Mistral Small 3
by Mistral AIChat
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.
- Context
- 32.8K tokens
- Max output
- 32,768 tokens
- Parameters
- 23.6B total
- Released
- 2025-01-30
- Weights
- Open
- Licence
- apache-2.0
mistral/mistral-small-24b-instruct-2501 · also seen as mistralai/Mistral-Small-24B-Instruct-2501, deepinfra/mistralai/Mistral-Small-24B-Instruct-2501, accounts/fireworks/models/mistral-small-24b-instruct-2501
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-01-30
- Weights
- Opennot gated
- License
- apache-2.0
- Input
- Text
- Output
- Text
- Context window
- 32,768 max across endpoints
- Max output
- 32,768
- Providers
- 5 + 4 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.05–$0.90 in · $0.08–$0.90 out per 1M tokens · 4 of 5 providers have a comparable price
More details
- Last updated
- 2025-01-30
- Knowledge cutoff
- 2023-10-31
- Weights link
- Hugging Face · mistralai/Mistral-Small-24B-Instruct-2501
- Parameters
- 23.6B total
- Base model
- mistralai/Mistral-Small-24B-Base-2501
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 cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- 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 $0.05 in / $0.08 out per 1M tokens at Mistral 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 3 |
|---|---|---|---|---|---|
| Llama 3.1 8B InstructMeta | $0.055 | $0.05 | $0.08 | 200K | +0% |
| llama-3-8bMeta | $0.055 | $0.05 | $0.08 | 8.2K | +0% |
| GLM-4.6V-FlashZ.ai (Zhipu AI) | $0.0546 | $0.0218 | $0.218 | 128K | −1% cheaper |
| Qwen FlashAlibaba (Qwen) | $0.0543 | $0.022 | $0.216 | 1M | −1% cheaper |
| Qwen3-VL FlashAlibaba (Qwen) | $0.0542 | $0.022 | $0.215 | 262K | −2% cheaper |
| Llama 3.2 1b InstructMeta | $0.056 | $0.027 | $0.201 | 131K | +2% |
| Command R7BCohere | $0.0563 | $0.0375 | $0.15 | 128K | +2% |
| Gemma 3 12B ITGoogle | $0.0533 | $0.04 | $0.12 | 131K | −3% cheaper |
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 |