Liner Offers Model Routing API With OpenAI Compatibility

Liner detailed its Model API on its website, saying the service automatically selects an AI model for each request through its Liner Orchestrator. The company claims frontier level performance at up to 50% lower cost, based on results across benchmarks including HLE, MedQA, MathBench, SciCode, AIME and FinQA.

The API works with existing OpenAI SDKs, prompts, streaming and tool calls. Developers change the base URL and API key, then select liner-mark-1.0 as the model. Liner uses one model per request but does not disclose which underlying model processed it.

Liner lists Mark 1.1 pricing at $1 per million input tokens, $5 per million output tokens and $0.10 per million cached input tokens. The company says it does not use API data for model training by default and offers configurable data retention, operation across multiple regions and a 99.9% uptime service level agreement for Enterprise plans.