Vercel adds OpenAI's GPT-6.1 Terra to AI Gateway for visual and desktop tasks

Vercel has made OpenAI's GPT-6.1 Terra available on its AI Gateway. According to Vercel, the model is built for fast visual reasoning, computer use and writing, and improves on the previous Terra model in visual reasoning, factual accuracy and coding.
- OpenAI's GPT-6.1 Terra is now available on Vercel's AI Gateway as openai/gpt-6.1-terra.
- The model targets visual reasoning, computer use and writing, and improves on the previous Terra in visual reasoning, factual accuracy and coding.
- It accepts text and images, returns text, and has a context window of more than 1M tokens.
- A fast mode for latency-sensitive work is available as openai/gpt-6.1-terra-fast.
- Vercel says AI Gateway reflects provider pricing with no markup and no platform fee on inference.
What GPT-6.1 Terra is designed for
Vercel describes GPT-6.1 Terra as a fast model aimed at high-volume work in documents and desktop apps. The examples it gives are filling out forms, interpreting technical drawings and entering invoice details into accounting software.
The model takes text and images as input and returns text. Its context window is more than 1M tokens. Compared with the earlier Terra model, the changelog says it is better at visual reasoning, factual accuracy and coding.
There is a limit on the coding side. Vercel notes that OpenAI still recommends its larger GPT-6 models for the most complex coding tasks, so Terra is positioned as a fast, high-throughput option rather than a replacement for the bigger models.
Features and how to call it
GPT-6.1 Terra supports several features developers commonly rely on:
- Configurable reasoning effort
- Structured outputs
- Tool calling
- Implicit and explicit prompt caching
For latency-sensitive work, a fast mode is available under the name openai/gpt-6.1-terra-fast. The standard model is called with openai/gpt-6.1-terra.
It works with the AI SDK, the OpenAI-compatible Chat Completions API, the Responses API, and coding agents connected to AI Gateway. Vercel's example uses the AI SDK's streamText function with the model name above and a prompt asking for a one-page proposal on migrating a docs site to Next.js.
To use the model in coding agents such as Codex and Cursor, Vercel says to install the latest Vercel CLI and run npx vercel ai-gateway setup, then select openai/gpt-6.1-terra in the agent. The model can also be tried in the model playground.
What AI Gateway offers
AI Gateway is Vercel's unified API for calling models. According to Vercel, it tracks usage and cost and lets teams configure retries, failover and performance optimizations for higher-than-provider uptime. It also includes custom reporting, Zero Data Retention support, budgets for API keys and routing rules.
On pricing, Vercel says AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.
For developers already routing traffic through AI Gateway, the addition means GPT-6.1 Terra can be used by changing the model name, without a separate integration. Teams with document-heavy or desktop-automation workloads get a faster option to test, while those with the hardest coding jobs are pointed by OpenAI toward its larger GPT-6 models.
Vercel: GPT-6.1 Terra now available on AI Gateway


