Mistral Small 4
by Mistral AIChat
Fast Mistral production model for chat, extraction, and cost-sensitive agents
- Context
- 262K tokens
- Max output
- 256,000 tokens
- Released
- 2026-03-16
- Weights
- Open
mistral/mistral-small-2603 · also seen as mistralai/mistral-small-2603, mistralai/Mistral-Small-4-119B-2603, mistral-small-4, mistral-small-2603@eu, +4 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-03-16
- Weights
- Open
- Input
- Text, Image
- Output
- Text
- Context window
- 262,144 max across endpoints
- Max output
- 256,000
- Providers
- 7 + 11 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.070–$0.258 in · $0.28–$1.03 out per 1M tokens · across all 7 providers
More details
- Last updated
- 2026-08-01
- Knowledge cutoff
- 2025-06
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefill
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.07 in / $0.28 out per 1M tokens at SAP AI Core on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Mistral Small 4 |
|---|---|---|---|---|---|
| Qwen 3 Coder 30B A3B InstructAlibaba (Qwen) | $0.225 | $0.15 | $0.60 | 262K | +0% |
| Qwen3 VL 30B A3B InstructAlibaba (Qwen) | $0.225 | $0.15 | $0.60 | 262K | +0% |
| Command RCohere | $0.225 | $0.15 | $0.60 | 128K | +0% |
| Llama 4 MaverickMeta | $0.225 | $0.15 | $0.60 | 131K | +0% |
| MiniMax-M3.1-FlashMiniMax | $0.225 | $0.15 | $0.60 | 1M | +0% |
| Mistral SmallMistral AI | $0.225 | $0.15 | $0.60 | 262K | +0% |
| GPT-4o miniOpenAI | $0.225 | $0.15 | $0.60 | 128K | +0% |
| GPT OSS Safeguard 120BOpenAI | $0.225 | $0.15 | $0.60 | 131K | +0% |
More from Mistral AI
Newest Mistral AI models in the catalogue. All Mistral AI models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Mistral Large 4 | 2026-10-06 | 1.05M | from $0.68 |
| Voxtral Small 24B 2507 STT | 2026-08-13 | — | unpriced |
| Leanstral 1.5 | 2026-06-30 | 262K | unpriced |
| Mistral Code Latest | 2026-06-02 | 128K | from $0.30 |
| Mistral Code Agent Latest | 2026-06-02 | 256K | from $0.40 |
| Voxtral Mini Transcribe | 2026-05-15 | 16.4K | unpriced |
| Mistral Medium 3.5 | 2026-04-30 | 262K | from $1.50 |
| Mistral Medium 3.5 | 2026-04-29 | 262K | from $1.50 |