Skip to content
OpenAIgpt-6-astra

GPT-6 Astra

OpenAI's most capable model for the hardest end-to-end work.

GPT-6 Astra is OpenAI's flagship, built for work that has to run from start to finish on its own: deep reasoning, heavy tool use, and long, complicated tasks.

  • Hardest problems
  • End-to-end work
  • Deep reasoning

Model details

Context window
1.1M tokens
Max output
128K tokens
Input
Text, images
Output
Text
Capabilities
Reasoning, Vision, Tool calling, Streaming, JSON output
Interfaces
OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Pricing

Per 1M tokens. The Inferray price is what you are charged — no gateway fee is added on top of it.

GPT-6 Astra pricing: the provider's list price and the Inferray price for each.
MetricList priceYou pay
Input$10$8.00
Cached input$1$0.80
Output$50$40.00

Why teams pick it

  • OpenAI's most capable model for demanding work
  • Reasoning and tool use built in, with adjustable effort
  • Over 1M tokens of context

Call GPT-6 Astra

GPT-6 Astra answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

/v1/chat/completionsOpenAI-style Chat Completions · openai SDK or plain HTTP
curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "messages": [{"role": "user", "content": "ship it"}]
  }'
/v1/messagesAnthropic-style Messages · @anthropic-ai/sdk SDK or plain HTTP
curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "ship it"}]
  }'
/v1/responsesOpenAI-style Responses · openai SDK or plain HTTP
curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "input": "ship it"
  }'

More from OpenAI