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 Aug 1, 2026Mistral Small 3.1 is a 24-billion-parameter text-and-image model released in 2025 with a permissive Apache licence. It handles up to 128,000 tokens in a single request and shows measured coding strength across six Arena benchmarks, making it a mid-tier generalist for teams that want open-weight flexibility.
Pick this for budget-conscious hosted deployment where both providers charge the same rate, or for coding tasks where it scores highest among its own measured skills. Use it for multimodal text-and-image workflows under Apache 2.0 terms, or long-context work up to 128,000 tokens. Skip it if you need measured vision quality scores, if creative writing quality is critical, or if you want the efficiency of a mixture-of-experts architecture.
The case for it
- Broad benchmark coverage with coding as the standout skill: its Arena Coding score is over 90 points higher than its own Creative Writing score.
- Truly permissive Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- 128,000-token request limit is large for a 24-billion-parameter model.
- Identical pricing across both tracked providers, so there is no markup arbitrage.
The case against it
- OpenRouter throughput is undisclosed; only Cloudflare shows a measured 39 tokens per second.
- Creative writing is the lowest of its six own Arena scores, trailing its coding score by over 90 points.
- Dense architecture with 24 billion total parameters and no verified active-parameter count — likely full 24 billion active per token, which may limit local efficiency compared with mixture-of-experts alternatives.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)124th of 143 · 1303.4
CodingWriting and fixing code on its own
Arena Coding114th of 143 · 1361.8
Arena Coding is the only board that has scored it for this.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Mistral Small 3.1 24B 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 Small 3.1 24B 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.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.35 in / $0.56 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.35 / $0.56 | 128K | not measured | Unknown | Unknown | Unknown |
| Cloudflare Workers AI | $0.35 / $0.56 | 128K | 43 tok/s | No | Yesunknown period | Unknown |
Cloudflare Workers 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 | ✗ | ✗ | ✗ |
| Cloudflare Workers AI | ✗ | ✗ | ✗ |
Tool calling: 0 of 2 listings say yes, 2 say no. 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
Dates behind this page
Prices last checked 4d ago
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 do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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
- Modality record
- text+image->text
- Catalogue slug
- mistralai-mistral-small-3-1-24b