xAI
Grok models — fast inference with large 2M context and low hallucination
API Configuration
| API Type | openai-completions |
| Base URL | https://api.x.ai/v1 |
| Auth Mode | api_key |
| Auth Keys | XAI_API_KEY — API Key — obtain from https://console.x.ai/ |
| Regions | us |
| Default Model | grok-4.20-beta-0309-reasoning |
| Status | active |
Pricing
Pay-as-you-go per token. Free tier available with rate limits. See docs.x.ai/docs/models for pricing.
Getting Started
Sign up at console.x.ai, add a payment method, then create an API key.
Models (4)
| Model | Context | Max Output | Pricing | Features |
|---|---|---|---|---|
Grok 4.20 Beta (Reasoning)grok-4.20-0309-reasoning | 2.0M | 131K | Input $2/M, output $6/M. | |
Grok 4.20 Beta (Non-Reasoning)grok-4.20-0309-non-reasoning | 2.0M | 131K | Input $2/M, output $6/M. | |
Grok 4-1 Fast (Reasoning)grok-4-1-fast-reasoning | 2.0M | 131K | Input $0.20/M, output $0.50/M. | |
Grok 4-1 Fast (Non-Reasoning)grok-4-1-fast-non-reasoning | 2.0M | 131K | Input $0.20/M, output $0.50/M. |