mistralai
Mistral Large 2407
mistralai/mistral-large-2407
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Mistral Large 2407 (Mistral Large 2, version 24.07) is Mistral AI's 123-billion-parameter flagship with a 128k-token context window, text and file inputs, and text output. Mistral reports strong multilingual coverage, support for more than 80 programming languages, and parallel and sequential function calling; its benchmark and parity claims are vendor-reported, not independently verified here. Instruct weights are published on Hugging Face under research and non-commercial terms. The model is now deprecated: Mistral says it is no longer maintained and recommends a newer Mistral Large.[1][2]
Strengths
- Vendor-reported strengths include reasoning, code generation, and instruction following, plus fine-tuning intended to reduce hallucinated or ungrounded answers; these are Mistral's claims rather than independently measured results.[1][2]
- Broad language coverage: Mistral lists dozens of natural languages and over 80 coding languages, and reports multilingual benchmark gains over the previous Mistral Large.[2]
- Supports parallel and sequential function calling, structured outputs, and tool use, alongside a 128k-token context window suited to long documents.[1][2]
Limitations
- Deprecated and no longer maintained; Mistral directs users to a newer Mistral Large model, so long-term support and updates should not be expected.[2]
- Evidence here is a catalog entry plus the vendor's announcement, with no independent evaluations in this pack; reported capabilities should be validated on your own workload before adoption.[1][2]
- The catalog lists a March 2024 knowledge cutoff, no dedicated reasoning mode, and no benchmark data for this endpoint; licensing separates research and non-commercial use from commercial self-deployment.[1][2]
Where to use it
- Multilingual chat and document applications that need long-context processing of text and file inputs.[1][2]
- Agent-style business workflows that rely on tool use and parallel or sequential function calls.[2]
- Code assistance across many programming languages, where vendor-reported code performance fits the team's needs.[2]
Sources
- [1] OpenRouter catalog · Mistral Large 2407Sources checked: Nov 13, 2026
- [2] Model documentation · Mistral Large 2407Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....
Specifications
- Model ID
- mistralai/mistral-large-2407
- Creator
- mistralai
- Added to OpenRouter
- 19.11.2024
- Context length
- 131,072
- Modality
- text+file->text
- Input modalities
- text, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2 / out $6
- Knowledge cutoff
- 31.03.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | input: file |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mistral | 131,072 | $2 | $6 | — | — | — |
| Mistral | 131,072 | $2 | $6 | — | — | — |
| Mistral | 131,072 | $2.2 | $6.6 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.