← variables.md

2026-09-05

84 change(s) in the model market

added to the catalog

• inclusionAI: Ling 3.0 Flash Sante (free) (inclusionai/ling-3.0-flash-sante:free) added to the catalog: 262,144 ctx, $0/M in / $0/M out
• OpenAI: GPT-6 Astra (openai/gpt-6-astra) added to the catalog: 1,050,000 ctx, $10/M in / $50/M out
• OpenAI: GPT-6 Astra Pro (openai/gpt-6-astra-pro) added to the catalog: 1,050,000 ctx, $10/M in / $50/M out
• OpenAI: GPT-6 Astra Pro (batch) (openai/gpt-6-astra-pro:batch) added to the catalog: 1,050,000 ctx, $5/M in / $25/M out
• OpenAI: GPT-6 Astra (batch) (openai/gpt-6-astra:batch) added to the catalog: 1,050,000 ctx, $5/M in / $25/M out
• Qwen: Qwen3.8 Max (0902) (qwen/qwen3.8-max-0902) added to the catalog: 1,000,000 ctx, $2/M in / $6/M out

removed from the catalog

• IBM: Granite 4.1 8B (ibm-granite/granite-4.1-8b) removed from the catalog
• Qwen: Qwen3.8 Max (qwen/qwen3.8-max) removed from the catalog

model price changes

• ~deepseek/deepseek-v4-flash-latest: prompt price $0.05/M → $0.05/M (−0.0%)
• ~deepseek/deepseek-v4-flash-latest: completion price $0.16/M → $0.1/M (−37.5%)
• ~moonshotai/kimi-latest: prompt price $2.5/M → $2.55/M (+2.0%)
• ~moonshotai/kimi-latest: completion price $14/M → $12.8/M (−8.9%)
• deepseek/deepseek-v4-flash: prompt price $0.089/M → $0.085/M (−3.8%)
• deepseek/deepseek-v4-flash: completion price $0.177/M → $0.171/M (−3.8%)
• deepseek/deepseek-v4-flash-vision-exp: prompt price $0.44/M → $0.22/M (−50.0%)
• deepseek/deepseek-v4-flash-vision-exp: completion price $1.32/M → $0.66/M (−50.0%)
• deepseek/deepseek-v4-pro: prompt price $1.04/M → $0.921/M (−11.7%)
• deepseek/deepseek-v4-pro: completion price $2.08/M → $1.84/M (−11.7%)
• deepseek/deepseek-v4-pro-0813: prompt price $1.12/M → $1.12/M (+0.5%)
• deepseek/deepseek-v4-pro-0813: completion price $3.35/M → $3.36/M (+0.5%)
• qwen/qwen3-235b-a22b-2507: prompt price $0.087/M → $0.09/M (+2.9%)
• qwen/qwen3-235b-a22b-2507: completion price $0.35/M → $0.55/M (+57.1%)
• qwen/qwen3.5-35b-a3b: prompt price $0.25/M → $0.08/M (−68.0%)
• qwen/qwen3.5-35b-a3b: completion price $1.25/M → $0.75/M (−40.0%)
• qwen/qwen3.6-27b: prompt price $0.6/M → $0.3/M (−50.0%)
• qwen/qwen3.6-27b: completion price $3.6/M → $2/M (−44.4%)

quantization changes

• DeepInfra: z-ai/glm-5.3-flash quantization fp8 → fp4

provider price changes

• Baidu: deepseek/deepseek-v4-flash prompt price $0.14/M → $0.085/M (−39.0%)
• Baidu: deepseek/deepseek-v4-flash completion price $0.28/M → $0.171/M (−39.0%)
• StreamLake: deepseek/deepseek-v4-flash prompt price $0.089/M → $0.085/M (−3.8%)
• StreamLake: deepseek/deepseek-v4-flash completion price $0.177/M → $0.171/M (−3.8%)
• Baidu: deepseek/deepseek-v4-flash-0731 prompt price $0.14/M → $0.05/M (−64.3%)
• Baidu: deepseek/deepseek-v4-flash-0731 completion price $0.28/M → $0.1/M (−64.3%)
• DeepSeek: deepseek/deepseek-v4-flash-0731 prompt price $0.44/M → $0.22/M (−50.0%)
• DeepSeek: deepseek/deepseek-v4-flash-0731 completion price $1.32/M → $0.66/M (−50.0%)
• 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%)
• DeepSeek: deepseek/deepseek-v4-flash-vision-exp prompt price $0.44/M → $0.22/M (−50.0%)
• DeepSeek: deepseek/deepseek-v4-flash-vision-exp completion price $1.32/M → $0.66/M (−50.0%)
• Baidu: deepseek/deepseek-v4-pro prompt price $1.69/M → $0.919/M (−45.6%)
• Baidu: deepseek/deepseek-v4-pro completion price $3.38/M → $1.84/M (−45.6%)
• NextBit: deepseek/deepseek-v4-pro prompt price $1.72/M → $1.74/M (+1.2%)
• NextBit: deepseek/deepseek-v4-pro completion price $3.45/M → $3.48/M (+0.9%)
• StreamLake: deepseek/deepseek-v4-pro prompt price $1.04/M → $0.921/M (−11.7%)
• StreamLake: deepseek/deepseek-v4-pro completion price $2.08/M → $1.84/M (−11.7%)
• 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%)
• StreamLake: deepseek/deepseek-v4-pro-0813 prompt price $1.12/M → $1.12/M (+0.5%)
• StreamLake: deepseek/deepseek-v4-pro-0813 completion price $3.35/M → $3.36/M (+0.5%)
• Baidu: moonshotai/kimi-k2.6 prompt price $0.95/M → $0.548/M (−42.3%)
• Baidu: moonshotai/kimi-k2.6 completion price $4/M → $2.31/M (−42.3%)
• Decart: moonshotai/kimi-k2.6 prompt price $0.568/M → $0.537/M (−5.5%)
• Decart: moonshotai/kimi-k2.6 completion price $3.33/M → $2.26/M (−32.1%)
• Inceptron: moonshotai/kimi-k2.6 prompt price $0.52/M → $0.56/M (+7.7%)
• Morph: moonshotai/kimi-k3 prompt price $2.5/M → $2.6/M (+4.0%)
• Mancer 2: openai/gpt-oss-120b prompt price $0.055/M → $0.05/M (−9.1%)
• Parasail: qwen/qwen3.8-27b prompt price $0.28/M → $0.24/M (−14.3%)
• Phala: qwen/qwen3.8-27b prompt price $0.4/M → $0.3/M (−25.0%)
• Baidu: z-ai/glm-5.1 prompt price $1.4/M → $0.909/M (−35.1%)
• Baidu: z-ai/glm-5.1 completion price $4.4/M → $2.86/M (−35.1%)
• Baidu: z-ai/glm-5.2 prompt price $1.4/M → $0.357/M (−74.5%)
• Baidu: z-ai/glm-5.2 completion price $4.4/M → $1.12/M (−74.5%)
• StreamLake: z-ai/glm-5.2 prompt price $0.56/M → $0.343/M (−38.8%)
• StreamLake: z-ai/glm-5.2 completion price $1.76/M → $1.08/M (−38.7%)
• Decart: z-ai/glm-5.3 prompt price $1.18/M → $1.19/M (+1.2%)
• Decart: z-ai/glm-5.3 completion price $3.7/M → $3.74/M (+1.2%)
• Io Net: z-ai/glm-5.3 prompt price $1.19/M → $1.25/M (+5.3%)
• Io Net: z-ai/glm-5.3 completion price $4.18/M → $4.4/M (+5.3%)
• Morph: z-ai/glm-5.3-flash prompt price $0.13/M → $0.097/M (−25.4%)
• Morph: z-ai/glm-5.3-flash completion price $0.45/M → $0.339/M (−24.6%)

provider context changes

• Sail Research: moonshotai/kimi-k3 context length 974,842 → 1,048,576

providers added

• AtlasCloud now serves deepseek/deepseek-v4-flash-vision-exp (fp8, 1,048,576 ctx, $0.44/M in / $1.32/M out)
• Baidu now serves deepseek/deepseek-v4-pro-0813 (fp8, 1,048,576 ctx, $1.12/M in / $3.36/M out)
• Together now serves minimax/minimax-m3 (unknown, 524,288 ctx, $0.3/M in / $1.2/M out)
• DeepInfra now serves openai/gpt-oss-120b (fp8, 131,072 ctx, $0.2/M in / $0.95/M out)
• AtlasCloud now serves z-ai/glm-5.3 (fp8, 262,144 ctx, $1.4/M in / $4.4/M out)
• CoreWeave now serves z-ai/glm-5.3-flash (fp8, 1,048,576 ctx, $0.15/M in / $0.5/M out)

providers removed

• CoreWeave no longer serves deepseek/deepseek-v4-flash (was fp8)
• CoreWeave no longer serves deepseek/deepseek-v4-pro (was fp8)
• CoreWeave no longer serves meta-llama/llama-3.1-70b-instruct (was bf16)
• CoreWeave no longer serves qwen/qwen3-30b-a3b-instruct-2507 (was bf16)
• CoreWeave no longer serves qwen/qwen3.5-35b-a3b (was fp8)
• CoreWeave no longer serves qwen/qwen3.6-27b (was fp8)
• Sail Research no longer serves z-ai/glm-5.2 (was fp8)

openrouter catalog snapshots 2026-09-04 → 2026-09-05 · schema 1 · generated 2026-09-05T09:05:57.940Z