Mistral AI API pricing
Live prices for every model Mistral AI serves: its own per-1M-token prices, or per image, second or character, next to the cheapest price elsewhere.
Mistral AI serves 19 models with live API prices on SF·SIX, 19 models priced per 1M tokens. The cheapest is Ministral 3 3B 2512 at $0.10 per 1M input and $0.10 per 1M output tokens. The most used on OpenRouter is GLM 5.3 (942.62B tokens on 2026-10-16).
- Models with live prices
- 19
- Cheapest language model
- Ministral 3 3B 2512$0.10 / $0.10 per 1M tokens
- Most used on OpenRouter (2026-10-16)
- GLM 5.3942.62B tokens
- Newest model
- Mistral Large 42026-10-06
- Cheapest standard host for
- 15 models of 19
Mistral AI token prices (USD per 1M tokens)
| Model | Input / 1M | Output / 1M | Terms | Cheapest standard price anywhere | Context (tokens) | OpenRouter tokens / day |
|---|---|---|---|---|---|---|
| GLM 5.3 | $1.40 | $4.40 | Standard · nvfp4 | $0.50 / $1.51Sail Research (fp8) | 1,048,576 | 942.62B |
| GLM 5.2 | $1.40 | $4.40 | Zero data retention · nvfp4 | $0.189 / $0.594Baidu (fp8) | 1,048,576 | 140.87B |
| Mistral Nemo | $0.15 | $0.15 | EU region | $0.0166 / $0.0216IO.NET (fp16) | 131,072 | Not in named rows |
| Mistral Small 3.2 24B | $0.10 | $0.30 | EU region | $0.075 / $0.20DeepInfra (fp8) | 256,000 | Not in named rows |
| Mistral Large 4 | $0.68 | $2.09 | Standard | Mistral AIcheapest standard host | 1,048,576 | Not in named rows |
| Mistral Medium 3.5 | $1.50 | $7.50 | Standard | Mistral AIcheapest standard host | 262,144 | Not in named rows |
| Mistral Small 4 | $0.15 | $0.60 | Standard | Mistral AIcheapest standard host | 262,144 | Not in named rows |
| Devstral 2 2512 | $0.40 | $2.00 | EU region | Mistral AIcheapest standard host | 262,144 | Not in named rows |
| Ministral 3 14B 2512 | $0.20 | $0.20 | Standard | Mistral AIcheapest standard host | 262,144 | Not in named rows |
| Ministral 3 8B 2512 | $0.15 | $0.15 | Standard | Mistral AIcheapest standard host | 262,144 | Not in named rows |
| Ministral 3 3B 2512 | $0.10 | $0.10 | Standard | Mistral AIcheapest standard host | 131,072 | Not in named rows |
| Mistral Large 3 2512 | $0.50 | $1.50 | Zero data retention | Mistral AIcheapest standard host | 262,144 | Not in named rows |
| Voxtral Small 24B 2507 | $0.10 | $0.30 | Standard | Mistral AIcheapest standard host | 32,768 | Not in named rows |
| Mistral Medium 3.1 | $0.40 | $2.00 | Standard | Mistral AIcheapest standard host | 131,072 | Not in named rows |
| Mistral Medium 3 | $0.40 | $2.00 | Standard | Mistral AIcheapest standard host | 131,072 | Not in named rows |
| Saba | $0.20 | $0.60 | Standard | Mistral AIcheapest standard host | 32,768 | Not in named rows |
| Mistral Large 2407 | $2.00 | $6.00 | Standard | Mistral AIcheapest standard host | 131,072 | Not in named rows |
| Mixtral 8x22B Instruct | $2.00 | $6.00 | Standard | Mistral AIcheapest standard host | 65,536 | Not in named rows |
| Mistral Large | $2.00 | $6.00 | Standard | Mistral AIcheapest standard host | 128,000 | Not in named rows |
Mistral AI’s own endpoint for each model (standard tier and default region first), next to the cheapest standard price from any provider. Most widely served first.
Method
Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.