AI model comparison
Ministral 3 3B 2512 vs Mistral Small 3
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Mistral
Ministral 3 3B 2512
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
- Input / 1M
- $0.10
- Output / 1M
- $0.10
- Context
- 131K
Mistral
Mistral Small 3
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.
- Input / 1M
- $0.05
- Output / 1M
- $0.08
- Context
- 33K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mistral Small 3
1.8x cheaper for a typical chat
Higher intelligence score
Mistral Small 3
6.7 vs 4.8 on Artificial Analysis
Larger context window
Ministral 3 3B 2512
131K vs 33K tokens
Newer release
Ministral 3 3B 2512
Released December 2, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Ministral 3 3B 25124.8Mistral Small 36.7Coding index
Ministral 3 3B 25124.8Mistral Small 3Not availableAgentic index
Ministral 3 3B 25120.8Mistral Small 3Not availablePricing
Ministral 3 3B 2512 vs Mistral Small 3 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Ministral 3 3B 2512 | Mistral Small 3 |
|---|---|---|
| Input tokensPer 1M tokens | $0.10 | $0.05 |
| Output tokensPer 1M tokens | $0.10 | $0.08 |
| Cached input (read)Per 1M tokens | $0.01 | Not available |
| 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
Ministral 3 3B 2512$0.25Mistral Small 3$0.14Coding task
30K in, 4K out
Ministral 3 3B 2512$3.40$0.70 cachedMistral Small 3$1.82Long document summary
150K in, 2K out
Ministral 3 3B 2512$15.20$1.70 cachedMistral Small 3$7.66Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Ministral 3 3B 2512 | Mistral Small 3 |
|---|---|---|
| Context window | 131K tokens | 33K tokens |
| Max output | 105K tokens | 16K tokens |
| Input types | Image, Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | December 2, 2025 | January 30, 2025 |
Features
Supported features
API features available for each model.
| Metric | Ministral 3 3B 2512 | Mistral Small 3 |
|---|---|---|
| Tool calling | Supported | Not 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.
Ministral 3 3B 2512View full model details- Ministral 3 3B 2512 vs Mistral Nemo
- Ministral 3 3B 2512 vs Llama 3.1 8B Instruct
- Ministral 3 3B 2512 vs Nova Micro 1.0
- Ministral 3 3B 2512 vs Gemma 3 12B
- Ministral 3 3B 2512 vs Ministral 3 8B 2512
- Ministral 3 3B 2512 vs Phi 4
- Ministral 3 3B 2512 vs Ministral 3 14B 2512
- Ministral 3 3B 2512 vs Granite 4.0 Micro
- Ministral 3 3B 2512 vs Gemma 3 4B
- Ministral 3 3B 2512 vs Llama 3.2 1B Instruct
Mistral Small 3View full model details- Mistral Small 3 vs gpt-oss-20b
- Mistral Small 3 vs Mistral Nemo
- Mistral Small 3 vs Llama 3.1 8B Instruct
- Mistral Small 3 vs Nova Micro 1.0
- Mistral Small 3 vs Ministral 3 8B 2512
- Mistral Small 3 vs Phi 4
- Mistral Small 3 vs Ministral 3 14B 2512
- Mistral Small 3 vs Nova Lite 1.0
- Mistral Small 3 vs Granite 4.0 Micro
- Mistral Small 3 vs Gemma 3 4B
Our take
Mistral Small 3 is 1.8x cheaper for a typical chat. Mistral Small 3 scores higher on the Artificial Analysis Intelligence Index (6.7 vs 4.8). Ministral 3 3B 2512 has the larger context window (131K vs 33K tokens). 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 Ministral 3 3B 2512 or Mistral Small 3 cheaper?
Mistral Small 3 is cheaper for a typical chat (2K input tokens and 500 output tokens). Mistral Small 3 costs $0.05 per 1M input tokens and $0.08 per 1M output tokens, while Ministral 3 3B 2512 costs $0.10 per 1M input tokens and $0.10 per 1M output tokens.
Which has a bigger context window, Ministral 3 3B 2512 or Mistral Small 3?
Ministral 3 3B 2512 supports up to 131K tokens of context, compared with 33K for Mistral Small 3.
Is Ministral 3 3B 2512 smarter than Mistral Small 3?
On the Artificial Analysis Intelligence Index, Ministral 3 3B 2512 scores 4.8 and Mistral Small 3 scores 6.7, putting Mistral Small 3 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Ministral 3 3B 2512 and Mistral Small 3 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Ministral 3 3B 2512 and Mistral Small 3 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Ministral 3 3B 2512 and Mistral Small 3 at the same time. Compare the answers side by side and keep the best one.