MODELS
GPT-5
by OpenAI
Overview
OpenAI model for coding and agentic tasks with text and image input, structured outputs, and parallel tool calling.
Details
GPT-5 is an OpenAI model positioned for coding and agentic tasks. Its official model documentation lists a 400,000-token context window, up to 128,000 output tokens, and support for text and image input. Supported API features include streaming, function calling, structured outputs, and parallel tool calling. OpenAI describes GPT-5 as a unified system with fast and deeper-reasoning modes; its current model catalog identifies it as a previous intelligent reasoning model.
When to Use
Build coding assistants and software-development workflows. Develop agents that call tools or execute multiple tool calls in parallel. Produce schema-constrained responses with structured outputs. Process long-context tasks that combine text and images.
Getting Started
- Review the official GPT-5 model documentation for limits
- inputs
- and supported API features.
- Prototype an API workflow using streaming
- function calling
- or structured outputs.
- Consult the official pricing page before estimating production costs.
- Review the GPT-5 system card for safety evaluation and mitigation information.
Key Features
- •400
- •000-token context window
- •Up to 128
- •000 output tokens
- •Text and image input
- •Streaming
- •Function calling
- •Structured outputs
- •Parallel tool calling
- •Fast and deeper-reasoning modes
Capabilities
- •coding
- •agentic tasks
- •long-context processing
- •text input
- •image input
- •streaming
- •function calling
- •structured outputs
- •parallel tool calling
Last updated Jul 31, 2026