Files
agent-cost-estimator/agent_cost_estimator/pricing.json
T

212 lines
9.0 KiB
JSON

{
"harness_credit_pools": {
"vibe": "mistral-vibe",
"hermes": "mistral-api"
},
"billing_url_pools": {
"api.mistral.ai": "mistral-api"
},
"providers": {
"default": {
"currency": "USD",
"models": {
"default": {
"input_price": 1.5,
"cached_input_price": 0.15,
"output_price": 7.5,
"note": "Global fallback rates for unknown providers/models",
"source": "agent-cost-estimator default",
"date": "2026-11-18"
}
}
},
"deepseek": {
"currency": "USD",
"provider_alias": "mistral",
"note": "DeepSeek models as hosted through Mistral's marketplace (Mistral API key, no separate DeepSeek account). Section is named deepseek because that is the provider/model prefix in harness logs; provider_alias makes the cost tracker display them as mistral:<model>.",
"models": {
"default": {
"input_price": 0.3,
"cached_input_price": 0.007,
"output_price": 1.2,
"note": "DeepSeek default rates - matches V4.1 Flash 1017 (Mistral hosted)",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"deepseek-v4-1-flash-1017": {
"input_price": 0.3,
"cached_input_price": 0.007,
"output_price": 1.2,
"note": "DeepSeek V4.1 Flash 1017 (Mistral-hosted model id deepseek-v4-1-flash-1017; 552B MoE, 1M context, MIT weights). DeepSeek's direct API serves the same release as deepseek-flash at $0.30 in / $0.006 cached / $1.20 out peak, half off-peak - see https://benchlm.ai/deepseek/api-pricing",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"deepseek-flash": {
"input_price": 0.3,
"cached_input_price": 0.007,
"output_price": 1.2,
"note": "deepseek-flash alias (DeepSeek direct API name for the V4.1-Flash-1017 release) - same rates as the Mistral-hosted deepseek-v4-1-flash-1017",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
}
}
},
"mistral": {
"currency": "USD",
"models": {
"default": {
"input_price": 1.5,
"cached_input_price": 0.15,
"output_price": 7.5,
"note": "Mistral default rates - matches Mistral Medium 3.5 (off the official pricing table since ~2026-11-17; unchanged rates confirmed by benchlm.ai and optimtoken.optimnow.io)",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-medium": {
"input_price": 1.5,
"cached_input_price": 0.15,
"output_price": 7.5,
"note": "Mistral Medium 3.5 - flagship reasoning model; no longer listed on the official pricing table (gone by 2026-11-17) - unchanged rates confirmed by benchlm.ai and optimtoken.optimnow.io",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-medium-3.5": {
"input_price": 1.5,
"cached_input_price": 0.15,
"output_price": 7.5,
"note": "Vibe's built-in hosted default model; no longer listed on the official pricing table (gone by 2026-11-17) - unchanged rates confirmed by benchlm.ai and optimtoken.optimnow.io",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-small": {
"input_price": 0.15,
"cached_input_price": 0.015,
"output_price": 0.6,
"note": "Mistral Small 4 model rates",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-small-4": {
"input_price": 0.15,
"cached_input_price": 0.015,
"output_price": 0.6,
"note": "Mistral Small 4 - efficient reasoning model",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-small-latest": {
"input_price": 0.15,
"cached_input_price": 0.015,
"output_price": 0.6,
"note": "Mistral Small -latest alias served by the API (same rates as Mistral Small 4)",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-large": {
"input_price": 0.7,
"cached_input_price": 0.07,
"output_price": 2.1,
"note": "Mistral Large 4 rates (alias of mistral-large-4); promotional rates still listed 2026-11-18",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-large-3": {
"input_price": 0.5,
"cached_input_price": 0.05,
"output_price": 1.5,
"note": "Mistral Large 3 - previous generation large model (no longer listed on the official pricing page)",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-large-4": {
"input_price": 0.7,
"cached_input_price": 0.07,
"output_price": 2.1,
"note": "Mistral Large 4 - natively multimodal MoE (1.05T params); promotional rates still listed 2026-11-18 (regular: $1.36 in / $0.14 cached / $4.18 out)",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"mistral-vibe-cli-latest": {
"input_price": 1.5,
"cached_input_price": 0.15,
"output_price": 7.5,
"note": "Mistral Vibe CLI latest model (default hosted model - Mistral Medium 3.5; off the official pricing table since ~2026-11-17, unchanged rates confirmed by benchlm.ai)",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"ministral-3-3b": {
"input_price": 0.1,
"cached_input_price": 0.01,
"output_price": 0.1,
"note": "Ministral 3 3B - compact edge model with symmetric pricing",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"ministral-3-8b": {
"input_price": 0.15,
"cached_input_price": 0.015,
"output_price": 0.15,
"note": "Ministral 3 8B - edge model with symmetric pricing",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"ministral-3-14b": {
"input_price": 0.2,
"cached_input_price": 0.02,
"output_price": 0.2,
"note": "Ministral 3 14B - edge model with symmetric pricing",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"codestral": {
"input_price": 0.3,
"cached_input_price": 0.03,
"output_price": 0.9,
"note": "Codestral - specialized code generation model",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
}
}
},
"zai": {
"currency": "USD",
"provider_alias": "mistral",
"note": "Z.ai GLM models as hosted through Mistral's marketplace (Mistral API key, no separate Z.ai account). Section is named zai because that is the provider/model prefix in harness logs (zai-glm-5-3); provider_alias makes the cost tracker display them as mistral:zai-glm-5-3. Optional per-model model_alias overrides the model part of the display the same way.",
"models": {
"default": {
"input_price": 1.4,
"cached_input_price": 0.14,
"output_price": 4.4,
"note": "Z.ai default rates - matches GLM 5.3 (Mistral hosted)",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"zai-glm-5-3": {
"input_price": 1.4,
"cached_input_price": 0.14,
"output_price": 4.4,
"note": "GLM 5.3 (Mistral hosted; billed via Mistral's marketplace as zai-glm-5-3). Z.ai direct API lists cached input at $0.26/1M - see https://docs.z.ai/guides/overview/pricing",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"zai-glm-5.3-flash": {
"input_price": 0.15,
"cached_input_price": 0.03,
"output_price": 0.5,
"note": "GLM 5.3 Flash (Mistral hosted) - efficient MoE model (320B total, 18B active); same rates on Z.ai direct",
"source": "https://docs.mistral.ai/inference/pricing",
"date": "2026-11-18"
},
"zai-glm-5.3-flashx": {
"input_price": 0.37,
"cached_input_price": 0.075,
"output_price": 1.25,
"note": "GLM 5.3 FlashX - advanced variant; not listed on Mistral's pricing page, rates are Z.ai direct (would differ if Mistral hosts it later); re-verified 2026-11-18 on docs.z.ai",
"source": "https://docs.z.ai/guides/overview/pricing",
"date": "2026-11-18"
}
}
}
}
}