Legal research

Model API

A model vendor’s API behind an application you build and own

• ASSESSMENT

  You write and host the application — the interface, the retrieval layer, the database, the access control, the audit log — and call somebody else’s endpoint for the model itself. Two kinds of endpoint sit in this class: a closed model from the vendor that made it (OpenAI, Anthropic, Google Gemini, xAI, DeepSeek, Moonshot, Mistral, Cohere), and an open-weight model served by a managed inference provider (Together, Fireworks, Groq and others).

• ASSESSMENT

  Those two are not interchangeable. A closed model can only be obtained from its vendor or from a cloud that licenses it, so the model and the supplier are one decision. An open-weight model can be moved: the same weights run on a managed endpoint today and on your own GPU later, which makes the provider a swappable component rather than a dependency — and makes the licence, not the contract, the document that governs what you may do with it.

• ASSESSMENT

  It is the shortest path to a frontier model: no GPUs to buy, no capacity to plan, no serving stack to patch, and you can change model with a configuration line. What it costs instead is a per-token bill that scales with use and a dependency on one supplier’s availability, pricing and deprecation schedule.

• ASSESSMENT

  What the supplier sees is the whole prompt: the user's question, the system instructions, and every passage your retrieval layer attached to it — which is usually the most sensitive part, because retrieval is what puts internal documents into the request. For a brief that involves no sensitive data was identified, that is the attribute to check first. What stays yours is everything else: the application, the retrieval index, the identity system, the logs, and the record of who asked what.

• ASSESSMENT

  Nothing about a supplier's handling of your data is assumed here. Before real content goes near an endpoint, verify against that supplier's own documents: the data processing agreement, and that it covers the API rather than only the consumer product; whether zero-data-retention or an equivalent no-logging mode is available on your account, and on which endpoints; the default retention period for prompts and outputs, and what triggers human review; the region the request is served from, and whether that is a commitment or a routing preference; the current subprocessor list and how you are notified when it changes; the supported-countries page, which decides whether you may use the service at all.

• RECOMMENDATION

  Take this route when the workflow is yours but the model is not the differentiator, and your team can build and run an application. Your stated technical capability is "unknown", which is the attribute this option most depends on. Where the same model is available inside your own cloud account, compare it against private cloud before committing — the application is identical and only the tenancy of the model changes.

• RECOMMENDATION

  Recommended for this brief: the workflow is yours to build, nothing in the brief requires an unusual data boundary, and a metered endpoint removes the capacity planning entirely, given you did not say who would run this, on data sensitivity, no sensitive data was identified, no existing cloud account was named, and you did not ask for local processing.