Try MiniMax FastH3 from Fastvideo →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
LLM & ChatActive

openai / gpt-5.2

gpt-5.2

byopenai

AI model for processing text prompts and image inputs with advanced reasoning capabilities. Supports multi-modal inputs and customizable responses.

Partner LLMLLM Tool Call
Model ID
gpt-5.2
Provider
openai
Runs
34837
Updated
1788114228
wiro playground—openai/gpt-5.2
Reset to defaults
Delete All
0 / 10
Maximum 10 image allowed

Optional. Multiple image files separated by semicolon. GPT-5.2 only supports images.

Required.

Random

Required for chat history. Numeric or string ID.

Random

Required for chat history. Numeric or string ID.

Sample outputs

No samples yet

Run this model to create outputs and build up samples.

Updated 1788114228

Overview

GPT-5.2 is an advanced AI model designed for processing text prompts and image inputs with enhanced reasoning capabilities. It supports multi-modal inputs and offers customizable response controls.

What you can build

  • Multi-modal content generators using text and image inputs
  • Intelligent chatbots with custom reasoning levels
  • Automated response systems with adjustable verbosity
  • Custom AI assistants with system instruction control

Inputs

  • Prompt (required): Text input for model processing
  • Input Image: Optional multiple image files
  • User ID: Required for chat history tracking
  • Session ID: Required for chat history tracking
  • System Instructions: Optional system-level guidance
  • Reasoning Effort: Controls reasoning depth (none, low, medium, high, xhigh)
  • Verbosity: Controls response detail level (low, medium, high)

Outputs

  • Generated text responses based on prompts
  • Processed outputs from combined image and text inputs
  • Customizable response formats based on settings

Recommended settings

  • Use default 'medium' reasoning effort for balanced performance
  • Set verbosity to 'medium' for standard output length
  • Include user_id and session_id for conversation continuity

Limitations

  • GPT-5.2 specifically requires image inputs for visual processing
  • Advanced features like system instructions may require API integration
  • Response quality depends on prompt clarity and input data quality

Safety & compliance

  • Models should be used in accordance with OpenAI's usage policies
  • Ensure appropriate content filtering for sensitive applications
  • Respect privacy and data protection regulations when handling user inputs

API quick start

Run gpt-5.2 with a single API call.

POST https://api.wiro.ai/v1/Run/openai/gpt-5.2
{
  "prompt": "Tell me about Türkiye",
  "inputImage": "https://your-cdn.com/input.png",
  "user_id": "...",
  "session_id": "..."
}
View full API docs