GPT-6.1 Terra API
openai/gpt-6.1-terraGPT-6.1 Terra turns text, screenshots, photos, and technical drawings into proposals, form entries, and structured answers, with a 1.05M-token context and 128K-token replies. Choose reasoning effort from none to max to trade response time for depth on each request.
GPT-6.1 Terra
OpenAI · chat-completions
Quick start
Send a POST request to /v1/chat/completions with openai/gpt-6.1-terra. Choose JSON or SSE with stream, and receive generated content and usage.
- Endpoint
- POST /v1/chat/completions
- Model ID
- openai/gpt-6.1-terra
- Protocol
- Chat Completions
Request fields
| Field | Requirement | Description |
|---|---|---|
| model | Required | openai/gpt-6.1-terra |
| messages | Required | A non-empty ordered array of role and content messages; content can combine text and image_url blocks. |
| max_tokens | Optional | A positive integer; API maximum: 128,000 output tokens, including reasoning tokens. Playground: 256–8,192, default 2,048. |
| temperature | Optional | Sampling temperature; the playground sends 1. |
| top_p | Optional | Nucleus sampling probability; the playground sends 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-6.1-terra",
"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-6.1 Terra API FAQ
What is the GPT-6.1 Terra API?
GPT-6.1 Terra is an OpenAI model that turns text and images into clear written answers, form entries, and document drafts, and it is the fast, lower-cost member of the GPT-6.1 family. OpenAI positions it for everyday work such as proposals, forms, technical drawings, and invoices. It offers six reasoning levels from none to max within a 1,050,000-token context. Use the API tab for Responses and Chat Completions examples, or try a conversation in the Playground.
What are the GPT-6.1 Terra context limits?
GPT-6.1 Terra has a 1,050,000-token context window with up to 922,000 input tokens and 128,000 output tokens. Reasoning tokens count toward the output limit. Its knowledge cutoff is 1 June 2026.
Which GPT-6.1 Terra reasoning effort should I use?
Set reasoning.effort to none, low, medium, high, xhigh, or max; medium is the default. None and low suit quick drafting and extraction, while high and above help with multi-step tasks. Higher levels use more output tokens.
Should I pick GPT-6.1 Terra or GPT-6.1 Sol?
Both share the 1.05M-token context and accept text and images. OpenAI prices Terra at half of Sol and says it is over three times faster on its computer-use tasks. OpenAI recommends GPT-6.1 Sol or GPT-6 Astra for the hardest coding and research.
What does GPT-6.1 Terra cost on Vidgo?
Input costs $0.80 (160 credits) and output costs $4.00 (800 credits) per 1M tokens, with reasoning tokens billed as output. OpenAI's Standard price is $1 input and $5 output per 1M tokens.
Can GPT-6.1 Terra analyze screenshots and drawings?
Yes. Send screenshots, product photos, charts, or technical drawings together with your question, using image_url blocks in Chat Completions or image content in Responses. The model replies in text, for example with extracted values, a checklist, or a written summary.
How did GPT-6.1 Terra improve over GPT-5.6 Terra?
OpenAI reports 50.3% on Terminal-Bench 4.0 at max effort, compared with 21.5% for GPT-5.6 Terra. Its Standard API price is also 50% lower than GPT-5.6 Terra's, so scoped coding and terminal tasks cost less per run.