GPT-5 nano API pricing
Standard tier, blended at 3:1 input to output: $0.138 per million tokens.
OpenAI charges $0.050 per million input tokens and $0.400 per million output tokens for GPT-5 nano. It is sold in 4 forms, from $0.069 to $0.138 blended; the table below shows what each costs against standard. 2 of the models nearest it in price are cheaper on a blended basis.
Every tier of GPT-5 nano
Blended at 3:1 input to output. The last column compares each against the standard tier.
| Source | ||||||||
|---|---|---|---|---|---|---|---|---|
| Standard Standard | gpt-5-nano | OpenAI | $0.050 | $0.400 | $0.005 | $0.138 | Standard | ↗ |
| Standard | gpt-5-nano | OpenRouter | $0.050 | $0.400 | $0.005 | $0.138 | Same | ↗ |
| Dated snapshot | gpt-5-nano-2025-08-07 | OpenAI | $0.050 | $0.400 | $0.005 | $0.138 | Same | ↗ |
| Batch | gpt-5-nano:batch | OpenRouter | $0.025 | $0.200 | $0.0025 | $0.069 | −50% | ↗ |
Prices last checked: . Methodology
Which tier to use
What each costs against standard in our data, and the job it is for.
Batch
The batch tier (gpt-5-nano:batch) is 50% cheaper than standard. Batch requests are queued and answered asynchronously, typically within 24 hours, so it suits work nobody is waiting on: evaluations, back-fills, bulk classification and tagging. Anything a user is waiting on belongs on the standard tier.
Dated snapshots
One dated snapshot (gpt-5-nano-2025-08-07) is listed at the same price as standard. A snapshot pins the model to one release, while the undated name moves to newer releases when the vendor updates it. Pin a snapshot in production when your prompts depend on exact output; use the undated name to pick up improvements automatically.
Direct or through a reseller
Through OpenRouter, gpt-5-nano is the same price as buying direct. A reseller is worth it for one bill across vendors and automatic fallback; buy direct for the vendor's own batch, caching and rate-limit terms.
Against the models nearest in price
Standard tiers, blended at a 3:1 input to output ratio.
| Source | ||||||
|---|---|---|---|---|---|---|
| GPT-5 nano This model | OpenAI | $0.050 | $0.400 | 272,000 | $0.138 | ↗ |
| Llama 4 Scout | OpenRouter | $0.100 | $0.300 | 1,310,720 | $0.150 | ↗ |
| Llama 3.3 70B Instruct | OpenRouter | $0.100 | $0.320 | 131,072 | $0.155 | ↗ |
| GPT-4.1 nano | OpenAI | $0.100 | $0.400 | 1,047,576 | $0.175 | ↗ |
| Gemini 2.5 Flash-Lite | Google AI | $0.100 | $0.400 | 1,048,576 | $0.175 | ↗ |
| Claude Haiku 5.5 | Anthropic | $0.100 | $0.500 | 1,000,000 | $0.200 | ↗ |
| Llama 3 8B Chat Hf | Together AI | $0.200 | $0.200 | 8,192 | $0.200 | ↗ |
| Llama 3.2 1B Instruct | Together AI | $0.060 | $0.060 | 131,072 | $0.060 | ↗ |
| Llama 3.2 3B Instruct | Together AI | $0.060 | $0.060 | 131,072 | $0.060 | ↗ |
Prices last checked: . Methodology
Questions
How much does GPT-5 nano cost per million tokens?
$0.050 per million input tokens and $0.400 per million output tokens, with cached input at $0.005. At a 3:1 input to output mix that blends to $0.138. Checked 28 Oct 2026.
How much cheaper is GPT-5 nano through the Batch API?
gpt-5-nano:batch costs $0.025 in and $0.200 out per million tokens, 50% cheaper than standard, in exchange for asynchronous delivery.
What would GPT-5 nano cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $10.20 a month on the standard tier, or $5.10 through batch.
What is the context window for GPT-5 nano?
272,000 tokens of input, with up to 128,000 tokens of output.
Llama 4 Scout · Llama 3.3 70B Instruct · GPT-4.1 nano · Gemini 2.5 Flash-Lite · Claude Haiku 5.5 · All OpenAI models · Cost calculator