Text APIGPT

GPT-6 Astra API

GPT-6 Astra is the newest OpenAI generation on BeatAPI. It uses the same Text API passthrough as every other text model, and every supported SDK format takes the model ID gpt-6-astra.

ModelChoose it forBilling
gpt-6-astraWork where the newest generation’s reasoning is worth a higher rate than GPT-5.6Flat — no long-context tier

Unlike the GPT-5.6 family, Astra is billed at one rate for the whole context. There is no 272K threshold to plan prompts around. Call GET /v1/models before rollout to confirm the models enabled for your account.

POST https://api.beatapi.io/v1/responses

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.BEATAPI_API_KEY,
5  baseURL: "https://api.beatapi.io/v1"
6});
7
8const response = await client.responses.create({
9  model: "gpt-6-astra",
10  input: "Design a resilient webhook retry strategy for a payments API.",
11  reasoning: { effort: "medium" }
12});
13
14console.log(response.output_text);
$curl --request POST \
>  --url https://api.beatapi.io/v1/responses \
>  --header 'Authorization: Bearer <BEATAPI_API_KEY>' \
>  --header 'Content-Type: application/json' \
>  --data '{
>  "model": "gpt-6-astra",
>  "input": "Design a resilient webhook retry strategy for a payments API.",
>  "reasoning": { "effort": "medium" }
>}'

Reasoning effort accepts none, low, medium, high, xhigh, and max. Use medium as a balanced starting point, then evaluate one level lower and higher on your own workload.

Existing SDK formats

You can migrate an existing integration by changing the base URL and replacing the provider key with a BeatAPI key.

OpenAI Chat Completions

POST https://api.beatapi.io/v1/chat/completions

$curl --request POST \
>  --url https://api.beatapi.io/v1/chat/completions \
>  --header 'Authorization: Bearer <BEATAPI_API_KEY>' \
>  --header 'Content-Type: application/json' \
>  --data '{
>  "model": "gpt-6-astra",
>  "messages": [
>    { "role": "user", "content": "Design a resilient webhook retry strategy for a payments API." }
>  ]
>}'

Anthropic Messages

POST https://api.beatapi.io/v1/messages

$curl --request POST \
>  --url https://api.beatapi.io/v1/messages \
>  --header 'Authorization: Bearer <BEATAPI_API_KEY>' \
>  --header 'Content-Type: application/json' \
>  --data '{
>  "model": "gpt-6-astra",
>  "max_tokens": 1024,
>  "messages": [
>    { "role": "user", "content": "Design a resilient webhook retry strategy for a payments API." }
>  ]
>}'

Gemini generateContent

POST https://api.beatapi.io/v1beta/models/gpt-6-astra:generateContent

$curl --request POST \
>  --url 'https://api.beatapi.io/v1beta/models/gpt-6-astra:generateContent' \
>  --header 'Authorization: Bearer <BEATAPI_API_KEY>' \
>  --header 'Content-Type: application/json' \
>  --data '{
>  "contents": [
>    { "role": "user", "parts": [{ "text": "Design a resilient webhook retry strategy for a payments API." }] }
>  ]
>}'

Confirm what your key can call

GET https://api.beatapi.io/v1/models

1{
2  "object": "list",
3  "data": [
4    { "id": "gpt-6-astra", "object": "model", "owned_by": "beatapi" }
5  ]
6}

The same API key and USD balance are shared across Text, Image, Video, Workflow, Effect, and Realtime APIs. Calls are metered from actual token usage; inspect request IDs, model, token totals, status, and settled amount in Dashboard usage logs.