# Mistral Large 3

Mistral Large 3 is a text generation model from Mistral, available through the Impossibl API. Its published context window is 128,000 tokens. The advertised input rate is $0.50 per million input tokens. The advertised output rate is $1.50 per million output tokens.

- Model identifier: ` mistral/mistral-large-3 `
- Creator: Mistral
- Model type: Text generation
- Canonical model page: [Mistral Large 3](<https://impossibl.com/mistral/mistral-large-3>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2025-12-02

## Capabilities and limits

- Context window: 128,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text, image
- Outputs: text
- Tool calling: Not published

## API access

Use ` mistral/mistral-large-3 ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.50 | per million input tokens |
| Output | $1.50 | per million output tokens |
| Cache read | Not published | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T11:52:20.926Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### Mistral Large 3

Source: [Evaluation source](<https://artificialanalysis.ai/models/mistral-large-3>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 9.71 |
| Omniscience Index | -39.57 |
| GPQA | 67.98% |
| Humanity’s Last Exam | 4.17% |
| SciCode | 36.57% |
| CritPt | 0.00% |
| Terminal-Bench v2.1 | 11.99% |
| Terminal-Bench v4.0 | 0.00% |
| Terminal-Bench Hard | 15.91% |
| AA-LCR | 36.00% |
| GDPval Elo | 588.39 |
| GDP.pdf All-pass | 1.20% |
| AutomationBench Partial | 1.50% |
| MMMU-Pro | 55.66% |
| IFBench | 36.19% |
| Tau2 | 24.56% |
| Tau Banking | 5.77% |
| LiveCodeBench | 46.46% |
| AIME 2025 | 38.00% |
| coding index (API) | 20.1 |
| agentic index (API) | 2.4 |
| intelligence index (API) | 9.7 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/mistral/mistral-large-3/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Mistral Large 3?

Mistral Large 3 is a text-generation model from Mistral, available through the Impossibl API.

### How much does Mistral Large 3 cost?

Mistral Large 3 costs $0.50 per million input tokens and $1.50 per million output tokens through the Impossibl API. All rates are in USD.

### What is the context length of Mistral Large 3?

Mistral Large 3 has a 128,000-token context window through the Impossibl API.

### What inputs and outputs does Mistral Large 3 support?

Mistral Large 3 accepts text and image as input. Mistral Large 3 returns text.

### How do I use Mistral Large 3 through an API?

Mistral Large 3 is available through the Impossibl API. Use mistral/mistral-large-3 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was Mistral Large 3 released?

Mistral released Mistral Large 3 on December 2, 2025.

Sources: [Creator release announcement](<https://legal.mistral.ai/ai-governance/models/mistral-large-3/>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Mistral Large 3: model details and pricing](<https://impossibl.com/mistral/mistral-large-3>)
- [Model directory](<https://impossibl.com/models>)