← All Models
GPT-6 Astra
OpenAI's model for complex reasoning, coding, research, and document work. Text and image input, 1,050,000-token context, 922,000-token maximum input, and 128,000-token maximum output including reasoning. Input/cache rates double and output rates increase 1.5x above 272K input tokens.
Web Search
Code Interpreter
File Search
Specifications
| Provider | OpenAI |
| Category | Text |
| Context window | 1.1M tokens |
Pricing (Starter tier)
1,300.00 credits / 1M input tokens
6,500.00 credits / 1M output tokens
Above 272K input: 2x input/cache rates and 1.5x output rates
Higher tiers get volume discounts. See tiers
Quick Start
curl -N https://query.genx.sh/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-6-astra","messages":[{"role":"user","content":"Review this architecture."}],"reasoning_effort":"high","max_tokens":8192,"stream":true}'
Parameters
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
prompt |
string | required | — | The input text prompt |
system_prompt |
string | optional | — | System instructions |
max_tokens |
number | optional | — | 16 to 128000 output tokens, including reasoning |
reasoning_effort |
string | optional | low |
low, medium, high, xhigh, or max. none and minimal are not supported. |
image_url |
string | optional | — | Image URL to analyze |
tools |
array | optional | — | Built-in web_search, code_interpreter, file_search |
Availability
GPT-6 Astra is available in the GenX Pro App and via the GenX Router API.