GPT 5 Chat is a conversational variant of GPT-5 optimized for multi-turn dialogue, delivering the GPT-5 family's advanced capabilities in an interface tuned specifically for chat-based applications.
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-5-chat', prompt: 'Why is the sky blue?'})GPT 5 Chat became available on August 7, 2025 as a conversational variant within the GPT-5 model family on AI Gateway. While the base GPT-5 model serves as a general-purpose model, GPT 5 Chat is specifically optimized for the patterns that matter in dialogue: maintaining coherence across many turns, producing natural conversational flow, and adapting tone and detail level based on the conversation context.
The model retains the GPT-5 family's core capabilities, including the context window of 128K tokens, strong instruction following, and multimodal input support. The optimization focuses on how these capabilities are applied in conversational settings, producing responses that feel more natural in back-and-forth dialogue.
For developers building chat-based products, GPT 5 Chat reduces the prompt engineering effort needed to achieve natural conversation quality. The model's training emphasizes the conversational use case directly rather than requiring developers to shape general-purpose model output into dialogue form.