GPT-6.1 Terra
Newopenai/gpt-6.1-terra-20261026
OpenAI: GPT-6.1 Terra processes file, image, and text inputs and generates text outputs. It has a context length of 1,050,000 tokens and supports tools and reasoning. Input pricing is $1 per million tokens, and output pricing is $5 per million tokens. It is not an open-weight model and was released on October 26, 2026.
Tracked, but not yet independently ranked
This model is in the catalog, but we do not yet have enough public benchmark data to place it confidently in quality-focused recommendations. It may still appear in price-based recommendations.
- tool use
- structured outputs
- reasoning
At a glance
Specifications
What the API gives you
- Context window
- 1.1M tokens
- Max output
- 128K tokens
- Input price
- $1 / 1M tokens
- Output price
- $5 / 1M tokens
- Cache read
- $0.050 / 1M tokens
- Modalities
- file, image, text → text
- Knowledge cutoff
- —
- Released
- Oct 26, 2026
Benchmarks
No independent benchmark results are linked to this model yet. We keep it visible while withholding quality claims until usable results arrive.
Task evidence
How broad is the support?
Each status is exact to this model version and the selected task. Official release claims remain provisional.
- Best LLM for Agentic CodingProvisional evidence
Official release evidence found; independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps.
- Best LLM for Computer & Browser UseProvisional evidence
Official release evidence found; independent confirmation is still missing from Berkeley Function Calling or LMArena Agent.
- Best LLM for Image UnderstandingProvisional evidence
Official release evidence found; independent confirmation is still missing from LiveBench Reasoning or LMArena Vision.
- Best LLM for a General AssistantProvisional evidence
Official release evidence found; independent confirmation is still missing from SimpleQA Verified (Epoch AI) or LiveBench Instruction Following.
Official release evidence · provisional
What the launch material actually says
Verbatim claims from the model provider. These help on launch day but do not count as independent confirmation.
“On Agents' Last Exam, a benchmark of professional tasks that includes turning architectural drawings into a 3D model and reviewing an animated film shot by shot to create a time-coded log for a restoration team. At medium reasoning effor…”
OpenAI · Introducing GPT-6.1 Terra | OpenAI“On MMMU-Pro , a benchmark of visual reasoning, GPT-6.1 Terra outperforms GPT-5.6 Terra at every reasoning setting.”
OpenAI · Introducing GPT-6.1 Terra | OpenAI“OSWorld 2.1 tests how well AI agents use desktop apps to complete multistep tasks, such as building a 3D model from a technical drawing. At medium reasoning effort, GPT-6.1 Terra surpasses GPT-5.6 Terra's best score at a fraction of the …”
OpenAI · Introducing GPT-6.1 Terra | OpenAI“On our internal benchmark of error-inducing prompts, the error rate at low reasoning effort fell from 53.6% with GPT-5.6 Terra to 16.7% with GPT-6.1 Terra, a drop of nearly 37 percentage points.”
OpenAI · Introducing GPT-6.1 Terra | OpenAI
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.