Matricxon API
Matricxon serves an Ollama-style HTTP API, so most Ollama clients work with it.
Chat and generation
Section titled “Chat and generation”| Endpoint | Notes |
|---|---|
POST /api/chat |
Streaming NDJSON chat, with tools and images. A request_id lets you cancel just this reply |
POST /api/generate |
Raw-prompt completion, no chat template |
POST /api/embeddings, POST /api/embed |
Mean-pooled, L2-normalized vectors (single and list input) |
Models
Section titled “Models”| Endpoint | Notes |
|---|---|
POST /api/pull |
Downloads hf.co/<repo>:<file> from Hugging Face with progress and a sha256 check |
GET /api/tags, POST /api/show, GET /api/ps |
Installed models with their capabilities, model details, loaded models with expiry |
DELETE /api/delete, POST /api/copy, POST /api/create |
Remove, duplicate, re-tag (create supports only FROM <tag>) |
POST /api/infer-capabilities |
Matricxon-only: what a file would be able to do, before it is downloaded |
POST /api/push |
Always refused. Matricxon has no registry to push to |
Pulling resolves only hf.co/<repo>:<file> tags.
Server and storage
Section titled “Server and storage”| Endpoint | Notes |
|---|---|
GET /api/health |
Matricxon-only: supported architectures, quantizations, MoE and vision lists |
GET /api/version |
Version string |
GET /api/storage |
Matricxon-only: each storage folder, its role, size and free space |
Saved chat caches
Section titled “Saved chat caches”See Prompt cache.
| Endpoint | Notes |
|---|---|
GET /api/cache/persistence |
Show the limits and how much is stored |
PUT /api/cache/persistence |
Change enabled, budget_mb or ttl_hours |
DELETE /api/cache/persistence |
Delete every saved cache |
DELETE /api/cache/persistence/chats/{tag} |
Delete the saved caches of one chat |
Cluster
Section titled “Cluster”The cluster and consensus endpoints are used by pAIring. See Cluster.
Admin routes and the admin secret
Section titled “Admin routes and the admin secret”Routes that change models, caches or the cluster (pull, delete, copy, create, the cache changes above, and the cluster routes) are admin routes.
- With
MATRICXON_ADMIN_SECRETset, each admin call must be signed with it. The signature covers the method, path, body, a timestamp and a one-time value, so a captured call cannot be changed or replayed. pAIring signs its calls for you. - With no secret, admin routes are open. Then protect the network instead.
The signature does not hide the content. Use TLS, or a trusted network, for that.