OpenAI: GPT-5 nano
gpt-5-nano- Input / Output-30%
- $0.05 / $0.40$0.035 / $0.28
- Context
- 400K
- Max output
- 128K
- Modalities
- VisionChat
- Capabilities
- Tool usePrompt CacheReasoning
About GPT-5 nano
GPT-5 nano is the smallest model in OpenAI's first GPT-5 family, tuned for speed and low cost on summarization and classification. It accepts text and images, returns text, and supports function calling and structured outputs. Use it for routing, tagging, and bulk jobs where each call is simple, and step up to mini or GPT-5 when answers get unreliable.
Where it works well
- OpenAI names summarization and classification as its best-fit tasks, so it suits labeling and digest jobs.
- Structured outputs keep results in a fixed JSON shape that downstream code can parse.
- Accepts image input, which lets it tag or describe pictures in bulk.
- Supports prompt caching, useful when many calls share one long instruction block.
When to choose another model
- It is the least capable GPT-5 model, so multi-step reasoning and long coding tasks fail more often than on mini.
- Its knowledge cutoff of May 2024 leaves out recent facts.
- Text output only; it cannot produce images or audio.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textResponses APIPOST/v1/responsesAPI format:curl https://api.tokenlab.sh/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-xxx" \ -d '{ "model": "gpt-5-nano", "input": "Hello!" }'
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Default spec
per 1M tokens- Official price
- Input $0.05 / Output $0.40 / Cache read $0.005
- Verified price
- Input $0.035 / Output $0.28 / Cache read $0.0035
- Discount
- -30%
Cache read
- Official price
- $0.005
- Verified price
- $0.0035
- Discount
- -30%
Charged per call, only when the model uses the tool.
Web search
- Official price
- $0.01/search
- Verified price
- $0.007/search
- Discount
- -30%
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Default spec | Input $0.05 / Output $0.40 / Cache read $0.005 | Input $0.035 / Output $0.28 / Cache read $0.0035 | -30% |
| Prompt cache pricing | |||
| Cache read | $0.005 | $0.0035 | -30% |
| Tool feesCharged per call, only when the model uses the tool. | |||
| Web search | $0.01/search | $0.007/search | -30% |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
- 30-day success rate
- 99.8%
- 30-day requests
- 100+
- Last active
- 9 minutes ago
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open GPT-5 nano in Console with a prompt ready to edit or send.
Help me try gpt-5-nano with a short message at /v1/responses. Show the reply, latency, and cost.
Use cases
Best for- Reasoning
- Vision
Request routing
Read an incoming message and decide which team, queue, or larger model should handle it.
Tagging at scale
Attach topics, sentiment, or language labels to large content backlogs through a strict schema.
Short summaries
Condense articles, chat logs, or meeting notes into a few lines for dashboards and notifications.
Image captions
Produce a one-line description of each uploaded product photo for search indexes.
Prompt examples
Label this review positive, neutral, or negative and return only the label.
Summarize this article in two sentences for a newsletter preview.
Describe this product photo in one line suitable for alt text.
This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.
FAQ
What is GPT-5 nano?
GPT-5 nano is OpenAI's smallest and cheapest model in the first GPT-5 family. It is made for fast summarization and classification, and it accepts both text and images as input.
What tasks is GPT-5 nano good for?
OpenAI points to summarization and classification. In practice that covers tagging, routing, short digests, and simple extraction that run in large volume with a fixed output format.
Does GPT-5 nano support function calling?
Yes. Function calling, structured outputs, file search, and web search are listed on its model page, along with image input. The output of every call is text.
Should I use GPT-5 nano for coding?
Only for small, contained edits. For multi-file changes or debugging, a larger model such as GPT-5 mini or the full GPT-5 will fail less often.
How does GPT-5 nano compare with GPT-5.4 nano?
GPT-5.4 nano is the newer small model, with a later knowledge cutoff and more reasoning effort levels. GPT-5 nano is the older one, still useful when you have validated prompts against it.
How much does GPT-5 nano cost?
On TokenLab, GPT-5 nano costs Input $0.035 / Output $0.28 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the context window and output limit of GPT-5 nano?
GPT-5 nano accepts up to 400,000 tokens of context and returns up to 128,000 tokens in one response.
Which endpoint should GPT-5 nano use?
Use https://api.tokenlab.sh/v1/responses for GPT-5 nano. The request example below shows the matching code shape.
Which operations does GPT-5 nano support?
GPT-5 nano supports Text to text. Select an operation above to see its endpoint and request example.
Compare GPT-5 nano
Sources
Reviewed Oct 2, 2026
More from OpenAI