Mistral AI model product
Devstral Small 1.1
1 foundation model, with a 128k-token context window and support for structured outputs.
Updated Sep 8, 2026. Default version: Devstral Small 1.1
LLMBoard Score16.1Devstral Small 1.1
Coverage0%1 benchmark families
Context window128KTokens
Official input price$0.10Mistral API
Devstral Small 1.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Devstral Small 1.1 Benchmark Results
Benchmark scores for Devstral Small 1.1.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSWE-Bench Verified | Score53.60% | Rank94 | Participants113 | Percentile16.96% | EvidenceC | Evaluated |
Devstral Small 1.1 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Devstral Small 1.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.10 input, $0.30 output per 1M
- Official provider
- Mistral
- Lowest third-party
- From $0.10 input, $0.30 output per 1M via Merge Gateway
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMerge Gateway | Provider model IDmistral/devstral-small-2507 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.30 | Context128K | Updated |
| ProviderMistral | Provider model IDdevstral-small-2507 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.30 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Devstral Small 1.1 Runtime Performance
Provider-specific output speed and catalog latency for Devstral Small 1.1. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderMistral AI | Output Speed137.10 tok/s | Catalog Latency0.23 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Devstral Small 1.1 Specifications
Technical details for the model's default version.
- Version
- Devstral Small 1.1
- Released
- Jul 11, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 24B
- Context window
- 128K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Devstral Small 1.1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionDevstral Small 1.1 | Released | LLMBoard16.11 | Parameters24B | Context128K | Max output128K | Open weightsYes | LicenseApache 2.0 |
Models similar to Devstral Small 1.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Mistral Large 3
Mistral AI
MA
Mistral Small 3.2 24B
Mistral AI
MA
Magistral Medium
Mistral AI
MA
Magistral Small
Mistral AI
MA
Min istral 3
Mistral AI
MA
Pixtral Large
Mistral AI
What is Devstral Small 1.1?
Key information about Devstral Small 1.1 and its available data.
1 foundation model. 0 for research and commercial use.
Data as of 2026-09-08.
FAQ
Common questions about Devstral Small 1.1.
When was Devstral Small 1.1 released?
Devstral Small 1.1's default version was released on Jul 11, 2025.
How much does Devstral Small 1.1 cost?
Devstral Small 1.1's official API price is $0.10 per million input tokens and $0.30 per million output tokens via Mistral. The lowest tracked third-party offer starts at $0.10 input and $0.30 output via Merge Gateway.
Who created Devstral Small 1.1?
Devstral Small 1.1 was created by Mistral AI.
What is the context window for Devstral Small 1.1?
The default version has a 128K token context window.
Is Devstral Small 1.1 open weight?
Yes. The default version is marked as open weight under Apache 2.0.