GPT-5 Nano API pricing
As of October 21, 2026, OpenAI GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens through OpenRouter, with cached input at $0.005 per million.
GPT-5 Nano benchmarks and specs · Every OpenAI model's price
- Input, per million tokens$0.05
- Output, per million tokens$0.40
- Cached input, per million$0.005
- Context window400K tokens
- Max output128K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0003 | $0.250 | Yes |
| Repository review | 50K input + 3K output tokens | $0.0037 | $3.70 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.014 | $14.00 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.109 | $109.41 |
Price history
We read this price every day and have since October 15, 2026. It has not changed yet; any change will be listed here with its date.
- October 15, 2026 First recorded: $0.05 input, $0.40 output
Cheaper models as good as GPT-5 Nano
Models within two points of GPT-5 Nano or above it on the Artificial Analysis Intelligence Index, with a lower output price. Cheapest first.
- Ling 3.0 Flash$0.063 Overall 20.1 against 13.0 · 84% cheaper output
- Qwen3.5-9B$0.13 Overall 13.3 against 13.0 · 68% cheaper output
- Mercury 2.5$0.15 Overall 12.3 against 13.0 · 63% cheaper output
- Ling 3.0 Flash VL$0.18 Overall 24.6 against 13.0 · 55% cheaper output
- DeepSeek V4 Flash 0423$0.182 Overall 24.4 against 13.0 · 55% cheaper output
GPT-5 Nano pricing questions
- How much does GPT-5 Nano cost per million tokens?
- $0.05 per million input tokens and $0.40 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does GPT-5 Nano support prompt caching?
- Yes. OpenRouter lists cached input at $0.005 per million tokens, against $0.05 for uncached input.
- Is there a cheaper model as good as GPT-5 Nano?
- Ling 3.0 Flash scores 20.1 on the Artificial Analysis Intelligence Index, within two points of GPT-5 Nano or above it, and costs $0.063 per million output tokens.
- Has the price of GPT-5 Nano changed?
- Not since we started recording it daily on October 15, 2026.