Mistral Small 3.2 24B
by Mistral AIChat
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.
- Context
- 32.8K tokens
- Max output
- 26,214 tokens
- Parameters
- 24B total
- Released
- 2025-06-20
- Weights
- Open
- Licence
- apache-2.0
mistral/mistral-small-3-2-24b-instruct-2506 · also seen as mistral-small-3-2-24b-instruct, mistralai/mistral-small-3.2-24b-instruct, mistralai/Mistral-Small-3.2-24B-Instruct-2506
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-06-20
- Weights
- Opennot gated
- License
- apache-2.0
- Input
- Text, Image
- Output
- Text
- Context window
- 32,768 max across endpoints
- Max output
- 26,214
- Providers
- 10 + 4 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.075–$0.330 in · $0.200–$0.456 out per 1M tokens · 9 of 10 providers have a comparable price
More details
- Last updated
- 2026-06-11
- Knowledge cutoff
- 2025-03
- Weights link
- Hugging Face · mistralai/Mistral-Small-3.2-24B-Instruct-2506
- Parameters
- 24B total
- Base model
- mistralai/Mistral-Small-3.1-24B-Base-2503
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 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 $0.075 in / $0.20 out per 1M tokens at Mistral on every data refresh since then.
Tracked from 19 Oct 2026, the earliest refresh this model's headline price can be rebuilt from. 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 3.2 24B |
|---|---|---|---|---|---|
| MiniMax-M2.7MiniMax | $0.12 | $0.08 | $0.32 | 205K | +0% |
| Doubao Seed 2.0 MiniByteDance Seed | $0.122 | $0.0493 | $0.485 | 256K | +2% |
| Qwen3.5 35B-A3BAlibaba (Qwen) | $0.122 | $0.0564 | $0.451 | 262K | +2% |
| Qwen2.5 7B InstructAlibaba (Qwen) | $0.117 | $0.10 | $0.20 | 131K | −3% cheaper |
| UI-TARS 7BByteDance Seed | $0.117 | $0.10 | $0.20 | 128K | −3% cheaper |
| LFM2.5-2.6BLiquid AI | $0.117 | $0.10 | $0.20 | 128K | −3% cheaper |
| Muse Spark 1.3 ContributorMeta | $0.117 | $0.10 | $0.20 | 1.05M | −3% cheaper |
| Reka Flash 3Reka | $0.117 | $0.10 | $0.20 | 65.5K | −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 |