GPT-6 Astra
Use GPT-6 Astra for demanding connected work. Check the model details, estimate your workload and try an example.
Model facts and API rates
gpt-6-astra · Last verified: · Official model reference
| Text tokens | USD per million (Standard) |
|---|---|
| Ordinary input | $10 |
| Cache reads | $1 |
| Cache writes | $12.5 |
| Billable output | $50 |
Context: 1,050,000 tokens · Maximum output: 128,000 tokens.
What GPT-6 Astra is for
GPT-6 Astra is OpenAI’s GPT-6 model for demanding connected work, released September 3, 2026. Its API ID is gpt-6-astra. Start with the published limits above, then try a small task that represents the work you want to repeat.
Give Astra a connected task with clear deliverables: compare source documents, propose a change and check the finished artifact. Keep references and acceptance criteria together so each conclusion can be traced to an input.
How to access GPT-6 Astra
Astra appears as GPT-6 Pro in ordinary Chat for Pro, Business and Enterprise. Work and Codex list Astra for Plus, Pro, Business and Enterprise. The access guide has product, plan and client checks. For the API, use gpt-6-astra in a project with model access and billing enabled. The API setup guide provides a Responses request you can adapt.
Price your workload
The rates above come from the shared, dated model configuration. Calculate your actual usage with ordinary input, cache reads, writes and billable output. Reasoning tokens count as output. Requests above 272,000 input tokens use higher rates for the entire request, so check the total before adding a large document collection.
For recurring work, include the number of requests and expected retries. The prompt caching calculator helps estimate repeated prefixes. Cache reads and writes are categories within total input, not extra tokens to add again.
Tools, context and output
Use Responses for built-in tools and function calling. Text output, image input and structured outputs are supported. Native audio/video and fine-tuning are not supported by this model. The context window includes both input and output; reserve space for the answer rather than filling the whole window with source material.
Astra supports low, medium, high, xhigh and max reasoning effort. A larger reasoning budget can change output-token usage; compare the actual result before making it the default for every call.
Try a task and inspect the output
Follow the practical guide, then inspect a worked example. Each example keeps its original model and run date. The prompt collection supplies reusable instructions and filled examples; skills package repeatable checks.
Compare with the rest of GPT-6
Open the Astra/Sol/Luna comparison to compare one workload across the family. It uses published rates and capabilities, without assigning a synthetic quality or speed score. For a migration from GPT-5, use the separate GPT-6 vs GPT-5 guide.
The release timeline explains when each family member launched. Related news records subsequent announcements; all GPT-6 models brings the current routes together.