Mistral Medium 3.5 API

Model details

Context window

262K tokens

Max output

—

Input

Text, images

Output

Text

Capabilities

Vision, Tool calling, Streaming, JSON output

Interfaces

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

Why teams pick it

• Mistral Medium 3.5 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call Mistral Medium 3.5

Mistral Medium 3.5 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": "mistral-medium-3-5",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistral-medium-3-5",
  "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": "mistral-medium-3-5",
  "input": "Hello"
}'

Use Mistral Medium 3.5 in your tools

Every coding agent below has a setup guide. Set the model to mistral-medium-3-5.

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

More from Mistral

Alternatives to Mistral Medium 3.5

• Qwen3.8 MaxAlibaba's flagship MoE, built for coding and long-horizon agents.Alibaba
• Fugu MaxFugu Max for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Sakana AI
• Grok 4.20 Beta Non-Reasoning (0309)Grok 4.20 Beta Non-Reasoning (0309) for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.xAI

Questions about this model

How much does the Mistral Medium 3.5 API cost?

Mistral Medium 3.5 costs $1.5 per 1M input tokens and $7.5 per 1M output tokens on Inferray. That is the list price, with no gateway fee on top.

Is there a free tier for Mistral Medium 3.5?

No. You add credit and pay Mistral Medium 3.5'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 Mistral Medium 3.5 included in Token Plans?

No. Mistral Medium 3.5 is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use Mistral Medium 3.5 in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to mistral-medium-3-5. The same key works in Codex, opencode, Cline, and other agents.

Does Mistral Medium 3.5 support tool calling and vision?

Mistral Medium 3.5 supports tool calling, image input, JSON output and streaming on Inferray.

Is it the real Mistral Medium 3.5?

Yes. A request for mistral-medium-3-5 is answered by Mistral Medium 3.5 from Mistral, billed at its published list price. Inferray never substitutes a different or smaller model.