OpenAI GPT-6 Astra，2026-09-04 发布的新一代旗舰模型
Model ID: gpt-6-astra · Type: chat · Provider: OpenAI
Endpoints: /v1/chat/completions · /v1/responses · /v1/messages
| Input (per 1M tokens) | $6.5 USD |
| Output (per 1M tokens) | $32.5 USD |
| Cache read (per 1M tokens) | $0.65 USD |
| Cache write 5m (per 1M tokens) | $8.125 USD |
| ≤ 272000 tokens | $6.5 / 1M in | $32.5 / 1M out |
| > 272000 | $13 / 1M in | $48.75 / 1M out |
from openai import OpenAI
client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
model="gpt-6-astra",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)GPT-6 Astra (`gpt-6-astra`) is billed per usage at $6.5/1M in · $32.5/1M out, in USD. Current pricing is always listed at https://j8api.com/models/gpt-6-astra.
Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "gpt-6-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.
GPT-6 Astra can be called on: /v1/chat/completions; /v1/responses; /v1/messages.
GPT-6 Astra accepts up to 922,000 input tokens and can return up to 128,000 output tokens. Requests exceeding the input limit are rejected before reaching the model.
GPT-6 Astra supports: vision, function_calling, prompt_caching.
GPT-6 Astra is a chat model from OpenAI, available through the J8API gateway with the same API key as every other model.
Call it through the J8API OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can discover and call every model on this gateway through MCP (https://mcp.router.ai/mcp) with no manual integration.