---
title: "GPT-6 Astra — API access"
description: "GPT-6 Astra through Codex: 872K maximum context, adjustable reasoning and image input. Official $10/$50 per 1M input/output tokens; $5/$25 with the flat 50% discount."
url: "https://apitoken.sale/models/gpt-6-astra"
language: "en"
---
# GPT-6 Astra

GPT-6 Astra is the latest GPT model in the model catalog. Use it for coding and reasoning through the OpenAI-compatible endpoint. Choose reasoning effort from low to max, send images, and use structured outputs or function tools.

- **Model ID:** `gpt-6-astra`
- **Tier:** Flagship
- **Context window:** 872K tokens
- **Max output:** 128K tokens
- **Official price (per 1M):** $10 input / $50 output
- **Your price (per 1M):** input $5, output $25 (flat 50% off)
- **Base URL:** `https://router.apitoken.sale/v1` · **Endpoints:** `POST /v1/responses`, `POST /v1/chat/completions` (Authorization: Bearer)

## Best for

- Coding and reasoning with explicit effort control.
- Image understanding with structured JSON output.
- Function calls and long conversations through Responses or Chat Completions.

## Notes

- This service uses Astra's Codex subscription limits: 272K default client context and 872K maximum. The larger direct OpenAI API window does not apply here.
- Discovery reports 872K total context, 128K output and 744K conservative input. Codex client reserve and automatic compaction thresholds are separate client settings.
- Above 272K input tokens, the whole request uses 2× input/cache rates and 1.5× output rates. Fast (priority) uses 2× the applicable API rates.
- Reasoning none and Codex-specific ultra delegation are not advertised. Async tools and mid-turn steering are outside this integration.

## Call it

```bash
curl https://router.apitoken.sale/v1/responses \
  -H "Authorization: Bearer $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-6-astra", "input": "Reply with exactly: connected"}'
```

## FAQ

**What does GPT-6 Astra cost?**

Official rates per 1M tokens are $10 input, $1 cached input, $12.50 cache write and $50 output. With the normal 50% B2C discount, these are $5, $0.50, $6.25 and $25. OpenKeys uses the official rates.

**Is Astra's context window 872K or 1.05M?**

This endpoint serves the Codex subscription model, whose verified maximum context is 872,000 tokens. The Codex client defaults to 272,000. The 1.05M direct API window is a different service limit.

**How do I select Astra?**

Set model to gpt-6-astra on https://router.apitoken.sale/v1. Supported reasoning levels are low, medium, high, xhigh and max. Use service_tier priority for Fast.

---
API reference: https://apitoken.sale/md/docs · All models: https://apitoken.sale/md/models