Agentic AIThe briefing
AI-generated illustration
OpenAI released GPT-6.1 Terra, a fast model for computer use and everyday work at $1 per million input tokens and $5 per million output tokens.
Agents that click through apps and fill in forms are useful but expensive to run at volume. On October 26, OpenAI released GPT-6.1 Terra, a mid-tier model built for that kind of work: reading screens, operating software, interpreting drawings and writing clearly.
Standard API pricing is $1 per million input tokens and $5 per million output tokens, which OpenAI says is half the price of GPT-5.6 Terra and GPT-6.1 Sol. The model has a context window of about 1.05 million tokens. It is available in ChatGPT Work and Codex for Plus, Pro, Enterprise and Edu users, and in the API as gpt-6.1-terra. AWS made it available on Amazon Bedrock the same day.
OpenAI reports that Terra scores 15 points higher than GPT-5.6 Terra on its Agents' Last Exam benchmark, performs on par with GPT-6 Astra there at a tenth of the price per token, and finishes tasks more than three times faster. It also reports a lower error rate on hard factual prompts. These are OpenAI's own numbers.
Computer-use agents are usually limited by cost per task and by mistakes, not by raw ability. Test Terra on your own forms or screens, record cost and error rate per finished task, and keep a human approval step before anything is submitted.
Halving model cost can turn a pilot that was too expensive into a viable one. Recalculate your numbers per completed task, including review time, before deciding.
Pick one high-volume, low-risk screen task, such as entering invoice details, and run a supervised trial for a week.
Source material behind this briefing. Our practical implications are Ashlr’s interpretation.
This briefing was prepared with AI assistance from the linked sources. The analysis may include interpretation; consult the original sources for complete context. Cover artwork is illustrative.
OpenAI launched GPT-6.1 Terra, a mid-tier model for computer use and visual reasoning tasks. It costs roughly half as much as GPT-5.6 Terra while running faster on agent workflows.
Agentic AIThe briefing
AI-generated illustration
Overnight into October 27, Phantom began recording each run's routing decision, Ashlr Stack added a merge-queue gate, and ashlr-plugin raised its MCP SDK floor.
Agentic AIAshlr release
AI-generated illustration
October 26 brought releases of Locus 0.5.2, Ashlr Stack 0.2.2 and ashlr-plugin 1.37.1, plus opt-in routing in Phantom that tries local models first.
