hide.st

Mistral Small 4 119B Thinking

mistralai/mistral-small-4-119b-2603:thinking

Mistral Small 4 with reasoning enabled (reasoning_effort=high). A hybrid MoE model with deep step-by-step reasoning for complex prompts, coding, and multi-step problem solving.

  • Vision
  • Reasoning
  • Tool calling
  • Structured output

Pricing

Includes our margin. Charged per request from your balance.

Input
$0.44 per 1M tokens
Output
$1.54 per 1M tokens
Typical message
$0.0018

Details

Provider
Mistral
Context
262K tokens
Max output
16K tokens
Added
Mar 17, 2026
Reasoning effort
none, high

Use it from the API

Replace $HIDE_API_KEY with a key from the Developers page. Base URL https://hide.st/api/v1.

curl https://hide.st/api/v1/chat/completions \
  -H "Authorization: Bearer $HIDE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-small-4-119b-2603:thinking",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Search

Search pages, chats and models