GPT-6.2 Astra

OpenAI GPT-6.2 Astra,适合复杂分析、软件工程和多步骤任务。

Model ID: gpt-6.2-astra · Type: chat · Provider: OpenAI

Endpoints: /v1/responses · /v1/chat/completions

Pricing

Input (per 1M tokens)$5.2 USD
Output (per 1M tokens)$26 USD
Cache read (per 1M tokens)$0.26 USD
Cache write 5m (per 1M tokens)$6.5 USD

Context tiers

≤ 272000 tokens$5.2 / 1M in$26 / 1M out
> 272000$10.4 / 1M in$39 / 1M out
import os

from openai import OpenAI

client = OpenAI(api_key=os.environ["ROUTER_API_KEY"], base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
    model="gpt-6.2-astra",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does GPT-6.2 Astra cost on 370.AI?

GPT-6.2 Astra (`gpt-6.2-astra`) is billed per usage at $5.2/1M in · $26/1M out, in USD. Current pricing is always listed at https://370.ai/models/gpt-6.2-astra.

How do I call GPT-6.2 Astra through 370.AI?

Send a request to https://api.router.ai/v1/responses with the header `Authorization: Bearer <your API key>` and `"model": "gpt-6.2-astra"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

Which endpoints does GPT-6.2 Astra support?

GPT-6.2 Astra can be called on: /v1/responses; /v1/chat/completions.

Who makes GPT-6.2 Astra?

GPT-6.2 Astra is a chat model from OpenAI, available through the 370.AI gateway with the same API key as every other model.

Call it through the 370.AI OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can browse the catalog and call any text model through MCP (https://mcp.router.ai/mcp); for image, video and other modalities use the API above.

Which should you pick

API reference · All models