Liner has launched the Liner Model API, an intelligent routing system that can reduce enterprise AI costs by over 50% by automatically directing requests to the most cost-efficient models capable of handling each task. The API eliminates the need for developers to manually select and benchmark models, streamlining the process and cutting expenses.
TL;DR
- Liner Model API reduces AI costs by routing requests to the most cost-efficient models, saving over 50% compared to frontier models.
- The API handles a wide range of requests, from everyday questions to complex tasks, without requiring developers to switch between models manually.
- Liner Model API is priced at $1 per 1 million input tokens, $6 per 1 million output tokens, and $0.10 per 1 million cached input tokens, with potential savings of at least 50% compared to similar models.
What happened
Liner, an AI agent solutions company, has introduced the Liner Model API, a model-routing API designed to help companies reduce the cost of running AI applications. The API automatically routes each request to the most cost-efficient model capable of handling the task, eliminating the inefficiency of paying frontier-model prices for routine AI workloads.
The Liner Model API was refined through real-world usage and controlled benchmark testing to assess model performance and cost efficiency. Following the deployment of Liner Orchestrator, Liner reported a reduction of more than 50% in internal token expenses in August 2026 compared to the first half of the year.
The API is designed to handle a wide range of requests, from everyday questions to more demanding workloads involving coding, reasoning, and deep research. It selects one model for each request, avoiding the additional token costs associated with multi-model approaches.
Why it matters
For developers and startups, the Liner Model API simplifies the process of optimizing AI costs by automating model selection. This allows developers to focus on building applications without the constant operational headache of benchmarking and switching between models.
For investors, Liner's innovative approach to cost efficiency in AI applications positions the company as a competitive player in the AI market. The potential savings of at least 50% compared to similar models make the Liner Model API an attractive option for enterprises looking to reduce AI costs.
The competitive angle lies in Liner's ability to offer a more cost-effective solution compared to frontier models like Claude Sonnet 5 and GPT-5.6-Terra. The API's benchmark results and pricing comparisons provide developers with the data they need to estimate potential savings based on their current model spend.
Key facts
- Liner Model API is priced at $1 per 1 million input tokens, $6 per 1 million output tokens, and $0.10 per 1 million cached input tokens.
- The API can cost at least 50% less than comparable models in the same performance tier, according to Liner.
- Liner reported a reduction of more than 50% in internal token expenses in August 2026 compared to the first half of the year.
- The API handles a wide range of requests, from everyday questions to complex tasks involving coding, reasoning, and deep research.
- Liner Model API is accessible through Liner's developer platform, where developers can create an API key, review benchmark results, and use a cost-savings calculator.
- Benchmark results compare Liner Model API's performance against frontier models including Claude Sonnet 5 and GPT-5.6-Terra.
- Liner is an evidence-first AI research platform designed for people who need answers they can verify, prioritizing citation-backed outputs and source traceability.
Context
In the broader AI landscape, cost efficiency is a significant concern for enterprises and developers. The Liner Model API addresses this by automating the process of selecting the most cost-efficient models for each task, reducing the need for manual intervention and optimization.
The launch of the Liner Model API comes at a time when the demand for AI applications is growing rapidly. Enterprises are increasingly looking for ways to reduce costs without compromising on performance, making solutions like the Liner Model API highly relevant.
Liner's focus on evidence-first AI research aligns with the growing need for trustworthy and verifiable AI outputs. As AI becomes more integrated into various industries, the ability to quickly audit claims and evaluate information quality is becoming increasingly important.
