GPT-6.1 Terra: OpenAI halves the cost of its mid-tier agentic model

On October 26, 2026, OpenAI introduced GPT-6.1 Terra, a fast mid-tier agentic model with API prices cut in half to $1 per million input tokens and $5 per million output tokens.

Compiled by Sergey KostenchukPublished 2026-10-26Updated 2026-10-27

2026-10-26 Coding OpenAI

🛠 GPT-6.1 Terra: OpenAI halves the cost of its mid-tier agentic model

OpenAI released GPT-6.1 Terra on October 26 — a fast mid-tier model for agentic scenarios, computer use, and everyday coding. API prices are half those of GPT-5.6 Terra: $1 per million input tokens, $5 per million output tokens, and $0.05 for cache. The API ID is gpt-6.1-terra.

🌍 The low-cost agentic tier makes routine automation — forms, invoices, and app screens — cost-effective for high-volume workloads. According to OpenAI's vendor benchmarks: 50.3% versus 21.5% for GPT-5.6 Terra on Terminal-Bench 4.0, and a 15 percentage point increase on Agents' Last Exam at one-third the cost per task.

👤 Terra is already available in ChatGPT Work and Codex for Plus, Pro, Enterprise, and Edu users: the same usage limits now cover more tasks. In the API, the reasoning.effort none option enables temperature and top_p.

Source 1: https://openai.com/index/introducing-gpt-6-1-terra/ Source 2: https://developers.openai.com/api/docs/models/gpt-6.1-terra

Sources