grok-code-fast

StreamingTool callingVisionReasoningJSON mode

Integration guide

Overview

grok-code-fast is available on MAX through the OpenAI-compatible API.

Pricing

Official list prices: token prices are per 1M tokens.

Input ≤ 200,000 tokens

Input: $1
Output: $2
Cache read: $0.2

Input > 199,999 tokens

Input: $2
Output: $4
Cache read: $0.4

Tier	Input	Output	Cache read
Input ≤ 200,000 tokens	$1	$2	$0.2
Input > 199,999 tokens	$2	$4	$0.4

This model uses tiered pricing: the tier is chosen by the total input length of each request.

Cache read applies to prompt tokens served from the prompt cache; cache write applies to tokens written into it.

Example request

curl https://api.link-io.cloud/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-code-fast",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'