Mistral Large
Mistral AI · released Feb 26, 2024
- Type
- Proprietary
- Input
- $2.00
- Output
- $6.00
- Cached
- $0.20
List price · per 1M tokens · Mistral AI at 128K context · source ↗
Our take
Written Aug 3, 2026Mistral Large is a hosted-only text model from Mistral AI that handles up to 128,000 tokens in a single request. It launched in early 2024 with broad benchmark coverage and strong instruction-following scores, though its reasoning on graduate-level problems is weak.
Pick this for long-document processing where a 128,000-token request limit matters, or for instruction-following tasks where its 84% score on that benchmark is relevant. Use it if you want predictable pricing across providers. Skip it if you need graduate-level reasoning, if you want to self-host, or if you need price competition between hosts to drive costs down.
The case for it
- Strong instruction-following performance, with an IFEval score of 84%.
- Broad benchmark coverage across six Arena categories, with ratings from 1210.71 to 1294.90.
- Identical pricing across both tracked providers, so costs are predictable.
The case against it
- Weak graduate-level reasoning: 24.9% on GPQA Diamond, near the random baseline for this benchmark.
- MMLU-Pro score of 50.7% lags for a flagship-class model on professional and graduate knowledge.
- Low measured throughput of 9 tokens per second on Mistral's own endpoint, with no price competition between its two offers.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)137th of 143 · 1242
CodingWriting and fixing code on its own
Arena Coding135th of 143 · 1294.9
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Mistral Large for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Mistral Large placed and give it no mark out of five.
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, which is why they get no rating.
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.
Or rent it from someone else
Why this differs from the header. The strip above quotes Mistral AI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $2.00 in / $6.00 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.00 / $6.00 | 128K | not measured | Unknown | Unknown | Unknown |
| Mistral AI | $2.00 / $6.00 | 128K | 4 tok/s | No | Yes30 days | Unknown |
Mistral AIAcross the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Mistral AI | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against Mistral Large
When we formed this view
Dates behind this page
Prices last checked 9d ago
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 2 listings do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+file->text
- Catalogue slug
- mistralai-mistral-large