Devstral Medium
DeprecatedDevstral Medium is Mistral AI's language model with a 256K context window, starting at $0.4 / 1M input and $2.00 / 1M output. Mistral AI's mid-tier agentic coding model developed jointly with All Hands AI, balancing code generation performance and efficiency.
| Specifications | |
|---|---|
mistral-devstral-medium | |
| Language | |
| Deprecated | |
| Mistral AI | |
| 256K tokens | |
| Text | |
| Text | |
| · 1 year ago | |
| · 1 year ago | |
| Benchmarks | |
|---|---|
| Intelligence Index | #340 |
| Math Index | #253 |
| MMLU-Pro | #220 |
| GPQA | #405 |
| HLE | #504 |
| LiveCodeBench | #207 |
| AIME | #143 |
| IFBench | #367 |
| Time to First Token | #223 |
| SciCode | #333 |
| MATH-500 | #137 |
| AIME 2025 | #253 |
| LCR | #315 |
| TerminalBench Hard | #227 |
| TAU2 | #339 |
| Output TPS | #463 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.4 | $2.00 | $0.04 | |
Cost Calculator
US Dollar ($)
Preset:
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Devstral 2 123B | — | 256K | $0.400 | $2.00 | |
| Devstral 2 | — | 256K | — | — | |
| Devstral Small 2 | Small | 256K | — | — | |
| Devstral 2 123B Instruct | — | — | 200K | — | — |
| Devstral | — | 262K | $0.400 | $2.00 |