LLM & ChatActive
openai / gpt-5-nano
gpt-5-nano
A compact AI model optimized for efficient processing of complex prompts and multi-modal inputs with support for images and structured data.
Partner LLM
Model ID
gpt-5-nano
Provider
openai
Updated
1774537909
wiro playground—openai/gpt-5-nano
Updated 1774537909
# Overview
GPT-5 Nano is a streamlined version of OpenAI's advanced language model, optimized for efficiency while maintaining strong performance in text generation and multimodal tasks. It supports image input and structured data processing, making it suitable for various AI applications.
# What you can build
- Text summarization tools
- Image captioning systems
- Multi-modal AI assistants
- Automated content generators
- Data processing pipelines
# Inputs
- **Prompt**: Required text input for model processing.
- **Input Image**: Optional image file(s) for multimodal analysis.
- **User ID & Session ID**: Optional for tracking chat history.
- **System Instructions**: Optional advanced configuration for model behavior.
- **Reasoning Effort**: Controls depth of reasoning (minimal, low, medium, high).
- **Verbosity**: Adjusts output detail level (low, medium, high).
# Outputs
- Generated text responses
- Image descriptions
- Structured data interpretations
# Recommended settings
- Default reasoning effort: medium
- Default verbosity: medium
- Use system instructions for fine-tuning behavior
# Limitations
- Designed primarily for text and image processing
- Not optimized for real-time inference at scale
- Requires specific input formatting for advanced features
# Safety & compliance
- Follow OpenAI's usage guidelines
- Implement appropriate content filters
- Ensure compliance with applicable regulations
API quick start
Run gpt-5-nano with a single API call.
POST https://api.wiro.ai/v1/Run/openai/gpt-5-nano
{
"prompt": "Tell me about Türkiye",
"inputImage": "https://your-cdn.com/input.png",
"user_id": "...",
"session_id": "..."
}