GPT 5 Chat
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?'})Playground
Try out GPT 5 Chat by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by OpenAI
| Model |
|---|
| 1M | 3.2s | 68tps | $5.00/M | $30.00/M | Read: $0.5/M Write: — | $10.00/K + input costs | — |   | 04/24/2026 | ||||
| 400K | 1.5s | 190tps | $0.75/M | $4.50/M | Read:$0.07/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 400K | 0.5s | 117tps | $0.20/M | $1.25/M | Read:$0.02/M Write:— | $10.00/K + input costs | — | | 03/17/2026 | ||||
| 128K | 0.5s | 111tps | $1.25/M | $10.00/M | Read:$0.13/M Write:— | $10.00/K + input costs | — | | 11/12/2025 | ||||
| 400K | 3.4s | 446tps | $0.25/M | $2.00/M | Read:$0.03/M Write:— | $14/K + input costs | — | | 08/07/2025 | ||||
| 131K | 0.1s | 223tps | $0.35/M | $0.75/M | Read:$0.25/M Write:— | — | — |    +5 | 08/05/2025 |
About GPT 5 Chat
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.
What To Consider When Choosing a Provider
- Configuration: GPT 5 Chat is specifically tuned for conversational patterns. If your application is primarily a chat interface, this variant may produce more natural dialogue flow than the base GPT-5 model.
- Configuration: The base GPT-5 is a general-purpose model; this variant prioritizes conversational coherence and turn-taking quality.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use GPT 5 Chat
Best For
- Customer-facing chatbots: Natural, coherent multi-turn conversations with strong reasoning
- Interactive assistants: Conversational interfaces that require context retention across many turns
- Tutoring and education: Dialogue-based learning experiences with adaptive conversation flow
- Support automation: Multi-step troubleshooting conversations that maintain context
- Conversational search: Natural language interaction for exploring complex topics
Consider Alternatives When
- Non-conversational workloads: Base GPT-5 is better for single-shot tasks, batch processing, or structured generation
- Cost-sensitive chat: GPT-5 mini provides strong conversational capability at lower cost
- Simple Q&A: GPT-4o mini handles straightforward chat at a fraction of the price
- Deep reasoning in chat: O3 provides stronger chain-of-thought for technically demanding conversations
Conclusion
GPT 5 Chat brings GPT-5's capabilities to a conversational interface optimized for multi-turn dialogue. For chat-based applications on AI Gateway where conversation quality and natural flow are priorities, it is purpose-built for the task.
Frequently Asked Questions
How does GPT 5 Chat differ from base GPT-5?
GPT 5 Chat is optimized for multi-turn dialogue patterns, producing more natural conversational flow while retaining the GPT-5 family's core reasoning and coding capabilities.
What context window does GPT 5 Chat support?
128K tokens, matching the GPT-5 family and enabling extended conversation histories.
Is GPT 5 Chat suitable for non-chat tasks?
It can handle them, but base GPT-5 is generally better optimized for single-shot generation, batch processing, and structured output tasks.
How does AI Gateway handle authentication for GPT 5 Chat?
AI Gateway accepts a single API key or OIDC token for all requests. You don't embed OpenAI credentials in your application; AI Gateway routes and authenticates on your behalf.
Can I use GPT 5 Chat with function calling?
Yes. It supports function calling and tool use, enabling conversational agents that interact with external APIs and services.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.