Developer referenceReviewed September 5, 2026

GPT-6 Astra API Guide

A source-checked implementation reference for model ID, endpoints, reasoning controls, tools, context limits and current API rate limits.

Model ID

gpt-6-astra

Minimal Responses API request

JavaScript

import OpenAI from "openai";

const client = new OpenAI();
const response = await client.responses.create({
  model: "gpt-6-astra",
  input: "Review this architecture and list the three highest-risk assumptions."
});

console.log(response.output_text);

OpenAI recommends the Responses API for new direct model integrations. Chat Completions remains supported, while Responses exposes the broader tool-oriented workflow used by newer agentic applications.

Supported endpoints

Endpoint	Current model-page status	Typical use
Responses	Supported	Recommended new integrations and tools
Chat Completions	Supported	Existing chat-style integrations
Batch	Supported	Asynchronous bulk processing
Realtime	Listed	Realtime-capable workflows

Core model capabilities

StreamingFunction callingStructured outputsImage inputReasoning tokens

Reasoning effort

Astra supports low, medium, high, xhigh and max reasoning effort. Higher effort is intended for harder multi-step work, but can increase latency and token consumption.

Responses API tools

Web searchFile searchImage generationCode interpreterHosted shellApply patchSkillsComputer useMCPTool search

Limits that matter

Context window	1,050,000 tokens
Maximum output	128,000 tokens
Knowledge cutoff	April 30, 2026
Fine-tuning	Not supported

Published API rate limits

OpenAI states that limits depend on usage tier and can increase as account usage grows. These values are a snapshot of the model page reviewed on September 5, 2026.

Tier	RPM	TPM	Batch queue
Tier 1	500	500K	1.5M
Tier 2	5K	1M	3M
Tier 3	5K	2M	100M
Tier 4	10K	4M	200M
Tier 5	15K	40M	15B

Free tier: listed as not supported on the model page at review time.

Start coding

Use one of the language-specific guides for a minimal implementation, then return here for model-level constraints and limits.

Python example →JavaScript example →Calculate cost →

Frequently asked questions

What is the GPT-6 Astra model ID?

The API model ID is gpt-6-astra.

Which API should a new GPT-6 Astra integration use?

OpenAI recommends the Responses API for new projects. Chat Completions remains supported.

Does GPT-6 Astra support function calling?

Yes. OpenAI lists function calling and structured outputs as supported.

Does GPT-6 Astra support fine-tuning?

No. Fine-tuning is currently listed as unsupported for GPT-6 Astra.

Primary sources

Specifications and prices can change. We prefer first-party documentation and record the date each page was reviewed.