NEAR AI
Sign inStart building
All models

GPT-6 Astra API

Incognito
openai/gpt-6-astra

OpenAI model for complex reasoning, coding, research, and document creation. Tool calling is not currently supported through NEAR AI Cloud.

Input / 1M tokens
$10
Output / 1M tokens
$50
Cache read / 1M tokens
$1
Context window
1.05M tokens

Privacy & execution

This Incognito model runs on a partner provider’s infrastructure. NEAR AI routes requests using shared provider credentials, so your NEAR AI account credentials are not forwarded.

Your prompts are processed by the provider under its terms and privacy policy. HTTPS protects data in transit. Model TEE attestation and client-to-model end-to-end encryption are not provided for this model. Where available, Gateway signatures verify the request and response handled by the Gateway.

Verification documentation
01

Make your first request

Call /v1/responses over HTTPS.

Get an API key and replace the API key placeholder below.

curl https://cloud-api.near.ai/v1/responses \ -H "Content-Type: application/json" \ -H "Authorization: Bearer <YOUR-NEAR-AI-CLOUD-API-KEY>" \ -d '{ "model": "openai/gpt-6-astra", "input": "What is the meaning of life?", "store": false }'

This HTTP example uses HTTPS. Use the SDK below to verify deployment evidence and the response signature.

02

Build and Verify with the SDK

Use the OpenAI Responses API and verify the Gateway’s response signature.

Verification guide

Set NEARAI_API_KEY before running an example. Responses use Gateway signatures and do not support field-level E2EE.

Setup

npm install @nearai/inference-sdk openai

Example

import OpenAI from "openai"; import { InferenceClient } from "@nearai/inference-sdk/node"; const apiKey = process.env.NEARAI_API_KEY; if (!apiKey) throw new Error("Set NEARAI_API_KEY first."); // Verify deployment evidence and the Gateway's Responses receipt. const inferenceClient = new InferenceClient({ apiKey, baseUrl: "https://cloud-api.near.ai/v1", e2ee: false, }); const openai = new OpenAI({ apiKey, baseURL: inferenceClient.getBaseUrl(), fetch: inferenceClient.fetch, maxRetries: 0, }); const response = await openai.responses.create({ model: "openai/gpt-6-astra", input: "Hello!", store: false, }); // Verify the exact request/response bytes before displaying the answer. const verified = await inferenceClient.verifyResponse(response.id); console.log(response.output_text); console.log("Verified signer:", verified.signatureKind);

JavaScript SDK guide

GPT-6 Astra API FAQ

How much does the GPT-6 Astra API cost?
$10.00 per 1M input tokens and $50.00 per 1M output tokens on NEAR AI Cloud, and $1.00 per 1M cached input tokens.
What is the context window of GPT-6 Astra?
1.05M tokens.
How do I call the GPT-6 Astra API?
Create an API key on NEAR AI Cloud, then send requests to https://cloud-api.near.ai/v1/responses with the model ID openai/gpt-6-astra. The endpoint is OpenAI-compatible, so OpenAI SDKs work by setting the base URL to https://cloud-api.near.ai/v1.
Where does GPT-6 Astra run?
On the model provider's infrastructure, under its terms. NEAR AI routes requests with shared provider credentials, so your NEAR AI account credentials are not forwarded. TEE attestation is not provided for this model.