GPT-6 Astra (Fast)

openai/gpt-6-astra-fast

A chat model with a 1.1M-token context window, at $21.00 per million input tokens and $105.00 per million output tokens.

Details

Maker: openai
Kind: Chat
Context window: 1,050,000 tokens
Max output: 128,000 tokens
Input: $21.00 per million tokens
Cached input: $2.10 per million tokens, 90% off
Cache write: $26.25 per million tokens
Output: $105.00 per million tokens
Capabilities: Reasoning, tool use, vision, file input, web search, fast
Takes: Text, image, pdf
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-09-04
Newer model: openai/gpt-6.1-solReleased later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-astra-fast",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model