GPT-6 Astra API
openai/gpt-6-astraGPT-6 Astra turns text and image input into analysis, code, and detailed answers for complex professional work. Its 1,050,000-token context window and configurable reasoning keep large codebases, research evidence, and multi-step instructions in view.
GPT-6 Astra
OpenAI · chat-completions
Quick start
Send a POST request to /v1/chat/completions with openai/gpt-6-astra. Choose JSON or SSE with stream, and receive generated content and usage.
- Endpoint
- POST /v1/chat/completions
- Model ID
- openai/gpt-6-astra
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | openai/gpt-6-astra |
| messages | Required | A non-empty array of conversation messages. |
| max_tokens | Optional | Limits output tokens for this response. |
| temperature | Optional | Sampling temperature; the playground allows 0–2. |
| top_p | Optional | Nucleus sampling probability; the playground allows 0–1. |
| stream | Optional | Returns an SSE event stream when true. |
Response and usage
Successful responses include generated content and usage. Billing settles from actual input, output, and cache tokens.
Streaming
Set stream: true to read SSE. Finalize usage accounting from the terminal usage event.
curl --request POST \
--url https://api.vidgo.ai/v1/chat/completions \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "openai/gpt-6-astra",
"messages": [
{
"role": "user",
"content": "Explain why deterministic retries matter in distributed systems."
}
],
"max_tokens": 1024,
"temperature": 1,
"top_p": 1,
"stream": false
}'Keep API keys on the server. Never expose them in browser code or public repositories.
Continue with
Related Models
GPT-6 Astra API — Frequently asked questions
What is the GPT-6 Astra API?
GPT-6 Astra is an OpenAI model for complex reasoning and agent workflows. It turns text and image context into analysis, code, and detailed answers across long tasks. Its 1,050,000-token context window and configurable reasoning help carry requirements and evidence through multiple steps. You can call it programmatically or try it from the playground above.
How much context can GPT-6 Astra use?
GPT-6 Astra has a 1,050,000-token context window and a maximum output of 128,000 tokens. Put related source files, documents, and instructions into the request so the model can analyze their connections.
How does GPT-6 Astra reason over images?
GPT-6 Astra can use text and image input together. In a Responses request, place written instructions before image content to focus its analysis of screenshots, diagrams, charts, or interfaces.
Which reasoning levels can GPT-6 Astra use?
GPT-6 Astra offers low, medium, high, xhigh, and max reasoning effort. Set reasoning.effort in a Responses request to choose the depth suited to the task.
How can GPT-6 Astra help with large codebases?
GPT-6 Astra can connect repository files, architecture constraints, and test evidence across a long coding task. Provide the target behavior, relevant files, and verification criteria when requesting a plan or code review.
Which tools can GPT-6 Astra use in agent workflows?
GPT-6 Astra works with Responses tool configurations for web search, file search, code interpretation, computer use, and MCP workflows. Specify the tools and task boundaries in the request so each step has a clear purpose.
How does GPT-6 Astra approach browser tasks?
GPT-6 Astra combines visual understanding and multi-step planning for browser and desktop workflows. Give it the intended outcome, the actions available through configured tools, and the evidence to verify after each step.
How many output tokens can GPT-6 Astra generate?
The API supports up to 128,000 output tokens for GPT-6 Astra. Set max_tokens with Chat Completions or max_output_tokens with Responses; the on-page Playground provides a 256–8,192-token control for interactive trials.