Model Library
MistralReleased July 10, 2025Devstral Small
Mistral · Released July 10, 2025
Intelligence score
9
At a glance
- Intelligence
- 9
- Speed
- 70.2tokens/sec
- Latency
- 1.13stime to first token
- Input price
- $0.10per 1M tokens
- Output price
- $0.30per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 24billions
Summary
Comparison summary
Devstral Small (Jul '25) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6). Devstral Small (Jul '25) generates output at 70.2 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 102.7 t/s). Devstral Small (Jul '25) costs $0.10 per 1M input tokens (better than average, median: $0.15) and $0.30 per 1M output tokens (better than average, median: $0.32), based on Mistral's API.
Specifications
Technical specifications
| Model name | Devstral Small |
|---|---|
| Provider | Mistral |
| Release date | July 10, 2025 |
| Intelligence score | 9 |
| Speed | 70.2 tokens/sec |
| Latency (TTFT) | 1.13s |
| Input price | $0.10 / 1M tokens |
| Output price | $0.30 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 24B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: devstral-small |
Pricing
Token prices
Price per 1M tokens
Devstral Small, as listed in the catalog record
- Input$0.10
- Output$0.30
| Token type | Price per 1M |
|---|---|
| Input | $0.10 |
| Output | $0.30 |
Model Intelligence legacy profile: devstral-small
FAQ · 19
Frequently asked questions
Devstral Small (Jul '25) was released on July 10, 2025.
Devstral Small (Jul '25) was created by Mistral.
Devstral Small (Jul '25) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 6).
Devstral Small (Jul '25) generates output at 70.2 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 102.7 t/s).
Devstral Small (Jul '25) has a time to first token (TTFT) of 1.13s (based on Mistral's API), which is better than average compared to other open weight non-reasoning models of similar size (median: 1.54s).
Devstral Small (Jul '25) costs $0.10 per 1M input tokens (better than average, median: $0.15) and $0.30 per 1M output tokens (better than average, median: $0.32), based on Mistral's API.
Devstral Small (Jul '25) costs $0.10 per 1M input tokens and $0.30 per 1M output tokens (based on Mistral's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.12 per 1M tokens. Pricing may vary by provider.
No, Devstral Small (Jul '25) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Devstral Small (Jul '25) supports text input.
Devstral Small (Jul '25) supports text output.
No, Devstral Small (Jul '25) does not support image input. It can only process text.
No, Devstral Small (Jul '25) is not multimodal. It only supports text input.
Devstral Small (Jul '25) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Devstral Small (Jul '25) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Devstral Small (Jul '25) has 24 billion parameters.
Devstral Small (Jul '25) is released under the Apache 2.0 license. This license allows commercial use.
Devstral Small (Jul '25) achieves a score of 9 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Devstral Small (Jul '25) is available via API through 1 provider.
Devstral Small (Jul '25) is available through 1 API provider.