models

GET /v1/models

List all available Epithre models, their tiers, context limits, and capabilities. Public: no authentication required.

Request

GET /v1/models HTTP/1.1
Host: api.epithre.com

No headers required (Authorization is optional and ignored).

Response shape

{
  "object": "list",
  "data": [
    {
      "id": "epithre-omni",
      "object": "model",
      "owned_by": "epithre",
      "tier": "flagship",
      "context_window": 49152,
      "max_output_tokens": 16384,
      "modalities": ["text", "image"],
      "capabilities": ["chat", "tool_use", "vision", "thinking"],
      "description": "...",
      "pricing_model": "per_token"
    },
    ...
  ]
}

Available models

ID	Tier	Context	Best for
`epithre-prme`	Premium	180,000	Long-context reasoning, full-codebase analysis, document review
`epithre-omni`	Flagship	49,152	General chat with vision, agentic tool-use, extended thinking
`epithre-lyt`	Compact	32,768	High-throughput cheap chat, image + audio + video input
`epithre-embed`	Embedding	4,096	Semantic search + cross-modal retrieval (4000-dim, text + image)
`epithre-rerank`	Reranker	2,048	Boosting retrieval quality after embed search
`epithre-iris`	Image	-	Text-to-image, multi-reference image editing

See per-model detail in the Models section.

Get a single model

GET /v1/models/{model_id}

Returns the same object shape, just one model. Convenient for client SDKs that call this for capability negotiation.

Use cases

Capability negotiation: check modalities and capabilities before sending vision input.
Pricing discovery: pricing_model indicates per-token vs. per-image vs. per-document billing.
Programmatic UIs: build a model picker without hardcoding the catalog.

Pricing

Free. No authentication, no rate limit at the per-key level (subject to backend rate limits on extreme abuse).