)
• Sail Research: z-ai/glm-5.3 completion price $3.4/M → $1.5/M (−55.7%)
• Decart: z-ai/glm-5.3-flash prompt price $0.096/M → $0.129/M (+34.4%)
• Decart: z-ai/glm-5.3-flash completion price $0.32/M → $0.43/M (+34.4%)
• Inceptron: z-ai/glm-5.3-flash completion price $0.5/M → $0.863/M (+72.4%)
• InferenceNet: z-ai/glm-5.3-flash completion price $0.4/M → $0.388/M (−3.0%)
• Morph: z-ai/glm-5.3-flash prompt price $0.027/M → $0.073/M (+170.4%)
• Morph: z-ai/glm-5.3-flash completion price $1/M → $0.65/M (−35.0%)
• OpenInference: z-ai/glm-5.3-flash prompt price $0.019/M → $0.029/M (+52.1%)
• OpenInference: z-ai/glm-5.3-flash completion price $0.9/M → $0.418/M (−53.5%)
• Phala: z-ai/glm-5.3-flash prompt price $0.112/M → $0.128/M (+13.3%)
• Phala: z-ai/glm-5.3-flash completion price $0.375/M → $0.425/M (+13.3%)
• Relace: z-ai/glm-5.3-flash prompt price $0.021/M → $0.029/M (+36.9%)
• Relace: z-ai/glm-5.3-flash completion price $0.723/M → $0.418/M (−42.2%)
• Sail Research: z-ai/glm-5.3-flash prompt price $0.045/M → $0.078/M (+74.1%)
• Sail Research: z-ai/glm-5.3-flash completion price $0.6/M → $0.3/M (−50.0%)
• Sail Research: z-ai/glm-5.3-flash prompt price $0.045/M → $0.078/M (+74.1%)
• Sail Research: z-ai/glm-5.3-flash completion price $0.6/M → $0.3/M (−50.0%)
• StreamLake: z-ai/glm-5.3-flash prompt price $0.043/M → $0.075/M (+72.4%)
• StreamLake: z-ai/glm-5.3-flash completion price $0.145/M → $0.25/M (+72.4%)

provider context changes

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

providers added

• Nebius now serves deepseek/deepseek-v4.1-flash (fp8, 1,048,000 ctx, $0.3/M in / $1.2/M out)
• Sail Research now serves moonshotai/kimi-k3 (fp4, 1,048,576 ctx, $0.84/M in / $13.5/M out)
• Amazon Bedrock now serves qwen/qwen3-coder-30b-a3b-instruct (unknown, 262,144 ctx, $0.15/M in / $0.6/M out)
• CoreWeave now serves z-ai/glm-5.3 (fp8, 1,048,576 ctx, $1.2/M in / $4/M out)
• Nebius now serves z-ai/glm-5.3 (fp4, 1,024,000 ctx, $1.4/M in / $4.4/M out)
• Tenstorrent now serves z-ai/glm-5.3 (fp8, 1,044,480 ctx, $0.6/M in / $2.5/M out)

providers removed

• Makora no longer serves tencent/hy4-preview (was fp8)

openrouter catalog snapshots 2026-10-16 → 2026-10-17 · schema 1 · generated 2026-10-17T09:22:17.412Z