Grok 4 Fast (Reasoning)
Specs
- Context
- 2M
- Max output
- —
- Input price
- $0.2/ 1M tokens
- Output price
- $0.5/ 1M tokens
- Released
- —
Context
- Context window
- 2M
- Max input
- —
- Max output
- —
Pricing · USD / 1M tokens
- Input
- $0.2
- Output
- $0.5
- Cache read
- $0.05
- Cache write
- —
Modalities
- Input
- TextImage
- Output
- Text
API
- API types
Reasoning
- Reasoning
- Yes
- Levels
- —
Info
- Status
- Retired
- Released
- —
- Knowledge cutoff
- —
Features
- Confirmed
How to call
1 provider
xaimodel = grok-4-fast-reasoning
chat
POSThttps://api.x.ai/v1/chat/completions
JSON
Standard format
{
"id": "grok-4-fast-reasoning",
"object": "model",
"created": null,
"owned_by": "xai",
"name": "Grok 4 Fast (Reasoning)",
"api": {
"types": [
"chat"
]
},
"limits": {
"context": 2000000,
"input": null,
"output": null
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 0.2,
"output": 0.5,
"cache_read": 0.05,
"cache_write": null
},
"features": [
"tools",
"structured_output",
"caching"
],
"info": {
"status": "retired",
"release_date": null,
"knowledge_cutoff": null,
"description": null,
"docs": "https://docs.x.ai/developers/migration/may-15-retirement",
"verified_at": "2026-10-11"
}
}Official sources
2