Skip to content

Devstral

Mistral AI

At a glance

Price per 1M tokens (input)
$0.40
Price per 1M tokens (output)
$2.00
Context
256,000 tokens
Free access
yes (see below)

Refreshed daily; data verified November 16, 2026. Published August 12, 2026, last price change September 18, 2026.

Devstral by Mistral AI is designed for developers and technical teams building applications that need structured interaction with external systems. It supports tool calling, which allows the model to invoke functions or APIs to retrieve data or perform actions, and it performs step-by-step reasoning to break down complex problems before answering. Mistral AI's approach emphasizes efficient, open-weight models that can be deployed in controlled environments with transparent architecture. The model is well suited for coding assistance, agent-based workflows, and multi-step analytical tasks where reliability and tool integration matter more than general conversation.

Specifications & pricing

Input (per 1M tokens)$0.40
Output (per 1M tokens)$2.00
Cache read (per 1M tokens)$0.04
Context window256,000 tokens
Max output256,000 tokens
Capabilitiestool calling, reasoning

LiteLLM community dataset (MIT), verified November 16, 2026. Official Mistral AI pricing.

What Devstral would cost on your workload — run it through the cost calculator →

Price history

DateInput / 1MOutput / 1M
August 9, 2026 (first record)$0.40$2.00
September 18, 2026$0.40$2.00

Where to try Devstral for free

  • Mistral AI offers a free chat — Le Chat (free plan). A vendor's free chat may run a different model from the same family — the exact model is not guaranteed.

Frequently asked questions

What is Devstral good for?+

Devstral is suited for software development tasks, including code generation, debugging, and building agents that call external tools or APIs. Its step-by-step reasoning helps with multi-stage problems such as system design or troubleshooting.

How do I get started with Devstral?+

Access the model through Mistral AI's platform or supported inference providers, then integrate it using standard chat completions with tool definitions. You will need an API key and a basic understanding of function schemas to enable tool calling.

How does Devstral differ from other Mistral models?+

Devstral is optimized for developer workflows and tool use, while sibling models may prioritize general conversation, multilingual tasks, or different deployment sizes. Choose Devstral when your application needs reliable function calling and structured reasoning.

What are the limitations of Devstral?+

The model depends on clearly defined tool schemas and may produce incorrect calls if instructions are ambiguous. It is not a replacement for human review in safety-critical systems, and its knowledge is bounded by its training data.

Compare with others

Org chart: how to move your company onto AI

Org chart: how to move your company onto AI

A practical map: which company roles and processes AI agents can take over, where to start, and in what order to roll it out.