# One model API for your apps and tools

Canonical URL: https://openorange.ai/model-api/
Updated: 2026-09-27

Call models through your OpenOrange instance with OpenAI- and Anthropic-compatible APIs. Use Claude Code, the OpenAI and Anthropic SDKs, or your own app, with keys and usage in one place.

Every OpenOrange instance has its own model API. Create an API key, point an OpenAI- or Anthropic-compatible client at your instance, and every call is attributed, priced, and shown next to your agents’ usage.

## Key capabilities

- OpenAI-compatible Chat Completions and Responses endpoints.
- An Anthropic-compatible Messages endpoint, so Claude Code and the Anthropic SDKs work.
- Keys for every model or only the models you choose, revocable at any time.
- Every call shows its key, model, tokens, and cost.

## Use the clients you already have

OpenAI-compatible clients call Chat Completions or Responses. Anthropic-compatible clients, including Claude Code and the Anthropic SDKs, call Messages. Embeddings, transcription, speech, and image models use the same API when your instance offers them.

## Keys you control

Create a key for a service, a script, or a person. Allow every model, including models added later, or only the models you select. The secret is shown once, and a revoked key stops working immediately.

## Usage and billing in one place

API calls take the same path as your agents’ calls, so they appear on the Requests and Billing pages with their model, tokens, and cost. Calls on OpenOrange models draw from your prepaid balance; calls on your own provider keys are free.

## The same models as your agents

The API offers the models configured for your instance, whether OpenOrange provides them or you connect your own provider keys. Agents, coding sessions, and your own apps share one model catalog and one usage record.

## Questions

### Does Claude Code work with OpenOrange?

Yes. Create an API key on your instance and point Claude Code at your instance’s Anthropic-compatible endpoint. Its calls appear in your usage like any other.

### Which models can I call?

The models configured for your instance, from OpenOrange or from provider keys you connect. A key can be limited to the models you select.

## Related guides

- [Agents and models](https://openorange.ai/runtime-adapters/)
- [Costs and usage](https://openorange.ai/model-usage-accounting/)
- [OpenOrange Code](https://openorange.ai/openorange-code/)

## Access and contact

The same infrastructure that runs agents for large organizations is opening to teams, independent builders, and individuals.

Public launch coming soon. The infrastructure behind enterprise AI, opening to everyone. Join the waitlist as an individual or a team. For enterprise access, talk to us.

Join the waitlist: https://openorange.ai/#contact
Enterprise contact: contact@openorange.ai

## Available languages

- [English](https://openorange.ai/model-api.md)
- [Русский](https://openorange.ai/ru/model-api.md)
- [Español](https://openorange.ai/es/model-api.md)
- [Deutsch](https://openorange.ai/de/model-api.md)
- [日本語](https://openorange.ai/ja/model-api.md)