Back to models
OpenAI

GPT-6 Astra

GPT-6 Astra is OpenAI's flagship model released 2026-09-03, with a 1.05M token context window and computer-use capability. Long-context requests (>272K input tokens) are billed at higher rates for the whole request.

Quick Stats

Context

1050K

Max Output

128K

Provider

OpenAI

Specs

1

Modalities

in textin imageout text

Specs & Platform Price (per 1M tokens)

Quality
Input $10Output $50Cache read $1Cache write 5m $12.5

Recommended Plan

GPT-6 Astra Starter Plan

Pay-as-you-go after top-up; $1 free credit for new users.

Buy Plan

API Endpoint

Model IDopenai/gpt-6-astra

cURL

curl https://intertoken.ai/v1/responses \
  -H "Authorization: Bearer $TOKENPORTAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-astra",
    "input": "Hello!"
  }'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://intertoken.ai/v1",
    api_key="$TOKENPORTAL_API_KEY",
)

resp = client.responses.create(
    model="openai/gpt-6-astra",
    input="Hello!",
)
print(resp.output_text)

Start using this model

Sign up free, get an API key, and make your first call in 30 seconds.