AI model comparison
Mistral Small 4 vs Mistral Large 3 2512
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Mistral
Mistral Small 4
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.
- Input / 1M
- $0.15
- Output / 1M
- $0.60
- Context
- 262K
Mistral
Mistral Large 3 2512
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
- Input / 1M
- $0.50
- Output / 1M
- $1.50
- Context
- 262K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mistral Small 4
2.9x cheaper for a typical chat
Higher intelligence score
Mistral Small 4
11.3 vs 9.3 on Artificial Analysis
Larger context window
Tie
262K vs 262K tokens
Newer release
Mistral Small 4
Released March 16, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Mistral Small 411.3Mistral Large 3 25129.3Coding index
Mistral Small 426.6Mistral Large 3 251220.1Agentic index
Mistral Small 40.8Mistral Large 3 25121Pricing
Mistral Small 4 vs Mistral Large 3 2512 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mistral Small 4 | Mistral Large 3 2512 |
|---|---|---|
| Input tokensPer 1M tokens | $0.15 | $0.50 |
| Output tokensPer 1M tokens | $0.60 | $1.50 |
| Cached input (read)Per 1M tokens | $0.02 | $0.05 |
| 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 Small 4$0.60Mistral Large 3 2512$1.75Coding task
30K in, 4K out
Mistral Small 4$6.90$2.85 cachedMistral Large 3 2512$21$7.50 cachedLong document summary
150K in, 2K out
Mistral Small 4$23.70$3.45 cachedMistral Large 3 2512$78$10.50 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mistral Small 4 | Mistral Large 3 2512 |
|---|---|---|
| Context window | 262K tokens | 262K tokens |
| Max output | 210K tokens | 210K tokens |
| Input types | Image, Text | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, None | Not available |
| Default reasoning effort | High | Not available |
| Release date | March 16, 2026 | December 1, 2025 |
Features
Supported features
API features available for each model.
| Metric | Mistral Small 4 | Mistral Large 3 2512 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | 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 Small 4View full model details- Mistral Small 4 vs Gemini 2.5 Flash Lite
- Mistral Small 4 vs gpt-oss-120b
- Mistral Small 4 vs GPT-5 Nano
- Mistral Small 4 vs Qwen3 235B A22B Instruct 2507
- Mistral Small 4 vs Nemotron 3 Super
- Mistral Small 4 vs Qwen3 Coder 480B A35B
- Mistral Small 4 vs GLM 4.6V
- Mistral Small 4 vs GLM 4.5 Air
- Mistral Small 4 vs Trinity Large Thinking
- Mistral Small 4 vs Llama 4 Maverick
- Mistral Small 4 vs Mistral Medium 3.1
- Mistral Small 4 vs Mistral Medium 3
- Mistral Small 4 vs Saba
Mistral Large 3 2512View full model details- Mistral Large 3 2512 vs GPT-4.1 Mini
- Mistral Large 3 2512 vs Qwen3 VL 235B A22B Instruct
- Mistral Large 3 2512 vs DeepSeek V3 0324
- Mistral Large 3 2512 vs Qwen3 Next 80B A3B Instruct
- Mistral Large 3 2512 vs Qwen3 VL 30B A3B Thinking
- Mistral Large 3 2512 vs Qwen3 Coder Next
- Mistral Large 3 2512 vs Mistral Medium 3.1
- Mistral Large 3 2512 vs Mistral Medium 3
- Mistral Large 3 2512 vs Devstral 2 2512
- Mistral Large 3 2512 vs GLM 4.5V
Our take
Mistral Small 4 is 2.9x cheaper for a typical chat. Mistral Small 4 scores higher on the Artificial Analysis Intelligence Index (11.3 vs 9.3). 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 Small 4 or Mistral Large 3 2512 cheaper?
Mistral Small 4 is cheaper for a typical chat (2K input tokens and 500 output tokens). Mistral Small 4 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens, while Mistral Large 3 2512 costs $0.50 per 1M input tokens and $1.50 per 1M output tokens.
Which has a bigger context window, Mistral Small 4 or Mistral Large 3 2512?
Mistral Small 4 supports up to 262K tokens of context, compared with 262K for Mistral Large 3 2512.
Is Mistral Small 4 smarter than Mistral Large 3 2512?
On the Artificial Analysis Intelligence Index, Mistral Small 4 scores 11.3 and Mistral Large 3 2512 scores 9.3, putting Mistral Small 4 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Mistral Small 4 and Mistral Large 3 2512 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mistral Small 4 and Mistral Large 3 2512 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mistral Small 4 and Mistral Large 3 2512 at the same time. Compare the answers side by side and keep the best one.