AI model comparison
Mistral Medium 3.1 vs Mistral Medium 3
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Mistral
Mistral Medium 3.1
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.
- Input / 1M
- $0.40
- Output / 1M
- $2
- Context
- 131K
Mistral
Mistral Medium 3
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.
- Input / 1M
- $0.40
- Output / 1M
- $2
- Context
- 131K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Tie
Same price for a typical chat
Higher intelligence score
Mistral Medium 3.1
9.2 vs 9 on Artificial Analysis
Larger context window
Tie
131K vs 131K tokens
Newer release
Mistral Medium 3.1
Released August 13, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Mistral Medium 3.19.2Mistral Medium 39Coding index
Mistral Medium 3.120.5Mistral Medium 3Not availableAgentic index
Mistral Medium 3.11.9Mistral Medium 3Not availablePricing
Mistral Medium 3.1 vs Mistral Medium 3 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mistral Medium 3.1 | Mistral Medium 3 |
|---|---|---|
| Input tokensPer 1M tokens | $0.40 | $0.40 |
| Output tokensPer 1M tokens | $2 | $2 |
| Cached input (read)Per 1M tokens | $0.04 | $0.04 |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Mistral Medium 3.1$1.80Mistral Medium 3$1.80Coding task
30K in, 4K out
Mistral Medium 3.1$20$9.20 cachedMistral Medium 3$20$9.20 cachedLong document summary
150K in, 2K out
Mistral Medium 3.1$64$10 cachedMistral Medium 3$64$10 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mistral Medium 3.1 | Mistral Medium 3 |
|---|---|---|
| Context window | 131K tokens | 131K tokens |
| Max output | 105K tokens | 105K tokens |
| Input types | File, Image, Text | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | August 13, 2025 | May 7, 2025 |
Features
Supported features
API features available for each model.
| Metric | Mistral Medium 3.1 | Mistral Medium 3 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Not supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Mistral Medium 3.1View full model details- Mistral Medium 3.1 vs GPT-4.1 Mini
- Mistral Medium 3.1 vs Mistral Small 4
- Mistral Medium 3.1 vs Qwen3 VL 235B A22B Instruct
- Mistral Medium 3.1 vs DeepSeek V3 0324
- Mistral Medium 3.1 vs Qwen3 Next 80B A3B Instruct
- Mistral Medium 3.1 vs Qwen3 Coder Next
- Mistral Medium 3.1 vs Mistral Large 3 2512
- Mistral Medium 3.1 vs Devstral 2 2512
- Mistral Medium 3.1 vs GLM 4.5V
- Mistral Medium 3.1 vs Mistral Large 2407
- Mistral Medium 3.1 vs Hermes 4 405B
- Mistral Medium 3.1 vs Nova Pro 1.0
- Mistral Medium 3.1 vs Mistral Large
- Mistral Medium 3.1 vs Mixtral 8x22B Instruct
Mistral Medium 3View full model details- Mistral Medium 3 vs Mistral Small 4
- Mistral Medium 3 vs GPT-4.1 Mini
- Mistral Medium 3 vs Qwen3 VL 235B A22B Instruct
- Mistral Medium 3 vs DeepSeek V3 0324
- Mistral Medium 3 vs Qwen3 Next 80B A3B Instruct
- Mistral Medium 3 vs Mistral Large 3 2512
- Mistral Medium 3 vs Qwen3 Coder Next
- Mistral Medium 3 vs Devstral 2 2512
- Mistral Medium 3 vs GLM 4.5V
- Mistral Medium 3 vs Mistral Large 2407
- Mistral Medium 3 vs Hermes 4 405B
- Mistral Medium 3 vs Nova Pro 1.0
- Mistral Medium 3 vs Mistral Large
- Mistral Medium 3 vs Mixtral 8x22B Instruct
Our take
Mistral Medium 3.1 scores higher on the Artificial Analysis Intelligence Index (9.2 vs 9). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Mistral Medium 3.1 or Mistral Medium 3 cheaper?
Mistral Medium 3.1 and Mistral Medium 3 cost the same for a typical chat (2K input tokens and 500 output tokens). Mistral Medium 3.1 costs $0.40 per 1M input tokens and $2 per 1M output tokens, and Mistral Medium 3 costs $0.40 per 1M input tokens and $2 per 1M output tokens.
Which has a bigger context window, Mistral Medium 3.1 or Mistral Medium 3?
Mistral Medium 3.1 supports up to 131K tokens of context, compared with 131K for Mistral Medium 3.
Is Mistral Medium 3.1 smarter than Mistral Medium 3?
On the Artificial Analysis Intelligence Index, Mistral Medium 3.1 scores 9.2 and Mistral Medium 3 scores 9, putting Mistral Medium 3.1 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Mistral Medium 3.1 and Mistral Medium 3 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mistral Medium 3.1 and Mistral Medium 3 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mistral Medium 3.1 and Mistral Medium 3 at the same time. Compare the answers side by side and keep the best one.