Input
- Official OpenAI
- $10
- Here (−50%)
- $5
gpt-6-astra
GPT-6 Astra API — price per token
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.
Pricing per 1M tokens
| Rate | Official OpenAI | Here (−50%) |
|---|---|---|
| Input | $10 | $5 |
| Cached input | $1 | $0.5 |
| Cache write | $12.5 | $6.25 |
| Output | $50 | $25 |
Cached input
- Official OpenAI
- $1
- Here (−50%)
- $0.5
Cache write
- Official OpenAI
- $12.5
- Here (−50%)
- $6.25
Output
- Official OpenAI
- $50
- Here (−50%)
- $25
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 872K tokens. Max output: 128K tokens. Reasoning efforts: low, medium, high, xhigh, max.
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.
Good to know
- 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.
How to use GPT-6 Astra
Create a free account, generate one key, and point any OpenAI-compatible tool at https://router.apitoken.sale/v1 with model ID gpt-6-astra — Responses and Chat Completions both work, authenticated with Authorization: Bearer. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up. Existing integrations on the legacy host https://openai.api.apitoken.sale/v1 keep working.
Frequently asked questions
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.
Run GPT-6 Astra on the OpenAI-compatible API at a flat 50% off — instant key, prepaid balance, card or crypto.