Grok 4.20 (reasoning)

Reasoning-mode of 4.20. Same price tier as 4.3 with integrated Chain of Thought.

ChatxAI1M tokens$1.3626 / $2.7251 · 1M

xai/grok-4.20-reasoning

Context
1M tokens
Completion cap
—
Tools
Yes
JSON
Yes

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xai/grok-4.20-reasoning",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Grok 4.20 (reasoning)?
Reasoning-mode of 4.20. Same price tier as 4.3 with integrated Chain of Thought. Grok 4.20 (reasoning) runs on the Geek Hub API (OpenAI-compatible). Model id: xai/grok-4.20-reasoning.
Is Grok 4.20 (reasoning) free?
No. Input is $1.3626 per 1M tokens and output is $2.7251 per 1M tokens on Geek Hub (markup included).
What is the context length of Grok 4.20 (reasoning)?
Grok 4.20 (reasoning) has a 1M tokens context window.
Does Grok 4.20 (reasoning) support tool calling and structured outputs?
Grok 4.20 (reasoning) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

More models from xAI