Wordcab has collaborated with Knowledgator and SCX.ai for the release of the new guardrails model family: Opir.ai
Docs/API/Models

Models

Every model this key can call, with metadata on context length, streaming, tool use, and hardware requirements.

Package availability

Wordcab SDKs, CLI tools, Helm charts, model weights, and deployment packages are delivered directly to each customer for self-hosted installation. They are not publicly published package-manager artifacts, so install commands in these docs are placeholders until your Wordcab team provides your private package source or offline bundle.

List models

GET/v1/models

Returns everything this key can call. Fields per model:

json
{
  "id": "qwen3.5-4b",
  "object": "model",
  "type": "llm",
  "context_length": 131072,
  "streaming": true,
  "tool_use": true,
  "modalities": ["text"],
  "requirements": {"min_gpu": "L40S", "vram_gb": 22},
  "license": "Apache-2.0"
}

Types

  • llm — chat completions.
  • stt — transcription (batch + streaming).
  • tts — speech generation.
  • embedding — embedding models.
  • diarization — speaker segmentation models.

Retrieve a single model

GET/v1/models/{model_id}