MistralReleased on Jul 11, 2025

Devstral Small 1.1: API Pricing, Context Window & Benchmarks

Devstral Small 1.1 is a language model from Mistral, released in July 2025.

Devstral Small 1.1 (also called devstral-small-2507) is based on the Mistral-Small-3.1 foundation model and contains approximately 24 billion parameters. It supports a 128k token context window, which allows it to handle multi-file code

Input
Text
Output
Text

Devstral Small 1.1 benchmarks

Rankings

Quality Tracker

Devstral Small 1.1 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Tue Jul 21 2026
Notice missing or incorrect data?

Devstral Small 1.1 pricing

Providers

Devstral Small 1.1 starts at $0.100 per million input tokens and $0.300 per million output tokens via Mistral AI.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
Mistral AI logoMistral AI
$0.100$0.300128.0K/128.0K
/0.23
137/
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

Devstral Small 1.1 model size

Devstral Small 1.1 has 24 billion parameters. See how it compares to other models in the same parameter range.

Parameters
24B
Medium (10–30B)
24B
1B7B70B405B

Devstral Small 1.1 context window

Input and output token limits for Devstral Small 1.1, plus how it ranks on long-context understanding.

InputOutput
128Ktokens
128Ktokens
192 pages of text
128K
8K128K1M

Devstral Small 1.1 API

Available from the model provider

Devstral Small 1.1 has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Devstral Small 1.1 examples

Recent arena outputs from Devstral Small 1.1, picked from the highest-ranked matchups.

Devstral Small 1.1 license

Devstral Small 1.1 is released under the Apache 2.0 license, which permits commercial use, has 24.0B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
24.0B

Apache License 2.0 - allows commercial use

Devstral Small 1.1 resources

Official sources for Devstral Small 1.1: api documentation, official launch post, model weights.

Devstral Small 1.1 vs other models

The most-compared alternatives to Devstral Small 1.1 are Claude 3.5 Sonnet, LongCat-Flash-Lite, Nemotron 3 Super (120B A12B). Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Devstral Small 1.1

Models ranked just above and below Devstral Small 1.1 by LLM Stats score.

 

Claude 3.5 Sonnet

Score pending
 

LongCat-Flash-Lite

Score pending
 

Nemotron 3 Super (120B A12B)

Score pending
 

o3-mini

Score pending

FAQ

Common questions about Devstral Small 1.1.

When was Devstral Small 1.1 released?

Devstral Small 1.1 was released on July 11, 2025 by Mistral. This is the official Devstral Small 1.1 release date tracked on LLM Stats.

How much does Devstral Small 1.1 cost?

Devstral Small 1.1 pricing starts at $0.10 per million input tokens and $0.30 per million output tokens via Mistral AI, the lowest price among tracked providers.

Is Devstral Small 1.1 available via API?

Yes, Devstral Small 1.1 is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is Devstral Small 1.1?

Devstral Small 1.1 has 24 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Devstral Small 1.1?

Devstral Small 1.1 was created by Mistral.

What is the license for Devstral Small 1.1?

Devstral Small 1.1 is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

What is Devstral Small 1.1 latency?

Devstral Small 1.1 p95 time to first token is 0.23 seconds via Mistral AI over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use Devstral Small 1.1?

Devstral Small 1.1 is available through 1 provider including Mistral AI.

Where is the Devstral Small 1.1 paper or technical report?

Devstral Small 1.1 has a paper or technical report available at https://huggingface.co/mistralai/Devstral-Small-2507. Use that source for architecture, training, release and evaluation details.

What models should I compare Devstral Small 1.1 against?

Common Devstral Small 1.1 comparisons include Devstral Small 1.1 vs Claude 3.5 Sonnet, Devstral Small 1.1 vs LongCat-Flash-Lite, Devstral Small 1.1 vs Nemotron 3 Super (120B A12B). Compare them side by side for benchmark scores, pricing, context window, latency and API availability.