AI Agent StoreOpenAI · Provider verified
GPT-6.1 Terra
Try Terra for reading screenshots, comparing product images, working in apps or revising text. Its standard token prices are half Sol’s; compare the results on your own tasks before switching.
Released 2026-10-26 · Catalog added 2026-10-26 UTC · Checked 2026-11-03. Catalog addition and provider launch are separate dates.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on your own tasks before switching; results for another version or thinking setting may not apply.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact catalog ID: openai/gpt-6.1-terra. Use gpt-6.1-terra for OpenAI’s native API. Accepts text and images and returns text. Tool calling requires the Responses API; Chat Completions supports requests without tools. Audio and video input are not supported.
Available thinking settings: none, low, medium, high, xhigh, max. We do not yet have comparable independent results for these settings. The documented OpenAI native API default is medium when effort is omitted. A default is not a recommendation for every task.
Fast costs twice Standard; Batch and Flex cost half Standard. These are service options for the same model. No matched independent result or measured response time is available here.
The 1,050,000-token combined budget allows at most 922,000 input and 128,000 output tokens. Thinking and the answer share the output allowance.
Native Standard costs $1 input, $0.05 cached input and $5 output per million tokens. Above 272,000 input tokens, the whole request costs twice the input/cache rate and 1.5 times the output rate. Cache writes cost $1.25 for 30-minute retention or $2.50 for 12-hour retention, before the long-input adjustment. Allow for retries and any tool fees. Models that think before answering may also charge for that work.
Provider release and specifications ↗
Inspect the exact catalog model ↗
More setup and licensing details ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗