Standard context
$2.00
- Input: $2.00 / 1M tokens · cached input: $0.20 / 1M tokens · output: $10.00 / 1M tokens.
- Applies when input context is 272,000 tokens or less.
GPT-6 Astra API / Long-context chat completions with transparent token pricing
Build with GPT-6 Astra through PiAPI's OpenAI-compatible chat completions endpoint. Use the playground to test messages and inspect the immediate response.
GPT-6 Astra token pricing
Limited-time promotional pricing (20% of OpenAI's official pricing). All prices are per 1M tokens.
Long context
$4.00
- Input: $4.00 / 1M tokens · cached input: $0.40 / 1M tokens · output: $15.00 / 1M tokens.
- Above 272,000 input tokens, the entire request is billed at this tier.
Ready to build with GPT-6 Astra?
GPT-6 Astra capabilities
An OpenAI-compatible chat API for long-context applications and developer workflows.
OpenAI-compatible chat
Send a standard messages array to POST /v1/chat/completions and receive the completed response immediately.
Reasoning controls
Choose low, medium, or high reasoning effort when your workflow needs a different balance of speed and depth.
Clear token billing
Input, cached input, and output token prices are shown together for both context tiers.
272K context threshold
When input context exceeds 272,000 tokens, the entire request moves to the long-context rate.
Get started
Create your API key
Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.
Top up credits
Add credits on the billing page when you are ready to scale beyond the free tier.
Call the API
POST your first task following the API docs, then poll the task until the result is ready.
Iterate in the playground
Prototype prompts and settings in the the playground above before wiring them into your product.
curl -X POST 'https://api.piapi.ai/api/v1/task' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-6-astra",
"task_type": "chat-completion",
"input": {
"messages": [{"role":"user","content":"Explain what an API gateway does, in two sentences."}]
}
}'
# → { "task_id": "9d5a…", "status": "pending" }curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'
# poll until status = completed
{
"data": {
"status": "completed",
"output": {
"content": "https://img.theapi.app/ephemeral/…"
}
}
}$ npm install -g piapi-cli $ piapi run gpt-6-astra \ messages=[object Object] ✓ Task completed! https://img.theapi.app/ephemeral/…
GPT-6 Astra API FAQ
How is GPT-6 Astra billed?
Standard requests cost $2.00 per 1M input tokens, $0.20 per 1M cached input tokens, and $10.00 per 1M output tokens.
What happens above 272,000 input tokens?
When input context exceeds 272,000 tokens, the entire request is billed at the long-context tier: $4.00 per 1M input tokens, $0.40 per 1M cached input tokens, and $15.00 per 1M output tokens.
Which endpoint does GPT-6 Astra use?
Use the OpenAI-compatible POST /v1/chat/completions endpoint with a model and messages array.
More questions? See the API docs.