Magistral Medium is Mistral AI's language model with a 128K context window and up to 64K output tokens, available from 2 providers, starting at $2.00 / 1M input and $5.00 / 1M output. Mistral AI's mid-tier reasoning model with transparent chain-of-thought capabilities, excelling at multilingual complex problem-solving.
| Specifications | |
|---|---|
mistral-magistral-medium | |
| Language | |
| Deprecated | |
| 128K tokens | |
| 64K tokens | |
| ImageText | |
| Text | |
| default | |
| · 1 year ago | |
| Benchmarks | |
|---|---|
| Intelligence Index | #236 |
| Coding Index | #141 |
| Math Index | #79 |
| MMLU-Pro | #95 |
| GPQA | #222 |
| HLE | #217 |
| LiveCodeBench | #52 |
| AIME | #47 |
| IFBench | #237 |
| Time to First Token | #206 |
| SciCode | #163 |
| MATH-500 | #68 |
| AIME 2025 | #79 |
| LCR | #206 |
| TerminalBench Hard | #202 |
| TAU2 | #187 |
| Output TPS | #441 |
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill✓
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $2.00 | $5.00 | |
| $2.00 | $5.00 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Magistral 1.2 Medium | — | 40K | $2.00 | $5.00 | Deprecated |
| Magistral Medium | 128K | $2.00 | $5.00 | Current |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Magistral 1.2 Small | Small | — | 40K | $0.500 | $1.50 |
| Magistral Small | Small | 128K | $0.500 | $1.50 |