Skip to content

Home Docs Model catalog

Overview Models Image, video & speech Coding tools Production API reference

Overview Models Image, video & speech Coding tools Production API reference

Sign in All models

Choose a model

Available models Image request builder

Chat models

Gemini chat GLM-5.3 GLM-5.3 Flash Qwen DeepSeek V4.1 / V4 Grok

grok-4.6ChatExamples verified 2026-09-25

Grok 4.6

The recommended Grok model, 500K context, reasoning_effort up to xhigh.

Official price: $2 / $6/ 1M tokensInput / output
Context window: 500K tokens500,000

Notes

On Chat Completions, completion_tokens excludes reasoning tokens; add reasoning_tokens when reconciling usage.
stop, presence_penalty, and frequency_penalty aren't supported.

Read the integration guideJSON Schema

Available groups

Grok Suite

Integration guide

Pricing

Official price in USD. Actual charge = official price × group multiplier.

Input: $2 / 1M tokens
Cached input: $0.50 / 1M tokens
Output: $6 / 1M tokens
Context over 200K: input ×2 · output ×2

Endpoints

POST/v1/chat/completions
POST/v1/responses

Same family

grok-4.20-multi-agent-0309 grok-4.20-0309-reasoning grok-4.5 grok-4.3

Prices come from the public catalog; limits come from specs exported from the gateway’s validation code. Actual charge = official price × group multiplier.