xAI: grok-4.20-0309-non-reasoning

grok-4.20-0309-non-reasoning is a language model from xAI. It reasons step by step before it answers.

Price per 1M tokens: $2.00 / $4.00input / output
Cached input: $0.32per 1M tokens
Context: 200K tokens

Providers

1 provider ·

1 provider through partner hosts · from $1.31 in · $2.63 out

Per 1M tokens: the provider's own price.

A request picks by price (:floor) or by speed (provider.sort, :nitro), or sets a floor on tokens per second. How routing works

API

curl https://api.opencheap.si/v1/chat/completions \
  -H "Authorization: Bearer $OPENCHEAP_API_KEY" -H "Content-Type: application/json" \
  -d '{ "model": "opencheap/grok-4.20-0309-non-reasoning", "messages": [{ "role": "user", "content": "Hi" }] }'