OpenAI/gpt-5-nano/Released Aug 2025

GPT 5 Nano

Ultra-low-latency GPT-5 model

Commercial use
Text

About GPT 5 Nano

GPT 5 Nano is a Multimodal LLM optimized for speed and efficiency, making it ideal for applications that require ultra-low latency or must operate under resource constraints. It excels in rapid summarization, classification, and other straightforward language tasks where cost and response time are critical, though it has more limited reasoning and coding abilities compared to larger GPT-5 variants.

Some other noteworthy features of GPT 5 Nano include support for both text and image inputs, minimal reasoning modes for even faster responses, and real-time streaming outputs.

MetricValue
Context Length400,000 tokens
MultilingualYes

Ready to build with GPT 5 Nano?

Try GPT 5 Nano in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "gpt-5-nano",
  "messages": [
    {
      "role": "user",
      "content": "Try sending a message."
    }
  ]
}'

API endpoint

See the API reference for request and response formats.

POSThttps://hub.oxen.ai/api/ai/chat/completions