GPT-6.1 Terra is now available on Birost

OpenAI released GPT-6.1 Terra today, and you can call it through Bifrost right now. Change one model string. Your routing, fallbacks, budgets, guardrails and logs keep working as they are.

Terra is OpenAI's new fast, low-cost model for computer use, visual reasoning and everyday writing. It costs half as much as GPT-6.1 Sol and, by OpenAI's numbers, matches GPT-6 Astra on agent benchmarks at a tenth of the price.

Why Terra

Terra is built for high-volume agentic work where cost and latency matter more than peak reasoning. OpenAI reports:

• Half the price. Standard API rates are 50% lower than both GPT-6.1 Sol and GPT-5.6 Terra.
• 3x faster. Terra finishes tasks more than three times faster than GPT-6 Astra and GPT-6.1 Sol.
• Astra-level agents. On Agents' Last Exam at medium effort, Terra matches GPT-6 Astra at one-tenth the price per token, and beats GPT-5.6 Terra by 15 points.
• Better at the terminal. At maximum effort, Terra solves 50.3% of Terminal-Bench 4.0, up from 21.5% for GPT-5.6 Terra.
• Fewer errors. On OpenAI's error-inducing prompts, the low-effort error rate fell from 53.6% to 16.7%.
• Large context. It supports 1.05M tokens in and 128K tokens out, with text and image input.

For the hardest coding tasks, OpenAI still recommends GPT-6.1 Sol or GPT-6 Astra. Bifrost makes the split easy: send the bulk of traffic to Terra and route the hard cases to Sol.

Pricing

At standard rates, Terra costs $1 per million input tokens and $5 per million output tokens.

Tier	Input ($/1M)	Cached input ($/1M)	Output ($/1M)
Standard	1.00	0.05	5.00
Flex	0.50	0.025	2.50
Batch	0.50	0.025	2.50
Fast	2.00	0.10	10.00

Requests with more than 272K input tokens are billed at a higher rate. Full per-model rates are on the Bifrost datasheet.

Supported providers

Bifrost serves Terra through every provider that hosts it. Pick one with the model prefix, or let Bifrost load-balance across them.

Provider	Bifrost model string	Notes
OpenAI	openai/gpt-6.1-terra	Standard, Flex, Batch and Fast tiers
OpenRouter	openrouter/openai/gpt-6.1-terra	Same rates as OpenAI Standard

As Azure OpenAI, Amazon Bedrock and Google Vertex AI add Terra, it will show up in Bifrost under their prefixes with no gateway upgrade. Bifrost refreshes its model list live.

Get started

Call Terra through Bifrost with the Responses API, the same way OpenAI's official examples do. Point the OpenAI SDK at your Bifrost endpoint and change the model string:

Or with curl:

Responses is the API to use for OpenAI's hosted tools, such as computer use, web search, code interpreter and MCP. Chat Completions also works if your stack already uses it.