Mistral Large
Mistral AI · released Feb 26, 2024
- Type
- Closed
- Input
- $2.00
- Output
- $6.00
- Cached
- $0.20
List price · per 1M tokens · Mistral AI at 128K context · source ↗
Our take
Written Sep 2, 2026Mistral Large is a hosted-only text model from Mistral AI that handles up to 128,000 tokens per request and accepts file attachments. It is a mid-tier generalist with broad arena coverage, though its reasoning scores lag and published technical details are thin.
Pick this for general text work where a 128K request limit and file input matter, or for creative-writing and instruction-following pipelines at its measured 84% accuracy. Skip it if you need graduate-level science reasoning, want to self-host, or need a wide choice of providers.
The case for it
- Broad arena benchmarking with a coding preference score 53 points above its own general mark.
- Strong measured instruction-following accuracy at 84% on IFEval.
- Three of four tracked offers at identical rates, making price comparison straightforward.
The case against it
- GPQA Diamond at 24.9% correct — barely above random chance on four-option science questions.
- Parameter count undisclosed, licence terms not published, and only four provider offers tracked.
- Maths performance 51 points below its own coding peak on the same arena leaderboard.
How good is it?
A general text model for chat and drafting, though it trails most rivals on everyday questions, prose and code.
- getting answers to everyday questionsArena Text (overall) · 161st of 168
- drafts, rewrites and editingArena Creative Writing · 158th of 168
- writing and completing codeArena Coding · 159th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)161st of 168 · 1243
CodingWriting and fixing code on its own
Arena Coding159th of 168 · 1296
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Arena Creative Writing158th of 168 · 1211
Arena Creative Writing is the only board that has scored it for this.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked 2 hours ago — each listing carries its own date.
Mistral AI, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Mistral AI on 128K of context.
- per 1M tokens
- $2.00 in / $6.00 out
- Context served
- 128K
- Throughput
- ~48 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $2.00 / $6.00checked 2 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $2.00 / $6.00checked 2 hours ago | 128K102K max reply | 48 tok/s | No | Yes30 days | Unknown |
| Mistral AIeuThrough OpenRouter | $2.20 / $6.60checked 2 hours ago | 128K102K max reply | 3 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Mistral AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Mistral AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against Mistral Large
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text and documents in, text out
- Catalogue slug
- mistralai-mistral-large