Mistral Large 2407
Mistral AI · released Nov 19, 2024
- Type
- Proprietary
- Input
- $2.00
- Output
- $6.00
- Cached
- $0.20
List price · per 1M tokens · Mistral AI at 131K context · source ↗
Our take
Written Aug 3, 2026Mistral Large 2407 is a hosted-only text model from Mistral AI that accepts file attachments and handles up to 131,072 tokens in a single request. Its benchmark suite shows coding as the strongest area, with consistent scores across two evaluation dates, though maths and creative writing trail by wide margins.
Pick this for long-document processing at 131K context when you accept hosted-only access. Use it for coding, its strongest measured area, or if you are already in the Mistral ecosystem. Skip it if you need downloadable weights, price competition between providers, or strong maths and creative writing scores.
The case for it
- Coding is its strongest arena category relative to its own other scores, with a 39.6-point gap over its overall text score and a 66.5-point gap over creative writing.
- Consistent benchmark results across two evaluation dates: Arena Text moved only 0.0652 points between 2026-07-30 and 2026-08-02.
- Identical pricing across both tracked providers eliminates shopping friction.
The case against it
- No measured throughput on the secondary provider; OpenRouter throughput is unmeasured in our data.
- Maths and creative writing lag its own coding score by substantial margins — 65.6 and 66.5 points respectively.
- Premium output pricing with proprietary weights and no published parameter count.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)121st of 143 · 1314.2
CodingWriting and fixing code on its own
Arena Coding119th of 143 · 1353.8
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 2407 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 2407 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 model6 scoresEvery figure we hold, from 6 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
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.00 / $6.00 | 131K | not measured | Unknown | Unknown | Unknown |
| Mistral AI | $2.00 / $6.00 | 131K | 27 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 2407
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-2407