Mistral Small 4
Mistral AIReleased Mar 16, 2026Open weights · Apache 2.0mistral-small-4
- Context
- 1M tokens
- Max output
- 64k tokens
- Input
- text, image
- Mistral AI's API
- yes, as mistral-small-2603
Read Sep 17, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Mistral AI
The cheapest host, Mistral AI, serves a 256K context (maker: 1M). Weights and context per host
Run it yourself
open weights, Apache 2.0 · fits 4 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 119B
- 6.5B active per token (MoE)
- Memory needed
- 71 GB
- in INT4 · 143 GB in INT8
- Smallest cloud setup
- A100
- 80 GB · $1.19/h, about $869 a month
- Worth it above
- 1B tokens
- a month, against the cheapest API at $0.75 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 71 GB | A100 · $1.19/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 143 GB | 2× H100 · $4.30/h | near-lossless |
| FP16 (full) | 286 GB | 4× H100 · $8.60/h | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (96 GB unified), about $5,499 once, or $0.2092/h over 3 years, electricity aside; it pays for itself after about 7B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | Uptime 24h | Checked |
|---|---|---|---|---|---|
| Mistral AI256K ctx (1M) · 32K out | $0.15 | $0.60 | — | — | Sep 3 |
| Veniceprecision not read: host terms · 256K ctx (1M) · 64K out | $0.19 | $0.75 | — | 100% | Sep 17 |
2 of 2 providers · prices per million tokens, read Sep 17, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Mistral AI | not checked yet | 256K | 32K | — | — | — |
| Venice | not read: host terms | 256K | 64K | — | — | — |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Mistral Small 4 spec sheet, field by field, with sources
Mistral Small 4 spec sheetmaker-declared
What Mistral AI declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 1,048,576 tokens
- Parameters
- 119,401,317,952≈ 119.4B
- Active experts
- 4 of 128 active per token
- Weight precision
- fp8
- License
- Apache 2.0 — open weights, permissivecurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the makermaker's docs · read 2026-09-07
- Modalities
- text · image
- Max output (official)
- not published by the makermaker's docs · read 2026-09-07
- Release date
- March 16, 2026maker's docs · read 2026-09-07
- Maker lifecycle status
- General availabilitymaker's docs · read 2026-09-07
Also declared in the weights
- Architecture class
- Mistral3ForConditionalGeneration
- Layers
- 36
- Vocabulary
- 131,072 tokens
- Weights first published
- January 23, 2026
- Weights last updated
- July 15, 2026
- Languages declared
- 24 languages
mistralai/Mistral-Small-4-119B-2603 · config.json @ a11f36b · read 2026-10-08 · 8 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Mistral AI | $0.45 | $1.50 | $1.20 |
| Venice | $0.56 | $1.88 | $1.50 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Mistral AI models · all its models, hosts and history ›
- Mistral Nemo6 providers · from $0.038
- Mistral Small 3.2 24B4 providers · from $0.28
- Codestral 25081 provider · from $1.20
- Devstral 2 25121 provider · from $2.40
- Ministral 3 14B 25121 provider · from $0.40
- Ministral 3 3B 25121 provider · from $0.20