Mistral Small 3.1 24B
Mistral AI · released Mar 11, 2025 · mistralai/Mistral-Small-3.1-24B-Instruct-2503
- Type
- Open weightsApache License 2.0
- Params
- 24B
- Context
- 128K
about 96K words of context
Our take
Written Sep 30, 2026Mistral Small 3.1 24B is a downloadable model you can run yourself and build on commercially, with room for a long document in a single request. Its measured quality is weak, though: every Arena placing we hold sits in the bottom fifth of its field.
Use it for cost-sensitive work, or where you want to run the model on your own hardware and keep the option of building on it commercially. Its 128,000-token request capacity means long documents need not be split up first, though reliable recall across all of it is unverified in our data. Skip it if you need a model near the top of the Arena boards for coding, maths or instruction following.
The case for it
- You can download it and build on it commercially: the Apache License 2.0 allows commercial use, changes and redistribution.
- A 128,000-token request capacity takes a long document in one go, though room to hold it is not a guarantee of accurate recall.
- Text and images go into the same request, so a screenshot does not have to be described in words first.
The case against it
- Weak measured quality across every board we hold: 147th of 168 on Arena Text (overall), 136th of 168 on Arena Coding and 141st of 163 on Arena Maths as of 25 Sep 2026, all in the bottom fifth of their fields.
- Those boards record which answer people preferred rather than whether it was correct, so they are a signal about reception, not a verdict on accuracy.
How good is it?
An open-weights text model for general chat, though it trails most models on everyday questions, writing and coding.
- getting answers to everyday questionsArena Text (overall) · 147th of 168
- drafts, rewrites and editingArena Creative Writing · 141st of 168
- writing and completing codeArena Coding · 136th of 168
EverydayGeneral questions and everyday reasoning
Arena Text (overall)147th of 168 · 1303
CodingWriting and fixing code on its own
Arena Coding136th of 168 · 1361
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 Writing141st of 168 · 1270
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 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.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 5.7 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 13.7 GB spare means a 10% error in the size would not change the answer.
Apple M2 (10-core GPU) · 24 GB
Borderline fit on an estimated size. It leaves 0.9 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.35 in / $0.56 out
- Context served
- 128K
- Throughput
- ~18 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.35 / $0.56checked 4 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| Cloudflare Workers AIThrough OpenRouter | $0.35 / $0.56checked 4 hours ago | 128K102K max reply | 18 tok/s | No | Yesunknown period | Unknown |
OpenRouterAcross the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 0 appear 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 | ✓ | ✗ | ✗ |
| Cloudflare Workers AIThrough OpenRouter | ✓ | ✗ | ✗ |
Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
Models people weigh against Mistral Small 3.1 24B
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
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- mistralai/Mistral-Small-3.1-24B-Instruct-2503
- Architecture
- Dense
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- mistralai-mistral-small-3-1-24b