Vercel's AI Gateway adds OpenAI's GPT-6.1 Terra model

Vercel says GPT-6.1 Terra, from OpenAI, is a fast model that improves on the previous Terra model in visual reasoning, factual accuracy and coding. It suits high-volume tasks such as filling out forms, interpreting technical drawings and entering invoice details into accounting software. OpenAI still recommends its larger GPT-6 models for the most complex coding work.

The model accepts text and images as input and returns text, with a context window of more than 1M tokens. It supports configurable reasoning effort, structured outputs, tool calling, and implicit and explicit prompt caching. A fast mode for latency-sensitive work is available as openai/gpt-6.1-terra-fast, and the model works with the AI SDK, both the Chat Completions and Responses APIs, and coding agents connected to the gateway.

AI Gateway offers a unified API for calling models, with usage and cost tracking, retries, failover and routing rules. Vercel says it passes through provider pricing with no markup and charges no platform fee on inference, including Bring Your Own Key requests. Coding agents can be set up with npx vercel ai-gateway setup.

Agent builders can point document, form and invoice workloads at GPT-6.1 Terra through one gateway and use the fast variant where latency matters. Teams that need stronger coding output should still compare it against the larger GPT-6 models that OpenAI recommends for those tasks. Check the model's details on Vercel before relying on its tool calling or prompt caching behavior in production.