Tabby via Tokonomix

Point Tabby’s chat model at Tokonomix in config.toml — give your whole self-hosted team 130+ models and a consensus option on one key.

HTTP chat model (config.toml)Self-hosted assistantApache-2.0 · open sourceDocker · self-hosted

Tabby — self-hosted coding assistant, via Tokonomix

What is Tabby?

Tabby is a self-hosted AI coding assistant — code completion and chat for your whole team from one server you run. Its chat model is configured as an HTTP endpoint in config.toml, so you can point it at any OpenAI-compatible API, including Tokonomix.

Runs as a server (Docker) and serves completion + chat to every developer on the instance.
The chat model is an HTTP endpoint — kind = "openai/chat" with an api_endpoint.
One change in config.toml updates the model for the whole team.
Open source and self-hosted — your data stays on your server.

Why route Tabby’s chat through Tokonomix?

Give every developer on the instance a tokonomix-consensus-backed chat answer.
One key, 130+ models — swap the chat model centrally without per-user keys.
Per-call spend caps bound team-wide usage; cost is metered in your dashboard.
Route by hosting_region / origin_country for the whole instance.

Connect Tokonomix in config.toml

Set the chat model’s HTTP endpoint to Tokonomix. (Tokonomix powers the chat model; Tabby’s completion model is a separate setting.)

# config.toml (Tabby server)
[model.chat.http]
kind         = "openai/chat"
api_endpoint = "https://tokonomix.ai/api/v1"
api_key      = "tok_live_your-key"
model_name   = "tokonomix-consensus"

Verify it works

Restart the Tabby server after editing config.toml.
Open the chat panel and ask a question.
Confirm the call and token usage appear 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 →