mistralai
Mistral: Mistral Large 4
mistralai/mistral-large-4-0
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Mistral Large 4 is Mistral AI's flagship open-weight model: a natively multimodal Mixture-of-Experts with roughly 1 trillion total and about 52 billion active parameters per token, accepting text and image input and producing text over a 1M-token context window. Vendor documentation reports it unifies instruction following, configurable reasoning, coding, and agentic tool use, with claimed strength in cybersecurity, finance, law, and visual grounding. Available via the Mistral API and aggregators such as OpenRouter, it can also be self-hosted with vLLM or SGLang, though at substantial infrastructure cost.[1][2]
Strengths
- Vendor-reported top-tier agentic coding among open-weight models, with substantially lower token use per task than the leading comparable model, according to Mistral's own benchmark reporting.[2]
- Mistral AI reports native fluency in more than 160 languages, including every official EU language.[2]
- Broad feature surface in a single set of weights: text and image input, text output, function calling, strict JSON schema enforcement, configurable reasoning effort, and a 1M-token context window.[1][2]
Limitations
- Evidence is limited to the vendor's model card and one aggregator listing, which even disagree on which reasoning-effort levels are exposed; no independent evaluations were included, so validate on your own workloads.[1][2]
- Self-hosting is heavy: at roughly 1 trillion parameters, the vendor's reference recipes use eight GPUs, and Mistral itself suggests its API if local serving falls short.[2]
- License caveat: Mistral's modified open-weight license permits commercial and non-commercial use, but operating a model-as-a-service business requires a separate commercial license.[2]
Where to use it
- A plausible fit for agentic coding assistants and tool-using pipelines, given native function calling and the vendor's reported token-efficiency advantage.[2]
- Worth evaluating for long-context document and image analysis, such as charts, technical drawings, and visual grounding, per the card's vision claims.[2]
- A candidate for multilingual products, especially across European Union languages, based on the vendor's fluency claims rather than independent testing.[2]
Sources
- [1] OpenRouter catalog · Mistral: Mistral Large 4Sources checked: Nov 13, 2026
- [2] Model documentation · Mistral: Mistral Large 4Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...
Specifications
- Model ID
- mistralai/mistral-large-4-0
- Canonical ID
- mistralai/mistral-large-4-0-20261006
- Creator
- mistralai
- Added to OpenRouter
- 06.10.2026
- Context length
- 1,048,576
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.700 / out $2.1
- Knowledge cutoff
- —
- 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 | BB — next 30% of the cohort | reasoning: optional · default high · efforts: high, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: high, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 26.1 | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 45.8% · rank 33 | 1,242Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 43.5% · rank 25 | 1,204Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 46.9% · rank 40 | 1,256Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 51.3% · rank 24 | 1,274Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 40.2% · rank 52 | 1,205Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 44.9% · rank 22 | 1,224Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 49% · rank 28 | 1,279Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 48% · rank 38 | 1,259Elo | AA — next 20% of the cohort | 13.11.2026 |
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 | 1,048,576 | $0.700 | $2.1 | — | — | 100% |
| Mistral | 524,288 | $0.770 | $2.31 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.