openai · CODEX
GPT-6 Astra API Pricing
Check the model ID and provider reference rates for GPT-6 Astra, along with current pricing availability on CODEX.
Effective CODEX API rates
USD per 1M tokens. Quota rates use the current AI in IDE base price × 0.8. Provider prices as of 2026-11-02.
| AI in IDE quota rate | Reference provider rate | |
|---|---|---|
| Input | $8.00 | $10.00 |
| Cache read | $0.80 | $1.00 |
| Output | $40.00 | $50.00 |
Use GPT-6 Astra in your client
Create an API key in your dashboard, replace YOUR_DASHBOARD_API_KEY, and run this request to verify the setup.
curl --globoff 'https://api.aiinide.com/responses' \
-H "Authorization: Bearer YOUR_DASHBOARD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6-astra","input":"Explain this repository.","max_output_tokens":256}'Example monthly API cost
Estimated with a 3:1 input-to-output token mix and current top-up tiers. Cache reads are excluded from these examples.
| Monthly tokens | Reference API cost | AI in IDE top-up cost |
|---|---|---|
| 1M | $20.00 | $7.99 |
| 10M | $200.00 | $27.05 |
| 100M | $2,000.00 | $217.99 |
Examples round top-up quota up to the next $25 with a $50 minimum. Actual charges vary by usage, plan, context, speed, and promotions.
GPT-6 Astra API FAQ
How much does GPT-6 Astra API cost?
Reference rates for GPT-6 Astra are USD 10 input, USD 1 cache read, and USD 50 output per 1M tokens. AI in IDE applies 0.8× its configured model price when charging quota.
What is the GPT-6 Astra model ID?
The model ID is gpt-6-astra.
How do I use GPT-6 Astra in my IDE?
Create a CODEX API key, run the setup example on this page, and follow the linked IDE guide.