LegalOn halves Codex costs while maintaining development speed

LegalOn halves Codex costs while maintaining development speed | OpenAI

October 8, 2026

LegalOn halves Codex costs while maintaining development speed

LegalOn cut costs by 65% while maintaining development speed by matching Astra, Sol, and Luna to tasks and managing budgets strategically.

Results

-20%

Cost reduction in mature business areas

Results

-65%

Reduction in estimated daily costs

LegalOn Technologies offers Professional AI globally, using AI to support legal work and other key business functions. By combining domain expertise with AI, it enables people to focus on complex judgments and decisions. Its goal is AI-driven management that improves the quality and speed of business decision-making.

This approach extends beyond its products to making the organization itself AI-native. The company integrated Codex into its development process and expanded adoption across the organization through day-to-day use.

As adoption took hold, a new challenge emerged: cost control. Unlimited use of high-performance models could drive up spending, while blanket restrictions risked undermining the productivity gains AI had enabled.

How could it reduce costs without slowing development? LegalOn Technologies addressed this challenge by selecting among GPT‑6 (Astra, Luna) and GPT‑6.1 Sol based on task complexity and development stage, and aligning budgets with each business’s stage of growth. The company halved costs while maintaining development speed.

Optimizing models to maintain development speed and reduce costs

The company initially gave developers unlimited access to its main model, GPT‑5.5 in Fast mode. They expanded its use to design, implementation, and everyday work, learning through experimentation how best to divide responsibilities between people and AI.

Continuing to use high-performance models without limits, however, would inevitably exceed the annual budget. The company's AI-powered Development CoE (AID CoE) began developing guidelines for model selection. AID CoE tested and monitored models, while managers shared its findings with their teams. This enabled each engineer to independently choose the most suitable model for each task.

Matching models to tasks and allocating resources strategically

The new guidelines shifted the company from using the highest-capability model for every task to choosing the right model for the job. Teams started with a lightweight model and moved to more capable models as task complexity increased.

To support governance, the company also introduced system controls through administrator settings, with monthly usage limits for departments and individuals. AID CoE monitors usage and adjusts limits as business needs require.

Internal testing under these controls helped make the selection criteria more specific. GPT‑6 Luna, the lightest model, handles code implementation with clear requirements; GPT‑6.1 Sol supports standard design, data analysis, and document preparation; and GPT‑6 Astra, the most capable model, handles advanced judgment, including architecture design. Matching models to tasks gradually became a shared practice across teams.

Choosing among three models for different tasks

GPT-6 Luna

Everyday execution and implementation; running everyday automations; delegating relatively simple tasks and analysis; code implementation, mainly as a subagent.

GPT-6.1 Sol

Standard design and analysis; relatively simple software design; routine numerical analysis and document creation; tasks requiring shorter completion times than with Luna.

GPT-6 Astra

Complex analysis, design, and orchestration; complex analysis and document creation; complex software design; coordinating agents as the orchestrator.

Alongside model selection, the company began restricting Fast mode by default, allowing individual requests only when needed. Although the change raised concerns about development speed, teams used approaches such as running tasks in parallel to maintain performance and transition smoothly.

It also introduced budget caps for AI spending at the department, group, and individual levels. The established LegalOn business was asked to improve cost efficiency by up to approximately 20%, while new businesses in the launch phase received generous budgets to encourage active use of AI.

Yuta Tokitake, Senior Engineering Manager at LegalOn Technologies, explains that new businesses prioritized business speed over cost efficiency. The aim was to use AI extensively to increase output and ultimately drive business growth.

Together, model selection, feature restrictions, and budgets tailored to each business reduced estimated daily costs by approximately 65%. This approach kept the overall budget under control while directing resources toward businesses the company wanted to grow.

Results at a glance

Model optimization and strategic resource allocation delivered the following results:

• A shift from using the most capable model for every task to selecting GPT‑6 Astra, GPT‑6.1 Sol, or GPT‑6 Luna based on task complexity and development stage.
• Development performance maintained after restricting Fast mode by default, supported by team practices such as parallel task execution.
• Budget caps that combined approximately 20% greater efficiency in mature businesses with active investment in new businesses.
• A 65% reduction in estimated daily costs compared with GPT‑5.5 by choosing among GPT‑6 and 6.1 models.

Measuring the true ROI of AI investment through feature releases

Through model optimization, the company reduced costs without sacrificing development speed or quality. Teams are also seeing AI steadily shorten the cycle from development to release.

But the company is looking further ahead. Does faster development alone make AI investment a success? The connection between faster development and customer value remained unclear. “It is almost a given that AI can accelerate system development and updates,” says Tokitake. “What we really want to understand is whether that faster development actually translates into value for customers.”

This question prompted the company to develop its own metric, shifting the basis for evaluating AI investment from development speed and usage volume to customer value.

Tokitake explains: “When using AI, we can track the cost of individual tasks, but the total cost of a complete piece of work—a feature release—often remains a black box. So we designed the measurement around...