GPT-5 Nano
Fastest, most cost-efficient version of GPT-5.
Specs
- Context
- 400K
- Max output
- 128K
- Input price
- $0.05/ 1M tokens
- Output price
- $0.4/ 1M tokens
- Released
- 2025-08-07
Context
- Context window
- 400K
- Max input
- 272K
- Max output
- 128K
Pricing · USD / 1M tokens
- Input
- $0.05
- Output
- $0.4
- Cache read
- $0.005
- Cache write
- —
Modalities
- Input
- TextImage
- Output
- Text
API
- API types
Reasoning
- Reasoning
- Yes
- Levels
- —
Info
- Status
- Active
- Released
- 2025-08-07
- Knowledge cutoff
- 2024-05-31
Features
- Confirmed
How to call
1 provider
openaimodel = gpt-5-nanoreasoning = 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": "gpt-5-nano",
"object": "model",
"created": 1754524800,
"owned_by": "openai",
"name": "GPT-5 Nano",
"api": {
"types": [
"chat",
"responses",
"batch"
]
},
"limits": {
"context": 400000,
"input": 272000,
"output": 128000
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 0.05,
"output": 0.4,
"cache_read": 0.005,
"cache_write": null
},
"features": [
"tools",
"structured_output",
"streaming",
"caching",
"batch"
],
"info": {
"status": "active",
"release_date": "2025-08-07",
"knowledge_cutoff": "2024-05-31",
"description": "Fastest, most cost-efficient version of GPT-5.",
"docs": "https://developers.openai.com/api/docs/models/gpt-5-nano",
"verified_at": "2026-10-10"
}
}Official sources
4