Mistral: Devstral Mediummistralai
Bottom Line
Mistral: Devstral Medium: $0.40/1M input, $2.00/1M output, 131K context, CPS grade B. Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...
API Pricing (per 1M tokens)
| Input | $0.40 |
| Output | $2.00 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.80 |
Specs & Performance
| Context Length | 131K |
| Max Output | — |
| Intelligence | 9 |
| Coding | 16 |
| Math | 5 |
| Speed | — |
| TTFT | — |
| CPS Grade | B |
| Input / Output Modalities | text, file → text |
More from mistralai
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Mistral: Devstral Medium API cost?
Mistral: Devstral Medium costs $0.40/1M input tokens and $2.00/1M output tokens. Blended cost at a 3:1 ratio is about $0.80/1M tokens.
What is the context window of Mistral: Devstral Medium?
Mistral: Devstral Medium supports a 131K token context window.
Is Mistral: Devstral Medium worth it?
Mistral: Devstral Medium has a CPS grade of B (score 56), intelligence index 9, coding index 16. Use the compare page to benchmark against rivals.