GPT-5 Nano
Provider: OpenAI US Official API price
Scheduled for retirement on 2026-12-11.
Input price
$0.025
/ 1M tokens
Output price
$0.20
/ 1M tokens
Cache price
$0.0025
/ 1M tokens (read)
Batch API
$0.025 / $0.20
input / output per 1M tokens
Context
400K tokens
Max output 128K tokens
Overview
OpenAI's GPT-5 Nano is a budget reasoning model targeting ultra-low latency developer tools and high-frequency interactions.
Strengths
- Processes a 400,000 token context window
- Supports vision, function-calling, and JSON mode
- Features a 128,000 token maximum output limit
- Includes cached input pricing at $0.0025 per million tokens
Best use cases
- High-throughput developer tool automation
- Structured JSON data extraction tasks
- Rapid low-latency interactive applications
Pricing position
Input pricing of $0.025/M tokens undercuts the older GPT-5.4 Nano and GPT-4.1 Nano models priced at $0.1/M.
Caveats
Offers no free tier and has lower reasoning depth than larger variants.
Notes drafted by an LLM from the figures on this page (2026-11-12) and rewritten when the price changes.
Key facts
- Price basis
- Official API price
- Max output
- 128K tokens
- Knowledge cutoff
- 2024-05-31
- Listed on OpenRouter
- 2025-08-07
- Tracked since
- 2026-05-07
- Last updated
- 2026-11-12
Features
Image inputFunction callingJSON outputReasoning
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.01 |
| 1M (small app) | 1 | 0.5 | $0.13 |
| 10M (mid scale) | 10 | 5 | $1.25 |
| 100M (large) | 100 | 50 | $12.50 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from OpenAI
Similar-priced models
Source: OpenRouter API (openai/gpt-5-nano)