GPT-5 Nano
GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.
- Input price
- $0.045list $0.0510% off
- Output price
- $0.36list $0.4010% off
- Context
- 400K
- Max output
- 128K
- Capability
- 139 (#76 of 82)
- Human preference
- 1320
- 30-day uptime
- —
- Released
- 2025-08-08
- Knowledge cutoff
- 2024-05-30
Providers
This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].
- SuccessTTFT
- Azure AI FoundryGlobal——
- OpenAIUnited States——
Pricing
Prices for this model. Each request is billed at these prices, whichever provider serves it.
| Item | Standard | Standard Discount | Batch | Batch Discount | Price | Price Discount | |||
|---|---|---|---|---|---|---|---|---|---|
| Inputper 1M tokens | $0.045 | list $0.05 | 10% off | $0.0225 | list $0.025 | 10% off | — | ||
| Outputper 1M tokens | $0.36 | list $0.40 | 10% off | $0.18 | list $0.20 | 10% off | — | ||
| Cache readper 1M tokens | $0.0045 | list $0.005 | 10% off | $0.002252 | list $0.0025 | 10% off | — | ||
| Web searchper request | — | — | $0.0126 | list $0.014 | 10% off | ||||
| Estimated cost of common use (500 output tokens each) | |||||||||
| One chat message3K input tokens | $0.000316 | — | — | ||||||
| Agent first turn100K tokens of context, none cached | $0.00468 | — | — | ||||||
| Each later agent turncontext read from cache, plus 2K new tokens | $0.000724 | — | — | ||||||
| 20-turn agent taskfirst turn plus 19 more | $0.0184 | — | — | ||||||
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text