Skip to main content

Overview

The Omnifact provider connects to the Omnifact API Gateway — an OpenAI-compatible endpoint for chat completions. Use your Omnifact organization API key and any model enabled for your organization.

Installation

createOmnifact()

Create an Omnifact provider instance.

Options

string
Your Omnifact organization API key.
string
Custom gateway base URL. Defaults to https://connect.omnifact.ai/v1/gateway.

Returns

OmnifactProvider with method chatModel().

Model IDs

Use the exact id values returned by GET /v1/gateway/models. The SDK passes the model id through unchanged. EU-hosted backends (Azure OpenAI, Vertex Google, Vertex Anthropic, Mistral, etc.) always use the eu/ prefix:
  • eu/gpt-5-mini — Azure OpenAI
  • eu/claude-4-6-sonnet — Vertex Anthropic
  • eu/mistral-large — Mistral
Direct non-EU providers use the plain type id:
  • gpt-5-mini — OpenAI
  • claude-4-6-sonnet — Anthropic
When both a direct and an EU backend exist for the same model type, both ids may appear in the model list. Use the one that matches where you want the request routed.

Provider support

Model capabilities

Every chat model exposes model.capabilities:
Plain OpenAI model IDs can use the OpenAI capability registry. Routed IDs such as eu/gpt-5-mini and IDs for other backend providers do not match that registry, so they receive generic OpenAI-compatible fallback capabilities. For those IDs, treat model.capabilities as defaults rather than an exact description of the backend model. In particular, the fallback reports 'image' and 'file' in modalities.input, so multimodal requests are forwarded to the backend rather than rejected locally.

Examples

Basic chat

Streaming

Provider-specific options

The gateway follows the OpenAI Chat Completions API. Pass options via providerOptions.openai:
The provider accepts compatible reasoning_content and reasoning output fields. See the OpenAI-compatible provider for the compatibility behavior and available Chat Completions options.