Model specification · Mistral
Mistral Small 3
mistralai/mistral-small-24b-instruct-2501
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...
SpecificationsReported values
- Context window
- 33K
- Maximum output
- 16K
- Architecture
- text->text
- Tokenizer
- Mistral
- Knowledge cutoff
- 2023-10-31
- Moderated
- No
- Input modalities
- text
- Output modalities
- text
Full pricingUSD where reported
| Price | Standard |
|---|---|
| Input | $0.050 / M |
| Output | $0.080 / M |
Benchmark indexesReported indexes
- Intelligence
- 6.7
- Coding
- —
- Agentic
- —
- Design Arena Elo
- —
Example workload costsStandard pricing only
| Workload | Input / output | Cache share | Estimated cost |
|---|---|---|---|
| Quick check | 10K / 1K × 1 | 0% | $0.00058 |
| Long analysis | 100K / 4K × 1 | 50% | $0.00532 |
| Workday | 20K / 2K × 1,000 | 30% | $1.16 |
More from MistralAll Mistral models
| Model | Context | Input / M | Output / M | Intel. |
|---|---|---|---|---|
| Mistral Large 4 | 1.0M | $0.680 | $2.09 | 38.4 |
| Mistral Medium 3.5 | 262K | $1.50 | $7.50 | 14.2 |
| Mistral Small 4 | 262K | $0.150 | $0.600 | 11.3 |
| Mistral Large 3 2512 | 262K | $0.500 | $1.50 | 9.3 |
| Mistral Medium 3.1 | 131K | $0.400 | $2.00 | 9.2 |
| Mistral Medium 3 | 131K | $0.400 | $2.00 | 9 |
| Devstral 2 2512 | 262K | $0.400 | $2.00 | 8.6 |
| Mistral Large 2407 | 131K | $2.00 | $6.00 | 7.6 |
| Saba | 33K | $0.200 | $0.600 | 6.5 |
| Ministral 3 14B 2512 | 262K | $0.200 | $0.200 | 6 |
| Mistral Large | 128K | $2.00 | $6.00 | 5.8 |
| Mixtral 8x22B Instruct | 66K | $2.00 | $6.00 | 5.7 |