Text model API
GPT-6 Astra Pro API
GPT-6 Astra Pro is OpenAI’s premium reasoning variant of GPT-6 Astra, configured with reasoning.mode: pro to deliver higher-quality reasoning on complex tasks. It is designed for demanding workloads such as advanced analysis, software engineering, research, and long-horizon problem solving. With a 1.05M-token context window and support for up to 128K completion tokens, the model can work with extremely large documents, codebases, and multi-step tasks. It accepts text, images, and PDFs as input and generates text output.
- Model id
gpt-6-astra-pro- Takes
- Text (required)
- Makes
- Text
- Endpoint
POST /api/v1/chat/completions- Made by
- OpenAI
- Mode
- Synchronous
Call GPT-6 Astra Pro
https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.Model gpt-6-astra-pro
POST /api/v1/chat/completions
curl https://payload.rentprompts.com/api/v1/chat/completions \
-H "Authorization: Bearer rp_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-astra-pro",
"messages": [
{
"role": "user",
"content": "Write a haiku about APIs."
}
],
"max_tokens": 256
}'Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →
What a typical call costs
- 1,000 input + 500 output tokens3.8 Joules
- 10,000 input + 2,000 output tokens22.4 Joules
Send requests to POST /api/v1/chat/completions. GPT-6 Astra Pro answers synchronously: the result comes back in the response to the same request. Token counts come from the model's own usage report, so a real call may use more or fewer tokens than this example.
Settings
This model has no extra settings. Send the standard fields shown in the example.