Bring your own model

How configuration works

Launchbit resolves a model from two places: environment variables for credentials, and an optional launchbit.toml in your repo root for defaults. The CLI never transmits your keys anywhere except the endpoint you configure. There is no Launchbit account and no proxy in the middle.

# launchbit.toml
[model]
provider = "anthropic"
name = "claude-opus-4-8"

[model.fallback]
provider = "ollama"
name = "qwen2.5-coder:14b"

Override the model for a single command with the --model flag, e.g. launchbit ask --model gpt-5 "...".

Anthropic

export ANTHROPIC_API_KEY=sk-ant-...
launchbit config set model.provider anthropic
launchbit config set model.name claude-opus-4-8

Any current Claude model works. Opus is the default for complex edits; Haiku is a good fit for fast, cheap retrieval answers.

OpenAI

export OPENAI_API_KEY=sk-...
launchbit config set model.provider openai
launchbit config set model.name gpt-5

Google Gemini

export GEMINI_API_KEY=...
launchbit config set model.provider google
launchbit config set model.name gemini-2.5-pro

Ollama (local)

Run a model entirely on your own machine. Start Ollama, pull a coding model, and point Launchbit at the local server. No key, no network egress beyond localhost.

ollama pull qwen2.5-coder:14b
launchbit config set model.provider ollama
launchbit config set model.name qwen2.5-coder:14b
launchbit config set model.base_url http://localhost:11434

vLLM (self-hosted)

vLLM exposes an OpenAI-compatible server, so Launchbit talks to it the same way it talks to OpenAI — just change the base URL to your inference host.

# Serving on your own GPU box
vllm serve meta-llama/Llama-3.3-70B-Instruct --port 8000

# Point Launchbit at it
launchbit config set model.provider openai-compatible
launchbit config set model.name meta-llama/Llama-3.3-70B-Instruct
launchbit config set model.base_url http://gpu-box.lan:8000/v1

Any OpenAI-compatible endpoint

LiteLLM, OpenRouter, and most gateways speak the OpenAI wire format. Set the provider to openai-compatible, give Launchbit the base URL and model name, and you are done.

export OPENAI_API_KEY=your-router-key
launchbit config set model.provider openai-compatible
launchbit config set model.name anthropic/claude-opus-4-8
launchbit config set model.base_url https://openrouter.ai/api/v1

That is the whole story: install, set a provider, and start asking. Your code stays on your machine.