LLM Reference
xAI Console

Using Grok 4 Fast Non-Reasoning on xAI Console

Implementation guide · Grok 4 · xAI

Serverless

xAI Console exposes Grok 4 Fast Non-Reasoning through model ID grok-4-fast-non-reasoning. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-10. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at xAI Console and generate an API key.
  2. 2
    Use the xAI Console SDK or REST API to call grok-4-fast-non-reasoning — see the documentation for request format.
  3. 3
    You'll be billed $1.25/1M input, $2.50/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See xAI Console documentation for integration details.

Pricing on xAI Console

TypePrice (per 1M)
Input tokens$1.25
Output tokens$2.50

Capabilities

VisionMultimodalReasoning

About Grok 4 Fast Non-Reasoning

Grok 4 Fast Non-Reasoning is a September 2025 xAI model retiring on 2026-05-15; use Grok 4.3 for current API work.

Full model details →

Model Specs

Released2025-09-01
Context2m
ArchitectureDecoder Only

More Models on xAI Console

Grok 4Grok 4.20Grok 4.3Grok 4.20 Multi-AgentGrok 4.1 FastGrok 4 Fast Reasoning
All models on xAI Console →

Also available on(2)

Microsoft FoundryInceptron
Compare all providers →

Provider

xAI Console
xAI Console

xAI

Burlingame, California, United States