List price
Input / 1M$0.10Output / 1M$0.10Cache read / 1M$0.010Blended$0.100Value index—Last move—
models.dev · MIT · retrieved Oct 24, 2026
Mistral
Ministral 3B (latest)
Ministral 3B (latest) is listed by Mistral at $0.1 input and $0.1 output per million tokens. The recorded context window is 131,072 tokens. Release date on file: 2024-10-01. No LMArena overall rating was matched for this name, so it is left out of the Value Index. Price source: models.dev (MIT).
- Context12
- Inverse price100
- Arena—
- GPQA—
- Tools100
- Modalities67
Price history
Input and output list price. A missing day stays a gap in the line. The series is not a quality history.
No ModelPriceWatch series matched this model, so there is no line to draw.
Benchmarks
LMArena is CC-BY-4.0. Epoch scores, including LiveBench where Epoch publishes it, are CC-BY-4.0. A blank cell means this snapshot has no match. Nothing here is estimated.
| Benchmark | Score | Detail | Source |
|---|---|---|---|
| LMArena overall | — | — | — |
| LMArena coding | — | — | — |
| LMArena math | — | — | — |
| GPQA Diamond | — | — | — |
| LiveBench | — | — | — |
| SWE-bench Verified | — | — | — |
| Epoch Capability Index | 118.04 | 106.31–121.89 | Epoch AI Capabilities & benchmarking · CC-BY-4.0 |
Provider prices
The list row is the price used for the value index. Other rows are the same model id on models.dev, plus the LiteLLM catalog price when we have one. A split quote is kept beside the list price.
| Quote | Provider | Input / 1M | Output / 1M | Blended | Source |
|---|---|---|---|---|---|
| List | Mistral | $0.10 | $0.10 | $0.100 | models.dev · MIT |
| Also listed | NanoGPT | $0.10 | $0.10 | $0.100 | models.dev · MIT |
| Also listed | Vercel AI Gateway | $0.10 | $0.10 | $0.100 | models.dev · MIT |
| Also listed | Azure Cognitive Services | $0.040 | $0.040 | $0.040 | models.dev · MIT |
| LiteLLM | mistral | $0.10 | $0.10 | $0.100 | LiteLLM model_prices_and_context_window.json · MIT |
Spec
Context131,072Max output128,000Inputtext, image, pdfOutputtextReleased2024-10-01Open weightsYes
Spec fields are from the models.dev row for Mistral.