🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
O

GPT-6 Astra

OpenAIModel IDgpt-6-astra
O

GPT-6 Astra

OpenAIModel IDgpt-6-astra

OpenAI introduced GPT-6 Astra (gpt-6-astra) on September 3, 2026. The model is intended for complex reasoning, coding, computer use, research, and document creation, with support for a context window of up to 1,050,000 tokens and up to 128,000 output tokens.

ModeText / Image → Text
Input price$10
Output price$50
Context length1050K tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
OpenAI
Input modality
Text / Image
Output modality
Text
Max output
128K tokens

Pricing

ProviderBilling typePrice summary
O
OpenAI-Balanced
Expression
Input price$10per 1M tokens
Completion price$50per 1M tokens
Cache read price$1per 1M tokens
Cache write price$12.5per 1M tokens
O
OpenAI-Custom
Expression
Input price$10per 1M tokens
Completion price$50per 1M tokens
Cache read price$1per 1M tokens
Cache write price$12.5per 1M tokens

Integration

Code Example

curl http://127.0.0.1:4179/v1/batch \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
openai-batch

Supported Parameters

ParameterTypeDefaultDescription
stringautoControls reasoning depth. Supported values: low, medium, high, xhigh, and max.
integer128000Controls the maximum number of output tokens, including visible output and reasoning tokens.
booleanfalseEnables incremental streaming responses.
array-Provides tools such as function calling, web search, file search, computer use, code interpreter, MCP, and other supported tools.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.