bolt.diy via Tokonomix

Set the OpenAILike provider in bolt.diy to Tokonomix — build full-stack apps in the browser, driven by 130+ models and consensus on one key.

OpenAILike provider (env)In-browser app builderMIT · open sourceBrowser · Docker

bolt.diy — open-source in-browser app builder, via Tokonomix

What is bolt.diy?

bolt.diy is the open-source version of Bolt — an in-browser AI app builder that scaffolds, edits and runs full-stack apps from a prompt. It supports many providers, including a generic OpenAILike provider for any OpenAI-compatible endpoint.

Generates and runs full-stack apps in a browser sandbox (WebContainers).
Ships an OpenAILike provider configured by two environment variables.
Pick the Tokonomix model from the provider’s model dropdown in the UI.
Open source; self-host with Docker or run locally.

Why route bolt.diy through Tokonomix?

One key, 130+ models in the OpenAILike model list — including tokonomix-consensus.
Reach for consensus when scaffolding architecture; a fast model for iterative edits.
Per-call spend caps keep an app-generating session within budget.
Region / origin routing applies to every generation call.

Connect Tokonomix to bolt.diy

Set the OpenAILike environment variables (in .env.local or your Docker env), then choose the OpenAILike provider and a Tokonomix model in the UI.

# .env.local
OPENAI_LIKE_API_BASE_URL=https://tokonomix.ai/api/v1
OPENAI_LIKE_API_KEY=tok_live_your-key

# Then in the bolt.diy UI:
#   Provider → OpenAILike
#   Model    → tokonomix-consensus (or any slug)

Verify it works

Set the env vars and restart bolt.diy (or its Docker container).
Select the OpenAILike provider and a Tokonomix model, then generate an app.
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 →