Open WebUI via Tokonomix

Add Tokonomix as an OpenAI connection in Open WebUI — give your self-hosted chat 130+ models and a consensus option on one key.

OpenAI connection (Base URL)Self-hosted chat UIBSD-3 · open sourceDocker · self-hosted

Open WebUI — self-hosted AI chat, via Tokonomix

What is Open WebUI?

Open WebUI is a popular self-hosted, ChatGPT-style interface you run for yourself or a team. It connects to any OpenAI-compatible API — add Tokonomix as an OpenAI connection and every model in the catalogue appears in the model picker.

A polished multi-user chat UI you host with Docker.
Adds OpenAI-compatible APIs as connections (Admin → Settings → Connections).
Or configure them by environment variable at startup.
Open source and extensible (functions, pipelines, RAG).

Why add Tokonomix to Open WebUI?

Expose tokonomix-consensus and 130+ direct models in the picker for your whole team.
Centralise billing on one key with per-call spend caps.
Route by hosting_region / origin_country across the instance.
Add or remove models by editing one connection — no redeploy.

Connect Tokonomix to Open WebUI

Add an OpenAI connection in the UI (Admin → Settings → Connections → OpenAI API), or set the environment variables at startup.

# Environment (docker run / compose)
OPENAI_API_BASE_URL=https://tokonomix.ai/api/v1
OPENAI_API_KEY=tok_live_your-key

# Or in the UI:
#   Admin → Settings → Connections → OpenAI API
#   API Base URL : https://tokonomix.ai/api/v1
#   API Key      : tok_live_your-key

Verify it works

Save the connection (or restart with the env vars).
Pick a Tokonomix model — e.g. tokonomix-consensus — in the model selector and send a message.
Confirm the call and token usage in your Tokonomix dashboard.

Model selection

Which model and endpoint should my agent use?

Pick by what your agent does, then swap the model id any time — every model in the catalog works through the same key.

What your agent does	Use this
Edits files / calls tools and streams responses (most coding agents)	An Anthropic model via the Anthropic endpoint (tools + streaming both work)
Calls tools but does not need streaming (any model)	The OpenAI-compatible endpoint with a single model id
Wants tools and streaming on a non-Anthropic model	Run non-streaming for now — streaming tool-calls on other providers is not enabled yet
Plain chat, no tools	Either endpoint; streaming is fine
Wants a cross-model verdict (consensus) on a high-stakes answer	Set model to tokonomix-consensus on the OpenAI-compatible endpoint — note: consensus rejects tool requests (no tool-calling)

Endpoint & API reference (technical)

anthropic-messages → https://tokonomix.ai/api/anthropic — tools ✓, streaming ✓ (use an Anthropic model). openai-completions → https://tokonomix.ai/api/v1 — tools ✓ (single-model passthrough), streaming with tools not yet enabled. Plain chat: streaming works on both. Consensus: openai-completions, model tokonomix-consensus, no tools. Swap the model id to any slug returned by GET /api/v1/models.

Browse all models →