Jan via Tokonomix

Add Tokonomix as a custom provider in Jan — give the local-first desktop app 130+ models and consensus on one key.

Custom provider Base URLDesktop appAGPL-3.0 · open sourcemacOS · Windows · Linux

What is Jan?

Jan is a local-first desktop AI assistant that runs models on your own machine but can also reach remote endpoints. It adds OpenAI-compatible providers from Settings, which is how Tokonomix plugs in — one key, many remote models, alongside anything you run locally.

Chats with local models or remote OpenAI-compatible endpoints from one desktop app.
Add a custom provider under Settings → Model Providers with a Base URL and API key.
Register remote models by id, then select them in the model picker.
Open source; supports tool calling through compatible models.

Why route Jan through Tokonomix?

One custom provider unlocks 130+ models from a single desktop app — no separate provider accounts.
Name a model tokonomix-consensus for high-stakes chats; add a direct slug for fast everyday questions.
Per-call spend caps bound usage, and region / origin routing keeps sensitive prompts compliant.
Cost is metered to the cent in your Tokonomix dashboard.

Connect Tokonomix to Jan

In Jan, add an OpenAI-compatible provider under Settings → Model Providers, then register the model id.

# Jan -> Settings -> Model Providers -> + (OpenAI-compatible)
Base URL : https://tokonomix.ai/api/v1
API Key  : tok-your-key

# Add Model -> id: anthropic/claude-sonnet-4-6
# then pick anthropic/claude-sonnet-4-6 in the model picker and chat
# Opt-in (planning/review only, no tool-calling): also add id: tokonomix-consensus

Verify it works

Add the custom provider, paste the Base URL and key, and register tokonomix-consensus as a model.
Pick it in the model picker and send a chat 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 →