GPT-6 Astra Pro

GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with OpenAI's reasoning mode set to pro. OpenAI GPT-6 Astra Pro Reasoning Mode, with a 1M token context window.

POST/v1/ai/chat

$0.01/call

Overview

GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with OpenAI's reasoning mode set to pro. OpenAI GPT-6 Astra Pro Reasoning Mode, with a 1M token context window.

Property	Value
Model ID	`openai/gpt-6-astra-pro`
Context Window	1,050,000 tokens
Max Output	128,000 tokens
Input Price	$14.77 / 1M tokens
Output Price	$73.85 / 1M tokens

Usage

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'openai/gpt-6-astra-pro',
    messages: [{ role: 'user', content: 'Find the bug in this concurrent cache implementation and explain why it only appears under load.' }],
  }),
});
const { data } = await res.json();
console.log(data.message.content);

curl -X POST https://api.yepapi.com/v1/ai/chat \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-6-astra-pro", "messages": [{"role": "user", "content": "Find the bug in this concurrent cache implementation and explain why it only appears under load."}]}'

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	Model ID (e.g. `openai/gpt-6-astra-pro`)	—
`messages`	`Message[]`	Yes	Array of `{ role, content }` objects	—
`maxTokens`	`number`	No	Maximum tokens in the response	Model default
`temperature`	`number`	No	Sampling temperature (0.0–2.0)	`1.0`
`topP`	`number`	No	Nucleus sampling threshold	`1.0`
`frequencyPenalty`	`number`	No	Penalize repeated tokens	`0`
`presencePenalty`	`number`	No	Penalize tokens already present	`0`
`stream`	`boolean`	No	Enable SSE streaming	`false`

Info

All AI models use the /v1/ai/chat endpoint. Specify the model with the model field.

Response

{
  "ok": true,
  "data": {
    "model": "openai/gpt-6-astra-pro",
    "message": {
      "role": "assistant",
      "content": "The get-or-compute path checks the map, misses, computes, then inserts \u2014 without holding the lock across the whole sequence. Under load two threads miss at the same time, both compute, and the second insert silently overwrites the first, so listeners registered on the first entry never fire. Compute under a per-key lock or use a compute-if-absent primitive."
    },
    "usage": {
      "promptTokens": 16,
      "completionTokens": 245,
      "totalTokens": 261
    }
  }
}

Streaming

Set "stream": true to receive Server-Sent Events. Each chunk contains a delta object:

data: {"delta":{"content":"Use"},"model":"openai/gpt-6-astra-pro","index":0}
data: [DONE]

Under the Hood

We handle auth, billing, and response normalization — you just send messages.