MMistral · Released Dec 2, 2025
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.
- Released
- Dec 2 2025
- Context window
- 131K 105K out
- Input / 1M tokens
- $0.10
- Output / 1M tokens
- $0.10
Where to run it
9 providers compared
Cheapest: Mistral, NanoGPT, Kilo Gateway +3 more at $0.10 / $0.10 per 1M input / output tokens — 51% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Mistralzdr | $0.10 | $0.10 | $0.01 | 131K | 105K | 100%24h | Cheapest |
| Mistral | $0.10 | $0.10 | $0.01 | 131K | 105K | 100%24h | Cheapest |
| NanoGPTno tool calling | $0.10 | $0.10 | $0.05 | 131K | 33K | — | Cheapest |
| Kilo Gateway | $0.10 | $0.10 | $0.01 | 131K | 105K | — | Cheapest |
| LLM Gatewayno tool calling | $0.10 | $0.10 | — | 131K | 131K | — | Cheapest |
| DevPass (LLM Gateway)no tool calling | $0.10 | $0.10 | — | 131K | 8K | — | Cheapest |
| Eden AI | $0.10 | $0.10 | $0.01 | 131K | 105K | — | Cheapest |
| LowRouter | $0.10 | $0.10 | $0.011 | 262K | 262K | — | +5% |
| Mistraleu | $0.11 | $0.11 | $0.011 | 131K | 105K | 100%24h | +10% |
| Cortecs | $0.12 | $0.12 | $0.012 | 256K | 256K | — | +23% |
| AI/ML API | $0.21 | $0.21 | $0.014 | 131K | 105K | — | +106% |
Value
Price vs. performance
Ministral 3 3B 2512 Other Mistral Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
2 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 25.3% | #120of 122 | Gemini 4 Argon96.4% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 5.5% | #119of 123 | Claude Sonnet 5.568.3% |
Specs
Details
- Model ID
mistralai/ministral-3b-2512- Developer
- Mistral
- Release date
- Dec 2, 2025 ·
- Context window
- 131,072 tokens
- Max output
- 104,857 tokens
- API price
- $0.10 / $0.10 per 1M input / output tokens
- Providers
- 9
- Input types
- text, image
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.