GeniusRelay
EN中文Sign upConsole

Mistral: Mistral Small 4 119B Thinking

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

CompareAPIGet an API keyGet an API key

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.

Modalities

Text + Image → Text

Input / output price

$0.520 / $1.82 per 1M

Context

262K · max output 16K

Capabilities

ReasoningVisionTool callingLong contextOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.520
Output$1.82
Cached input$0.260

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00302
Per day
$1.51
Per month (30 days)
$45.24

Mistral Small 4 119B Thinking: input $0.52/M · output $1.82/M · cached input $0.26/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai-small-4-119b-2603:thinking", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to mistralai-small-4-119b-2603:thinking.

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

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Mistral Small 4 119B Thinking billed?
Input is $0.520 and output is $1.82 per million tokens; cached input is $0.260. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
262K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.