Devstral Small 1.1
Provider: Mistral AI EU
Overview
Devstral Small 1.1 is a mid-tier model from Mistral AI, designed for efficient general-purpose workloads. It offers a large context window and specialized capabilities for structured interactions. This model targets developers needing robust function-calling and JSON mode support.
Strengths
- Provides a generous 131072-token context window for handling extensive inputs.
- Supports reliable function-calling for robust tool integration in applications.
- Offers JSON mode for consistent and structured output generation.
- Features a very low cache read price, optimizing costs for repeated queries.
- Input pricing is competitive with similarly-tiered models like Gemini Flash and GPT-4.1 Nano.
Best use cases
- Summarizing and analyzing large documents or extensive codebases.
- Developing AI agents that interact with external APIs via function calls.
- Extracting structured data from unstructured text using JSON mode.
- Building advanced chatbots with extended memory and complex multi-turn conversations.
- Rapid prototyping of applications requiring reliable structured outputs.
Pricing position
Devstral Small 1.1 is priced at $0.10/M for input and $0.30/M for output, placing it on the higher end among Mistral AI's 'Small' models compared to Mistral Small 3 and Mistral Small 3.2 24B. Its input pricing aligns exactly with several similarly-tiered peers such as Google's Gemini Flash models and OpenAI's GPT-4.1 Nano. Notably, its output price of $0.30/M is more cost-effective than these same peers which typically charge $0.40/M for output.
Caveats
A notable limitation is the unknown maximum output token limit, which could impact use cases requiring very long responses. For simpler, less demanding tasks, other Mistral AI models such as Mistral Nemo or Mistral Small 3 offer significantly lower input and output pricing. Additionally, there is no free tier available for this model, and the data does not specify any advanced multimodal capabilities like vision or audio.
Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.
Key facts
- Max output
- Unknown
- Tracked since
- 2026-05-08
- Last updated
- 2026-05-31
Features
Price history
- 2026-05-31 No longer listed
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.03 |
| 1M (small app) | 1 | 0.5 | $0.25 |
| 10M (mid scale) | 10 | 5 | $2.50 |
| 100M (large) | 100 | 50 | $25.00 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Mistral AI
Similar-priced models
Source: OpenRouter API