GPT-5 nano API pricing
GPT-5 nano costs $0.05 per million input tokens and $0.40 per million output tokens on OpenAI's API. Input read back from the prompt cache costs $0.005 per million. A typical support chat reply (1,500 tokens in, 300 out) costs about $0.00019.
| Input | $0.05 per 1M tokens |
|---|---|
| Output | $0.40 per 1M tokens |
| Cached input | $0.005 per 1M tokens |
| Context window | 400K tokens |
| Reads | text, images, files |
| Released | August 7, 2025 |
What requests cost on GPT-5 nano
The same four requests on every page, so you can compare models directly.
| Request | Tokens in / out | Per request | Per 10,000 requests |
|---|---|---|---|
| A support chat reply | 1,500 / 300 | $0.00019 | $1.95 |
| Summarizing a 10-page document | 6,000 / 500 | $0.00050 | $5.00 |
| Sorting a support ticket into a category | 400 / 5 | $0.000022 | $0.22 |
| A question about a 120-page document | 60,000 / 800 | $0.0033 | $33.20 |
Other OpenAI models
| Model | Input | Output | A chat reply | Next to GPT-5 nano |
|---|---|---|---|---|
| GPT-4.1 nano | $0.10 | $0.40 | $0.00027 | 38% more |
| GPT-6 Luna | $0.10 | $0.50 | $0.00030 | 54% more |
| GPT-4o mini | $0.15 | $0.60 | $0.00040 | 2.1x the price |
| GPT-5.6 Luna | $0.20 | $1.20 | $0.00066 | 3.4x the price |
| GPT-5.4 nano | $0.20 | $1.25 | $0.00068 | 3.5x the price |
| GPT-5 mini | $0.25 | $2 | $0.00097 | 5.0x the price |
| GPT-4.1 mini | $0.40 | $1.60 | $0.0011 | 5.5x the price |
| GPT-5.4 mini | $0.75 | $4.50 | $0.0025 | 13x the price |
| o4-mini | $1.10 | $4.40 | $0.0030 | 15x the price |
| o3-mini | $1.10 | $4.40 | $0.0030 | 15x the price |
| GPT-5.1 | $1.25 | $10 | $0.0049 | 25x the price |
| GPT-5 | $1.25 | $10 | $0.0049 | 25x the price |
| GPT-4.1 | $2 | $8 | $0.0054 | 28x the price |
| o3 | $2 | $8 | $0.0054 | 28x the price |
| GPT-6.1 Sol | $2 | $10 | $0.0060 | 31x the price |
| GPT-6 Sol | $2 | $10 | $0.0060 | 31x the price |
| GPT-5.6 Terra | $2 | $12 | $0.0066 | 34x the price |
| GPT-4o | $2.50 | $10 | $0.0067 | 35x the price |
| GPT-5.2 | $1.75 | $14 | $0.0068 | 35x the price |
| GPT-5.4 | $2.50 | $15 | $0.0083 | 42x the price |
| GPT-5.6 Sol | $4 | $20 | $0.012 | 62x the price |
| GPT-5.5 | $5 | $30 | $0.017 | 85x the price |
| GPT-6 Astra | $10 | $50 | $0.03 | 154x the price |
| o1 | $15 | $60 | $0.041 | 208x the price |
| o3-pro | $20 | $80 | $0.054 | 277x the price |
| GPT-5 Pro | $15 | $120 | $0.059 | 300x the price |
| GPT-5.2 Pro | $21 | $168 | $0.082 | 420x the price |
| GPT-5.5 Pro | $30 | $180 | $0.099 | 508x the price |
| GPT-5.4 Pro | $30 | $180 | $0.099 | 508x the price |
| o1-pro | $150 | $600 | $0.405 | 2077x the price |
Similar price from other companies
| Model | Input | Output | A chat reply | Next to GPT-5 nano |
|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | $0.00027 | 38% more |
| Claude Haiku 5.5 | $0.10 | $0.50 | $0.00030 | 54% more |
Paying flagship prices for every request?
Most apps send simple requests to the same strong model as the hard ones. PromptUnit checks each request your app sends and uses a cheaper model only when it is just as good for that request. You pay 20% of what it saves, and nothing if it saves nothing.
Checked October 14, 2026. Prices are read every day from OpenAI's pricing page. Context window, inputs and release date come from OpenRouter's public model list.
These are the standard list prices on each provider's own API. Batch, flex and priority tiers, cloud platforms such as Amazon Bedrock or Google Vertex AI, and regional endpoints are priced differently. Request costs above count input and output tokens only, not cache, search or image fees.