GPT-5.4 Nano API pricing
As of October 21, 2026, OpenAI GPT-5.4 Nano costs $0.20 per million input tokens and $1.25 per million output tokens on OpenAI's own API, with cached input at $0.02 per million.
GPT-5.4 Nano benchmarks and specs · Every OpenAI model's price
- Input, per million tokens$0.20
- Output, per million tokens$1.25
- Cached input, per million$0.02
- 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 | $0.0008 | $0.825 | Yes |
| Repository review | 50K input + 3K output tokens | $0.014 | $13.75 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.052 | $52.50 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.14 | $140.00 |
Price history
We have read OpenAI's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $0.20 input, $1.25 output
Cheaper models as good as GPT-5.4 Nano
Models within two points of GPT-5.4 Nano or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- Qwen3.5-Flash$0.26 Overall 50.1 against 45.7 · 79% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 45.7 · 78% cheaper output
- DeepSeek V4 Flash 0731$0.28 Overall 55.2 against 45.7 · 78% cheaper output
- MiMo-V2.5$0.336 Overall 50.7 against 45.7 · 73% cheaper output
- Claude Haiku 5.5$0.50 Overall 67.6 against 45.7 · 60% cheaper output
GPT-5.4 Nano pricing questions
- How much does GPT-5.4 Nano cost per million tokens?
- $0.20 per million input tokens and $1.25 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does GPT-5.4 Nano support prompt caching?
- Yes. OpenRouter lists cached input at $0.02 per million tokens, against $0.20 for uncached input.
- Is there a cheaper model as good as GPT-5.4 Nano?
- Qwen3.5-Flash scores 50.1 on the LLMBenchmark Index, within two points of GPT-5.4 Nano or above it, and costs $0.26 per million output tokens.
- Has the price of GPT-5.4 Nano changed?
- Not since we started recording it daily on October 21, 2026.