Open Interpreter via Tokonomix

What is Open Interpreter?

Open Interpreter is a natural-language terminal agent: you describe a task in plain English and it writes and runs code on your machine to do it. It routes through LiteLLM, so any OpenAI-compatible endpoint — including Tokonomix — can be the model behind it.

Generates and executes code (Python, shell and more) locally to complete a task.
Configurable from the CLI (--api_base, --api_key, --model) or in Python via interpreter.llm.*.
Uses LiteLLM under the hood, so OpenAI-compatible slugs take the openai/ prefix.
Open source; runs on macOS, Windows and Linux.

Why route Open Interpreter through Tokonomix?

Open Interpreter runs whatever the model writes — use openai/tokonomix-consensus to cross-check a step before anything irreversible runs.
One key swaps between 130+ models — a fast direct slug for routine commands, consensus for the risky ones.
Per-call spend caps bound an agent that can fire many calls; region / origin routing keeps execution compliant.
Every call is metered to the cent in your Tokonomix dashboard.

Connect Tokonomix to Open Interpreter

Pass the Tokonomix base URL, your key and an openai/-prefixed model on the command line — or set the same fields in Python.

interpreter \
  --api_base "https://tokonomix.ai/api/v1" \
  --api_key "tok_live_your-key" \
  --model "openai/anthropic/claude-sonnet-4-6"
  # Opt-in (planning/review only, no tool-calling): --model "openai/tokonomix-consensus"

# or in Python:
from interpreter import interpreter
interpreter.llm.api_base = "https://tokonomix.ai/api/v1"
interpreter.llm.api_key = "tok_live_your-key"
interpreter.llm.model = "openai/anthropic/claude-sonnet-4-6"
# Opt-in (planning/review only, no tool-calling): interpreter.llm.model = "openai/tokonomix-consensus"
interpreter.chat()

Verify it works

Set --api_base, --api_key and an openai/-prefixed model slug.
Ask Open Interpreter for a small, reversible task and approve it.
Confirm the call and token usage in your Tokonomix dashboard.

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 →

//What is Open Interpreter?

//Why route Open Interpreter through Tokonomix?

//Connect Tokonomix to Open Interpreter

//Verify it works

Which model and endpoint should my agent use?

Related agents

What is Open Interpreter?

Why route Open Interpreter through Tokonomix?

Connect Tokonomix to Open Interpreter

Verify it works