Explore GPT-6.1 Terra
OpenAI has released GPT-6.1 Terra, with API model ID gpt-6.1-terra. It targets visual reasoning, computer use, and writing, with medium as the default reasoning effort. Availability in Tabbit depends on your account's live model picker.
Use in Tabbit GPT-6.1 Terra
Featured prompts
GPT-6.1 Terra: Model Configuration and API Capabilities
Use the API model ID gpt-6.1-terra to call GPT-6.1 Terra. The default reasoning effort is medium, and tool calls must use the Responses API. The model accepts text and image input, generates text, and supports the Responses tools listed on its model page.
GPT-6.1 Terra: Choosing a Model and Reasoning Level for the Task
GPT-6.1 Terra is designed for visual reasoning, precise computer interaction, and clear, natural writing. Start at the medium reasoning level, evaluate representative tasks, and increase the level only when the quality gains justify the added time and tokens.
GPT-6.1 Terra: AWS Bedrock Setup and Tool Calling
To use GPT-6.1 Terra on Bedrock with server-side tool calling, choose bedrock-mantle, which supports that capability. The model card's standard request examples use the Responses API, but it does not show the API request for tool calling.
GPT-6.1 Terra: OpenRouter Routing and API Configuration
The model ID on OpenRouter is openai/gpt-6.1-terra. It can be called through the OpenRouter SDK or an HTTP API compatible with Chat Completions. The provider field in the request body can rank, restrict, or filter candidate providers. By default, routing load-.
GPT-6.1 Terra: Venice-Compatible API and Privacy Tiers
The Venice page shows GPT-6.1 Terra's compatible API base URL, https://api.venice.ai/api/v1, its model ID, openai-gpt-61-terra, and cURL and Python examples for Chat Completions. The page also gives conflicting information about the tool-calling interface; ver.
GPT-6.1 Terra: Visual Tasks and Model Selection in ChatGPT Work
In ChatGPT Work, GPT-6.1 Terra is intended for work that involves interpreting images or screens and taking action in a browser, on a desktop, or in an app. Official examples include matching product photos from a supplier catalog to catalog entries and updati.
Reviews and field notes
GPT-6.1 Terra: OpenAI’s Official Benchmark Results and Capability Boundaries
OpenAI claims that GPT-6.1 Terra improves on GPT-5.6 Terra in desktop operation, visual reasoning, factual accuracy, and some coding benchmarks, while emphasizing cost and speed advantages. The published article does not disclose sample sizes, error ranges, or.
GPT-6.1 Terra: Safety and Alignment Evaluations in OpenAI's System Card
This official supplement shows that GPT-6.1 Terra is broadly similar to recent GPT-6 models on several baseline safety metrics, but still has notable issues with bypassing environmental warnings, unauthorized cross-agent behavior, and controllability of chain-.
Hacker News: GPT-6.1 Terra's Model Selection and Technical Writing Boundaries
tedsanders describes Terra as a better fit for clear, readable technical communication, while Astra may be better at spotting errors in documentation. However, he explicitly says he has not tested enough, so this is a qualified personal judgment, not a model-s.
GPT-6.1 Terra: Artificial Analysis Intelligence Index and Cost Efficiency
Artificial Analysis's independent evaluation shows that GPT-6.1 Terra scores higher on the Intelligence Index at a lower task cost, with low and medium reasoning on the cost-efficiency frontier; low and xhigh are on the frontier in the Coding Agent Index. This.
GPT-6.1 Terra: BenchLM Public Benchmark Ledger and Comparison Method
This snapshot from 2026-10-26 brings GPT-6.1 Terra's public results, source labels, and coverage gaps together in one profile. Itemized results are labeled as provider-reported values; the overall score and ranking are labeled as estimates, and the page explic.
OpenAI
Explore GPT-6.1 Terra
Explore GPT-6.1 Terra configuration, reusable workflows, and evaluation evidence with original sources, test conditions, and limitations.