OpenAI · Legacy
GPT-5 nano
Fastest, most cost-efficient version of GPT-5 for classification and summarization.
- Reasoning
-
- Speed
-
- Context window
- 400K
- Input
-
Text input supportedImage input supportedAudio input not supportedVideo input not supported - Output
-
Text output supportedImage output not supportedAudio output not supportedVideo output not supported
Pricing
per 1M tokens
Input price
$0.05
Cache read price
$0.005
Cache write price
—
Output price
$0.40
Capabilities
- ✓ Function calling
- ✓ Vision
- ✓ Structured output
- – Extended reasoning
- ✓ Prompt caching
- ✓ Batch API
- ✓ Streaming
Limits & knowledge
- Context window
- 400K
- Max output
- 128K
- Knowledge cutoff
- May 2024
- Family
- GPT-5
Source & last check
Source: https://developers.openai.com/api/docs/models/gpt-5-nano · Verified on: May 25, 2026