The faster start, with a trade-off

Running it through your own provider key

No model to download: install the tool, paste a key and it is running in minutes, on your own account with Anthropic, OpenAI or OpenRouter, your contract, your retention settings. What you give up is where the specification goes, which is the next paragraph and is the whole of the decision.

Read this part first

On this path the specification, and everything you ask about it, is transmitted to the provider you configure. A published patent is public, but your questions and the claims drafted from it can still show a client’s strategy. For that, and for an unpublished or privileged application, it is a decision only you can make for that matter, against your own professional obligations. The tool does not make it for you, and it prints a note on every run that routes off your machine.

If you want the specification to stay on your hardware, use a local model instead: choose one for your machine.

Setting it up

Create a key

With whichever provider you already have an account with: Anthropic, OpenAI, or OpenRouter, which reaches many vendors on one key. Add credit.

Ask about zero data retention

If you want it, it is an arrangement on your own provider account, and it applies whether or not you use this tool. OpenRouter offers it as an account setting. Anthropic and OpenAI arrange it with eligible accounts, and Anthropic’s Fable and Mythos models are not available under it.

Know what a prompt cache keeps

Providers cache the start of a prompt so that sending it again costs less, and most prompts this tool sends carry the whole specification. A cache is held after the call returns, and what is held depends on how you run the tool. Where a provider lets the tool choose, it asks for the shortest retention on offer. The same table closes the model guide.

How you run it	What is kept
A model on your own computer	Nothing leaves the computer, as long as the model server runs on it too. The specification goes only to that server.
Claude through OpenRouter	Anthropic keeps no prompts or answers by default, except on its Fable and Mythos models, which it keeps for 30 days for safety monitoring. The tool also asks for a prompt cache, which holds the start of each prompt, mostly the specification, in memory for up to an hour after its last use.
Claude with your own Anthropic key	No prompt cache: the Anthropic endpoint this tool uses does not support one. Otherwise as above: nothing kept by default, except on Fable and Mythos models, kept for 30 days.
OpenAI, with your own OpenAI key	The tool asks for the shortest prompt cache OpenAI offers, which depends on the model: minutes on older models, up to 24 hours on gpt-5.5, and 30 minutes after last use on gpt-5.6 and later. OpenAI says cached data may be kept encrypted in GPU-local storage.
OpenAI models through OpenRouter	OpenRouter does not pass the cache setting on, so OpenAI's own default for the model applies.
Other models through OpenRouter	The model runs on whichever host OpenRouter chooses, and that host's policy decides what it keeps. One question can reach more than one host: in a test, four calls about one specification went to four different companies.

This is what running the tool causes a provider to keep. Each provider also has its own terms on logging, abuse monitoring and training, which depend on your account and are yours to check. Checked against each provider’s documentation on 29 September 2026.

Make the key available

Read from the environment first, then from ~/.continuation-drafter/config.json, a file the binary creates readable only by you. Never from a command-line flag and never written to a log.

export ANTHROPIC_API_KEY=sk-ant-...
export OPENAI_API_KEY=sk-...
export OPENROUTER_API_KEY=sk-or-...

Set the one you use. Each provider reads only its own variable.

The local web UI can save the key into that file for you, which also keeps it out of your shell history, where a key typed at a command line can stay. The command line does not save it. Setting the environment variable always takes precedence over the saved file.

Name a remote model

A slash in the name routes remotely, through OpenRouter. To reach Anthropic or OpenAI directly, name the provider: the same model is called anthropic/claude-opus-4 at OpenRouter and claude-opus-4 at Anthropic, so the model string alone cannot say which company receives your specification.

./continuation-drafter draft --spec spec.txt --parent parent-claims.txt \
  --model openai/gpt-5.5

./continuation-drafter draft --spec spec.txt --parent parent-claims.txt \
  --provider anthropic --model claude-opus-4

What you gain and what you give up

Large remote models are faster than large local ones and, on the strategy axis, they aimed their independent claims across more of the relevant loci in our testing, where strong local models tended to cluster on the most literal reading of the disclosure. That is a difference in breadth, and it is the reason the choice is a tradeoff rather than a preference.

Whether breadth is what you want is a separate question. In a later test against eleven real continuations, the directions two remote models proposed sat further from what those continuations actually claimed than a small local model's did: they looked hardest for matter the parent had left unclaimed, and most of the continuations broadened the parent's own claims instead. What those continuations changed is published with its method.

One practical note from the same testing: the small model we measured, qwen3.5:9b, was slower and less reliable reached through OpenRouter than running on a laptop, with some calls running to the time limit. For a small model, local is the faster route as well as the private one.