MODELS

One endpoint. The right latency for every request.

Meet Your Competitive Advantage

Serve the model. Choose the latency per request.

Choose fast inference for user-facing work or lower-cost inference for background, evaluation, and long-running agents. Terminal handles routing and scaling behind the API.

Request Access

Get Started

Ship the model. We’ll scale the inference.

Request access to Terminal for open-source and custom model serving.

Request Access

Get Started

See Why Top Finance Teams Use Lateral

Request access to Terminal for open-source and custom model serving.

Request Access

Get Started

Ship the model. We’ll scale the inference.

Request access to Terminal for open-source and custom model serving.

Request Access