> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bettertoken.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT-6 Astra is live

> GPT-6 Astra is available on BetterToken as gpt-6-astra for complex reasoning, coding, research, computer use, and long-running agent workflows.

Updated: September 5, 2026

BetterToken now supports **GPT-6 Astra** with the exact Model ID `gpt-6-astra`. OpenAI describes Astra as its most capable model for difficult end-to-end work, including complex reasoning, software engineering, research, computer use, and document creation. Check current availability and BetterToken pricing in the <a href={"https://bettertoken.ai/pricing"}>model plaza</a>.

## Highlights

* **End-to-end work**: designed for complex, multistep tasks across code, browsers, tools, and professional applications
* **Software engineering**: OpenAI positions Astra as its strongest model so far for coding and agentic software development
* **Large context**: OpenAI documents a `1,050,000`-token context window and up to `128,000` output tokens
* **Adjustable reasoning**: the OpenAI API supports `low`, `medium`, `high`, `xhigh`, and `max` reasoning effort
* **Responses API tools**: OpenAI documents support for function calling, structured outputs, web search, file search, code interpreter, computer use, MCP, and other Responses API tools

## Configuration recommendations

* Use Astra for difficult coding, research, computer-use, or long-running agent tasks. For routine work, compare it with faster or lower-cost models in the model plaza.
* Start with a representative test task before switching production traffic. Compare output quality, latency, and token usage in your own workflow.
* Use the **GPT provider**, the Base URL `https://bettertoken.ai/v1`, and the exact BetterToken Model ID `gpt-6-astra`.
* Availability can change during a staged rollout. Treat the model plaza as the source of truth for BetterToken availability and pricing.

## Quick start

1. Create a BetterToken API Key or open the **Setup** dialog for an existing key.
2. Confirm that `gpt-6-astra` is available in the model plaza.
3. Set the Base URL to `https://bettertoken.ai/v1` and the model to `gpt-6-astra` in your client.
4. Restart the client if it does not refresh its model list automatically.
5. Run a small test task and verify the request in the Dashboard.

Use one of these guides:

* [Codex CLI and Codex App setup](/en/ai-tools/codex)
* [OpenCode setup](/en/ai-tools/opencode)
* [Model selection guide](/en/faq/model-calling/model-selection-guide)

## Frequently asked questions

### What is the GPT-6 Astra Model ID?

Use `gpt-6-astra`. Do not substitute the display name `GPT-6 Astra` or an ID copied from another platform.

### Does BetterToken provide the full 1,050,000-token context window?

OpenAI lists a `1,050,000`-token context window for GPT-6 Astra. The usable limit can also depend on the client, request settings, and current BetterToken routing. Check the model plaza and your client documentation before sending very large prompts.

### How do I fix Model not found?

Confirm that the Model ID is exactly `gpt-6-astra`, the BetterToken API Key can access the model, the **GPT provider** is selected, and the Base URL is `https://bettertoken.ai/v1`. Then restart the client and test again.

### Where can I find the current price?

Check the live <a href={"https://bettertoken.ai/pricing"}>model plaza</a>. BetterToken pricing may differ from OpenAI's direct API pricing and can change over time.

<Note>
  Model availability and BetterToken pricing can change. Check the live <a href={"https://bettertoken.ai/pricing"}>model plaza</a> before configuring the model.
</Note>

## Official sources

* [GPT-6 Astra announcement](https://openai.com/index/gpt-6-astra/)
* [GPT-6 Astra API model reference](https://developers.openai.com/api/docs/models/gpt-6-astra)
* [GPT-6 Astra model guidance](https://developers.openai.com/api/docs/guides/latest-model)
* [GPT-6 Astra safety overview](https://openai.com/index/safety-overview-gpt-6-astra/)