Mistral Small 4
Mistral AI · released Jan 23, 2026 · mistralai/Mistral-Small-4-119B-2603
- Type
- Open weightsApache License 2.0
- Params
- 119B
- Context
- 262K
about 197K words of context
Our take
Written Aug 3, 2026Mistral Small 4 is a 119.4-billion-parameter text-and-image model released in January 2026 with a permissive Apache licence. It can handle up to 262,144 tokens in a single request, among the longest disclosed limits for downloadable models, though no independent quality scores are available yet.
Pick this when you need a permissive open licence for commercial deployment or fine-tuning, or for long-document tasks that need a quarter-million-token request limit. Use it for basic text-and-image inference where you value licence freedom over measured quality. Skip it if you need verified benchmark scores, a wide choice of hosting providers, or independently confirmed speed claims.
The case for it
- Apache 2.0 licence allows unrestricted commercial use, fine-tuning and redistribution.
- 262,144-token request limit is among the longest disclosed for downloadable models.
- The cheapest tracked provider delivers higher throughput than the most expensive one: 58 tokens per second versus 37.
The case against it
- No benchmark scores yet — chat, reasoning, coding and multimodal quality are all unverified in our data.
- Only three tracked offers, with narrow price variation and one provider charging more for slower throughput.
- The fastest throughput figure comes from the vendor's own platform, not an independent source.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Mistral Small 4 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
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%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M1 Ultra (64-core GPU) · 128 GB
Room to spare. 16.1 GB spare means a 10% error in the size would not 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 3 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
- $0.15 in / $0.60 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.15 / $0.60 | 262K | not measured | Unknown | Unknown | Unknown |
| Mistral AI | $0.15 / $0.60 | 262K | 104 tok/s | No | Yes30 days | Unknown |
| Venice AIfp8 | $0.19 / $0.75 | 256K | 6 tok/s | No | No | Confirmed |
Mistral AIAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 do not say. 1 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 | ✓ | ✓ | ✓ |
| Venice AIfp8 | ✗ | ✓ | ✓ |
Tool calling: 2 of 3 listings say yes, 1 says no. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against Mistral Small 4
When we formed this view
Dates behind this page
Prices last checked 5d 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.
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings do not say whether they train on prompts.
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-4-119B-2603
- Architecture
- Dense
- Modality record
- text+image->text
- Catalogue slug
- mistralai-mistral-small-4