Mistral Medium Latest

mistral/mistral-medium-3.5

A chat model with a 262K-token context window, at $1.575 per million input tokens and $7.875 per million output tokens.

Details

Maker: mistral
Kind: Chat
Context window: 262,144 tokens
Max output: 256,000 tokens
Input: $1.575 per million tokens
Cached input: $0.1575 per million tokens, 90% off
Cache write: Same as input
Output: $7.875 per million tokens
Capabilities: Reasoning, tool use, vision
Takes: Text, image
Returns: Text
Zero data retention: Yes, on every provider
No training on requests: Yes, on every provider
Released: 2026-04-29
Newer model: mistral/mistral-large-4Released later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

Mistral's frontier-class multimodal model optimized for agentic and coding use cases.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-medium-3.5",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model