← variables.md

2026-10-11

99 change(s) in the model market

model price changes

• ~deepseek/deepseek-flash-latest: prompt price $0/M → $0.03/M (+29900.0%)
• ~deepseek/deepseek-flash-latest: completion price $0.6/M → $0.99/M (+65.0%)
• ~deepseek/deepseek-pro-latest: prompt price $0.3/M → $0.219/M (−27.0%)
• ~deepseek/deepseek-pro-latest: completion price $5/M → $0.657/M (−86.9%)
• ~deepseek/deepseek-v4-flash-latest: prompt price $0.01/M → $0.018/M (+81.8%)
• ~deepseek/deepseek-v4-flash-latest: completion price $1.28/M → $0.64/M (−50.0%)
• ~moonshotai/kimi-latest: prompt price $0.33/M → $0.75/M (+127.3%)
• ~moonshotai/kimi-latest: completion price $14.9/M → $14.9/M (+0.1%)
• ~z-ai/glm-latest: prompt price $0.039/M → $0.07/M (+79.5%)
• deepseek/deepseek-v4-flash: prompt price $0.018/M → $0.03/M (+64.8%)
• deepseek/deepseek-v4-flash-0731: prompt price $0.01/M → $0.018/M (+81.8%)
• deepseek/deepseek-v4-flash-0731: completion price $1.28/M → $0.64/M (−50.0%)
• deepseek/deepseek-v4-pro: prompt price $0.948/M → $0.209/M (−78.0%)
• deepseek/deepseek-v4-pro: completion price $1.9/M → $0.418/M (−78.0%)
• moonshotai/kimi-k2.6: prompt price $0.465/M → $0.65/M (+39.8%)
• moonshotai/kimi-k2.6: completion price $2.45/M → $3.41/M (+39.2%)
• moonshotai/kimi-k3: prompt price $0.64/M → $0.8/M (+25.0%)
• moonshotai/kimi-k3: completion price $13.5/M → $10/M (−25.9%)
• nvidia/nemotron-3-ultra-550b-a55b: prompt price $0.5/M → $0.6/M (+20.0%)
• nvidia/nemotron-3-ultra-550b-a55b: completion price $2.2/M → $2.4/M (+9.1%)
• 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 $0.425/M → $0.04/M (−90.6%)
• qwen/qwen3.8-27b: completion price $2.55/M → $2.3/M (−9.8%)
• z-ai/glm-5.3: prompt price $0.039/M → $0.07/M (+79.5%)

provider price changes

• Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.091/M (−35.1%)
• Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.182/M (−35.1%)
• OpenInference: deepseek/deepseek-v4-flash prompt price $0.019/M → $0.033/M (+71.4%)
• Relace: deepseek/deepseek-v4-flash prompt price $0.018/M → $0.03/M (+64.8%)
• Wafer: deepseek/deepseek-v4-flash prompt price $0.075/M → $0.195/M (+160.0%)
• Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.44/M → $0.13/M (−70.5%)
• Baidu: deepseek/deepseek-v4-flash-0731 completion price $1.32/M → $0.389/M (−70.5%)
• Inceptron: deepseek/deepseek-v4-flash-0731 prompt price $0.097/M → $0.184/M (+89.4%)
• OpenInference: deepseek/deepseek-v4-flash-0731 prompt price $0.01/M → $0.02/M (+89.5%)
• Relace: deepseek/deepseek-v4-flash-0731 prompt price $0.01/M → $0.018/M (+81.8%)
• Relace: deepseek/deepseek-v4-flash-0731 completion price $1.28/M → $0.64/M (−50.0%)
• Baidu: deepseek/deepseek-v4-pro prompt price $1.69/M → $0.171/M (−89.9%)
• Baidu: deepseek/deepseek-v4-pro completion price $3.38/M → $0.341/M (−89.9%)
• Reka: deepseek/deepseek-v4-pro prompt price $1.2/M → $1.05/M (−12.5%)
• Reka: deepseek/deepseek-v4-pro completion price $12/M → $10.5/M (−12.5%)
• Relace: deepseek/deepseek-v4-pro prompt price $0.3/M → $0.45/M (+50.0%)
• Relace: deepseek/deepseek-v4-pro completion price $4.2/M → $3/M (−28.6%)
• StreamLake: deepseek/deepseek-v4-pro prompt price $0.948/M → $0.209/M (−78.0%)
• StreamLake: deepseek/deepseek-v4-pro completion price $1.9/M → $0.418/M (−78.0%)
• Baidu: deepseek/deepseek-v4-pro-0813 prompt price $1.32/M → $0.219/M (−83.4%)
• Baidu: deepseek/deepseek-v4-pro-0813 completion price $3.96/M → $0.657/M (−83.4%)
• Baidu: deepseek/deepseek-v4.1-flash prompt price $0.3/M → $0.035/M (−88.4%)
• Baidu: deepseek/deepseek-v4.1-flash completion price $1.2/M → $0.139/M (−88.4%)
• InferenceNet: deepseek/deepseek-v4.1-flash prompt price $0.07/M → $0.077/M (+10.0%)
• InferenceNet: deepseek/deepseek-v4.1-flash completion price $0.6/M → $0.4/M (−33.3%)
• Ionstream: deepseek/deepseek-v4.1-flash completion price $1.1/M → $0.75/M (−31.8%)
• Morph: deepseek/deepseek-v4.1-flash prompt price $0.029/M → $0.042/M (+44.8%)
• Morph: deepseek/deepseek-v4.1-flash completion price $1/M → $0.6/M (−40.0%)
• OpenInference: deepseek/deepseek-v4.1-flash prompt price $0/M → $0.055/M (+49900.0%)
• Relace: deepseek/deepseek-v4.1-flash prompt price $0/M → $0.05/M (+49900.0%)
• Wafer: deepseek/deepseek-v4.1-flash prompt price $0.05/M → $0.035/M (−30.0%)
• Wafer: deepseek/deepseek-v4.1-flash completion price $1.6/M → $1.4/M (−12.5%)
• Baidu: moonshotai/kimi-k2.6 prompt price $0.95/M → $0.434/M (−54.3%)
• Baidu: moonshotai/kimi-k2.6 completion price $4/M → $1.83/M (−54.3%)
• Inceptron: moonshotai/kimi-k2.6 prompt price $0.465/M → $0.434/M (−6.6%)
• Decart: moonshotai/kimi-k3 prompt price $1.98/M → $2.55/M (+28.8%)
• Decart: moonshotai/kimi-k3 completion price $9.9/M → $12.8/M (+28.8%)
• InferenceNet: moonshotai/kimi-k3 prompt price $0.64/M → $0.8/M (+25.0%)
• InferenceNet: moonshotai/kimi-k3 completion price $13.5/M → $10/M (−25.9%)
• Morph: moonshotai/kimi-k3 prompt price $0.339/M → $0.75/M (+121.2%)
• Wafer: moonshotai/kimi-k3 prompt price $0.33/M → $1.95/M (+490.9%)
• Wafer: moonshotai/kimi-k3 completion price $14.9/M → $15/M (+0.7%)
• Wafer: nvidia/nemotron-3.5-lightning prompt price $0.045/M → $0.035/M (−22.2%)
• DekaLLM: qwen/qwen3.8-27b prompt price $0.049/M → $0.04/M (−18.4%)
• DekaLLM: qwen/qwen3.8-27b completion price $3/M → $2.5/M (−16.7%)
• Reka: qwen/qwen3.8-27b prompt price $0.14/M → $0.05/M (−64.3%)
• Reka: qwen/qwen3.8-27b completion price $1.4/M → $3/M (+114.3%)
• Wafer: qwen/qwen3.8-27b prompt price $0.03/M → $0.04/M (+33.3%)
• Baidu: z-ai/glm-5.2 prompt price $1.4/M → $1.4/M (−0.1%)
• Baidu: z-ai/glm-5.2 completion price $4.4/M → $4.4/M (−0.1%)
• Baidu: z-ai/glm-5.2 prompt price $2.25/M → $1.4/M (−37.8%)
• Baidu: z-ai/glm-5.2 completion price $7.88/M → $4.9/M (−37.8%)
• Decart: z-ai/glm-5.2 prompt price $0.273/M → $0.26/M (−4.8%)
• Decart: z-ai/glm-5.2 completion price $1.68/M → $1.6/M (−4.8%)
• Inceptron: z-ai/glm-5.2 completion price $5.46/M → $1.95/M (−64.3%)
• InferenceNet: z-ai/glm-5.2 prompt price $0.18/M → $0.15/M (−16.7%)
• InferenceNet: z-ai/glm-5.2 completion price $4.4/M → $0.6/M (−86.4%)
• Morph: z-ai/glm-5.2 prompt price $0.18/M → $0.4/M (+122.2%)
• Wafer: z-ai/glm-5.2 completion price $10/M → $8/M (−20.0%)
• Baidu: z-ai/glm-5.3 prompt price $1.4/M → $0.35/M (−75.0%)
• Baidu: z-ai/glm-5.3 completion price $4.4/M → $1.1/M (−75.0%)
• Inceptron: z-ai/glm-5.3 completion price $2.2/M → $1.1/M (−50.0%)
• Io Net: z-ai/glm-5.3 prompt price $0.75/M → $0.65/M (−13.3%)
• Io Net: z-ai/glm-5.3 completion price $3.4/M → $3.1/M (−8.8%)
• Morph: z-ai/glm-5.3 prompt price $0.693/M → $0.25/M (−63.9%)
• Morph: z-ai/glm-5.3 completion price $6/M → $5/M (−16.7%)
• Wafer: z-ai/glm-5.3 prompt price $0.039/M → $0.07/M (+79.5%)
• InferenceNet: z-ai/glm-5.3-flash completion price $0.5/M → $0.05/M (−90.0%)
• Morph: z-ai/glm-5.3-flash prompt price $0.117/M → $0.06/M (−48.7%)
• Wafer: z-ai/glm-5.3-flash prompt price $0.07/M → $0.09/M (+28.6%)

providers added

• Tenstorrent now serves qwen/qwen3.8-27b (fp4, 262,144 ctx, $0.04/M in / $1.35/M out)

providers removed

• Phala no longer serves meta/muse-glimmer-30b (was unknown)
• Phala no longer serves nvidia/nemotron-3.5-lightning (was unknown)
• Nebius no longer serves z-ai/glm-5.3 (was fp4)

openrouter catalog snapshots 2026-10-10 → 2026-10-11 · schema 1 · generated 2026-10-11T11:24:41.890Z