o4-mini
Fast, cost-efficient reasoning model, succeeded by GPT-5 Mini.
Specs
- Context
- 200K
- Max output
- 100K
- Input price
- $1.1/ 1M tokens
- Output price
- $4.4/ 1M tokens
- Released
- 2025-04-16
Context
- Context window
- 200K
- Max input
- —
- Max output
- 100K
Pricing · USD / 1M tokens
- Input
- $1.1
- Output
- $4.4
- Cache read
- $0.275
- Cache write
- —
Modalities
- Input
- TextImage
- Output
- Text
API
- API types
Reasoning
- Reasoning
- Yes
- Levels
- —
Info
- Status
- Deprecated
- Released
- 2025-04-16
- Knowledge cutoff
- 2024-06-01
Features
- Confirmed
How to call
1 provider
openaimodel = o4-minireasoning = reasoning.effort
chat
POSThttps://api.openai.com/v1/chat/completions
responses
POSThttps://api.openai.com/v1/responses
batch
POSThttps://api.openai.com/v1/batches
JSON
Standard format
{
"id": "o4-mini",
"object": "model",
"created": 1744761600,
"owned_by": "openai",
"name": "o4-mini",
"api": {
"types": [
"chat",
"responses",
"batch"
]
},
"limits": {
"context": 200000,
"input": null,
"output": 100000
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 1.1,
"output": 4.4,
"cache_read": 0.275,
"cache_write": null
},
"features": [
"tools",
"structured_output",
"streaming",
"caching",
"batch"
],
"info": {
"status": "deprecated",
"release_date": "2025-04-16",
"knowledge_cutoff": "2024-06-01",
"description": "Fast, cost-efficient reasoning model, succeeded by GPT-5 Mini.",
"docs": "https://developers.openai.com/api/docs/models/o4-mini",
"verified_at": "2026-10-11"
}
}Official sources
5