Custom endpoints
Connect any OpenAI-compatible server to ACOG: Ollama, vLLM, llama.cpp, DeepSeek, or a gateway of your own.
A custom connection sends requests to any server that implements the OpenAI Chat Completions API: a model server you run (Ollama, vLLM, llama.cpp), an inference vendor (DeepSeek and others) or another gateway.
Connect
- In ACOG, open Admin → Providers → Connect provider and choose Custom.
- Enter:
| Field | Notes |
|---|---|
| Base URL | The server’s base, without /v1. ACOG calls {base URL}/v1/chat/completions. |
| API key | Optional. Sent as Authorization: Bearer. Leave it empty for a server with no authentication. |
| Server type | generic, deepseek, ollama, qwen or vllm. It tells ACOG how the server handles prompt caching. |
| Label | Optional display name |
| API version | Optional. Appended as api-version for servers that need it. |
- Declare the models the server serves, exactly as it names them (for example
llama3.3:70b), and choose a default.
Where the server can be
| Deployment | Allowed addresses |
|---|---|
| Hosted | A public HTTPS address on port 443. Private, LAN and loopback addresses, other ports and http:// are refused. |
| Self-hosted | Any address you configure, including http:// and private networks |
To use a server on your own network with the hosted service, publish it at a public HTTPS address you control, protected by its API key.
Calling a custom endpoint through ACOG
Use the Chat Completions API, or the Messages API which ACOG translates. The OpenAI-compatible Embeddings API works if your server implements /v1/embeddings. The native route is https://gateway.acog.tessarac.com/custom.
The savings mechanisms apply to custom connections as to any other: the response cache, de-duplication and the semantic cache work regardless of the server.