GPT-6.2 Astra API
openai/gpt-6.2-astraThe GPT-6.2 Astra API runs OpenAI's newest frontier model for professional documents, scientific analysis, and complex coding, with a 1.05M-token context and image input. Vidgo prices the GPT-6.2 Astra API at $6.40 input and $32 output per 1M tokens, 20% below OpenAI.
GPT-6.2 Astra
OpenAI · chat-completions
Quick start
Send a POST request to /v1/chat/completions with openai/gpt-6.2-astra. Choose JSON or SSE with stream, and receive generated content and usage.
- Endpoint
- POST /v1/chat/completions
- Model ID
- openai/gpt-6.2-astra
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | openai/gpt-6.2-astra |
| messages | Required | A non-empty ordered array of role and content messages; use the system role for system instructions. |
| max_tokens | Optional | A positive integer; API maximum: 128,000 output tokens. Playground: 256–8,192, default 2,048. |
| temperature | Optional | Sampling temperature from 0 to 2; default 1. |
| top_p | Optional | Nucleus sampling probability from 0 to 1; default 1. |
| stream | Optional | Defaults to false for complete JSON; true returns an SSE event stream. |
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-6.2-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-6.2 Astra API FAQ
What is the GPT-6.2 Astra API?
The GPT-6.2 Astra API gives developers access to GPT-6.2 Astra, the frontier model OpenAI released on November 17, 2026 for professional documents, scientific research, and complex coding. It reads text and images, returns text, and supports a 1,050,000-token context with up to 128,000 output tokens. Compared with GPT-6 Astra, OpenAI reports higher benchmark scores at a lower cost per task. You can call it programmatically or try it from the playground above.
How much does the GPT-6.2 Astra API cost?
On Vidgo, the GPT-6.2 Astra API costs $6.40 (1280 credits) per 1M input tokens and $32 (6400 credits) per 1M output tokens. Cache reads cost $0.32 and cache writes $8 per 1M tokens. That is 20% below OpenAI's $8 / $40 list price. Reasoning tokens are billed as output, and you pay only for the tokens each response uses.
Is the GPT-6.2 Astra API available now?
Yes. OpenAI released GPT-6.2 Astra on November 17, 2026, in ChatGPT, Codex, and the API. The GPT-6.2 Astra API is live on Vidgo under the model ID openai/gpt-6.2-astra, and any Vidgo API key can call it.
How do I call the GPT-6.2 Astra API?
Send a POST request to https://api.vidgo.ai/v1/chat/completions with model openai/gpt-6.2-astra and a messages array, or to /v1/responses with an input field. Pass your Vidgo API key as a Bearer token; both endpoints support streaming. The API tab on this page has ready-to-copy cURL, JavaScript, and Python examples.
How is GPT-6.2 Astra different from GPT-6 Astra?
OpenAI reports that GPT-6.2 Astra scores 5.2 points higher on Agents' Last Exam v1.1 and 9 points higher on Terminal-Bench-Science 0.1, each at less than a third of the cost per task, and 6.2 points higher on GDPval v2 with 22% fewer output tokens. The context window and output limit are the same. It is also cheaper: 1280 input and 6400 output credits per 1M tokens on Vidgo, compared with 1600 and 8000 for GPT-6 Astra.
Should I use the GPT-6.2 Astra API or the GPT-6.2 Sol API?
Use the GPT-6.2 Astra API for your hardest work: client deliverables, scientific research, and complex codebase changes. Use the GPT-6.2 Sol API for everyday coding, writing, and agents at one-quarter of Astra's token price. On FrontierCode 2.0, OpenAI reports Sol within 0.5 points of Astra at about one-fifth of the cost, both at max effort.
What is the GPT-6.2 Astra API context window?
GPT-6.2 Astra has a 1,050,000-token context window and returns up to 128,000 output tokens, including reasoning tokens. Its knowledge cutoff is May 18, 2026.
What are the GPT-6.2 Astra benchmarks?
OpenAI reports new highs for GPT-6.2 Astra on Agents' Last Exam v1.1 (5.2 points above GPT-6 Astra), Terminal-Bench-Science 0.1 (9 points above), and its internal GDPval v2 (6.2 points above, with 22% fewer output tokens). On FrontierCode 2.0, which tests merge-ready changes in real codebases, it scores above GPT-6 Astra at a lower cost.
Which reasoning effort levels does the GPT-6.2 Astra API support?
Set reasoning.effort in a Responses request to low, medium, high, xhigh, or max; medium is the default. Use medium for most tasks and xhigh or max for long research or multi-file coding, which use more output tokens.
Does the GPT-6.2 Astra API support function calling?
Yes. Define function tools in a Responses request; your application runs each tool call and sends back the result, and GPT-6.2 Astra plans the next step. It also accepts images, such as charts, slide templates, and scanned pages, as image_url blocks in Chat Completions or image content in Responses.



































