Mistral API Pricing
Mistral models from Mistral AI. French AI company focused on efficient and powerful language models. Requesty routes to 14 Mistral AI models starting at $0.11 per 1M input tokens with context windows up to 1M tokens. One API key and an OpenAI-compatible SDK. Provider rates plus 5% on pay as you go, or 0% with your own keys.
Flagship model
mistral-large-4Intelligence Index
26.1
All Mistral AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | Coding |
|---|---|---|---|---|---|---|
mistral-large-4 50% off | 524K | — | $1.36$0.68 | $4.18$2.09 | 👁🧠🔧⚡ | N/A |
| 1M | 128K | $1.54 | $4.84 | 🧠🔧⚡ | N/A | |
| 1M | 128K | $1.54 | $4.84 | 🧠🔧⚡ | N/A | |
| 256K | — | $0.44 | $2.20 | 🧠🔧 | N/A | |
| 262K | 33K | Free | Free | 🧠🔧 | N/A | |
| 262K | — | $1.65 | $8.25 | 👁🧠🔧 | N/A | |
| 131K | — | $0.44 | $2.20 | 🧠🔧 | N/A | |
| 256K | — | $0.17 | $0.66 | 👁🧠🔧 | N/A | |
| 256K | — | $0.17 | $0.66 | 👁🧠🔧 | N/A | |
| 131K | — | $0.55 | $1.65 | 🔧 | N/A | |
| 131K | — | $0.33 | $0.99 | 🔧 | N/A | |
| 131K | — | $0.11 | $0.33 | 🧠🔧 | N/A | |
| 33K | — | $0.11 | $0.33 | 🧠🔧 | N/A | |
| 33K | — | $0.28 | $0.28 | 🔧 | N/A |
About Mistral AI on Requesty
How many Mistral AI models are available through Requesty?
Requesty routes to 14 Mistral AI models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Mistral AI model?
The cheapest Mistral AI model starts at $0.11 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Mistral AI pricing?
No. Requesty passes through exactly what Mistral AI charges. You pay the same per-token rates as going direct, plus you get smart routing, caching, analytics, and one unified API for 600+ models.
Is my data used to train Mistral AI models?
Mistral AI's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Mistral AI models hosted?
Mistral AI models are hosted in 🇪🇺 EU. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI: filter by region on the Mistral AI rows in the models explorer.