CodeGPT via Tokonomix

Use Tokonomix as CodeGPT’s Custom provider — 130+ models and consensus inside VS Code on one key.

Custom provider endpointVS Code extensionOpen sourceVS Code · all platforms

What is CodeGPT?

CodeGPT is a VS Code AI coding extension with chat, autocomplete and code actions. It supports a Custom provider that takes a model, key and completion endpoint, which is how Tokonomix plugs in — one key behind chat and code actions across 130+ models.

Adds AI chat, code generation and explanation inside VS Code.
The Custom provider takes a Model, API Key and completion Endpoint (BYOK).
The Custom provider requires a CodeGPT Pro or Teams plan.
Point the endpoint at the Tokonomix OpenAI-compatible base URL.

Why route CodeGPT through Tokonomix?

One key reaches 130+ models from inside VS Code — no separate provider accounts.
Point the model at tokonomix-consensus for a multi-model check on risky in-editor answers; a direct slug for routine completions.
Per-call spend caps bound usage, and region / origin routing keeps repo data compliant.
Cost is metered to the cent in your Tokonomix dashboard.

Connect Tokonomix to CodeGPT

In the CodeGPT panel, select a model and choose the Custom provider, then fill in the model, key and endpoint.

# CodeGPT panel -> select model -> Provider: Custom
Model    : tokonomix-consensus
API Key  : tok-your-key
Endpoint : https://tokonomix.ai/api/v1

# Connect (BYOK; the Custom provider needs a Pro/Teams plan)

Verify it works

Select the Custom provider and fill in tokonomix-consensus, your key and the endpoint.
Ask a question in the CodeGPT panel or trigger a code action.
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 →