Devstral 2 API

Model details

Context window

262K tokens

Max output

—

Input

Text

Output

Text

Capabilities

Streaming, JSON output

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• Devstral 2 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Devstral 2

Devstral 2 answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "devstral-2512",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "devstral-2512",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "devstral-2512",
  "input": "Hello"
}'

Use Devstral 2 in your tools

Every coding agent below has a setup guide. Set the model to devstral-2512.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from Mistral

Alternatives to Devstral 2

• SonarSonar for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Perplexity
• Qwen3.5 27BQwen3.5 27B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Alibaba
• Gemini 3.5 Flash LiteThe fastest, cheapest 3.5 model for high-throughput work.Google

Questions about this model

How much does the Devstral 2 API cost?

Devstral 2 costs $0.4 per 1M input tokens and $2 per 1M output tokens on Inferray. That is the list price, with no gateway fee on top.

Is there a free tier for Devstral 2?

No. You add credit and pay Devstral 2's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is Devstral 2 included in Token Plans?

No. Devstral 2 is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Devstral 2 in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to devstral-2512. The same key works in Codex, opencode, Cline, and other agents.

Does Devstral 2 support tool calling and vision?

Devstral 2 supports JSON output and streaming on Inferray. It does not take image input. It does not support tool calling.

Is it the real Devstral 2?

Yes. A request for devstral-2512 is answered by Devstral 2 from Mistral, billed at its published list price. Inferray never substitutes a different or smaller model.