SpareTokens

Home / Docs / Providers

Providers

Which AI accounts and local models the SpareTokens worker supports, and how each one is connected under your own account.

The worker is provider-pluggable. You pick where the model comes from, and every provider keeps its credentials on your machine. The coordinator only receives the task result, a few small artifact files, and usage numbers.

Supported providers

ProviderWhat it usesUsage reported
anthropic-apiYour ANTHROPIC_API_KEY, run through the Claude Agent SDK with an OS-sandboxed shell and a tool allowlist. Web search available.Dollars and tokens
claude-codeOff. A Claude subscription login is not supported: Anthropic's terms bar automated use of consumer plans. Use anthropic-api instead.Not applicable
openai-apiYour OPENAI_API_KEY, with the built-in tool loop and a sandboxed shell.Tokens (dollars if you pass prices)
codexOff for a ChatGPT login. Using a ChatGPT plan for automated work like this is not permitted by OpenAI's terms as we read them. Use openai-api instead.Not applicable
xaiYour XAI_API_KEY (Grok, through the OpenAI-compatible API).Tokens (dollars if you pass prices)
openrouterYour OPENROUTER_API_KEY.Dollars as reported by OpenRouter, and tokens
localAny OpenAI-compatible server you run: Ollama, LM Studio or an MLX server, through --base-url.Tokens and wall-clock seconds
noneNo model at all. Runs only solver tasks (run_solver and re_verify) in the OS sandbox.Wall time only

Literature tasks need web search, which only the Anthropic API provider offers today.

Capability tiers

Each provider and model declares a tier, and the coordinator only hands out task types that tier can do. Verification protects the results either way, so routing just saves your time.

  • Tier 1: small or local models, for solver runs and re-verification. No model is needed at all for these.
  • Tier 2: mid-size models, for literature checks and model-written computation tasks.
  • Tier 3: frontier models, for referee reviews and Lean formalization.

Defaults: local is tier 1, and a local model of 70B or more counts as tier 2. Models whose name contains mini, nano or haiku are tier 2. Other Claude and GPT models are tier 3. OpenRouter is tier 2 unless the model is a known frontier model. Override with --tier if you know better. See task types and tiers.

Use a dedicated project or service-account key

Where your provider offers projects, workspaces or service accounts, create one just for SpareTokens and make the worker's key inside it, rather than reusing a personal key or an organization-wide key. OpenAI support suggested this approach for workers like ours. It has real benefits:

  • Its own limit. Set a spend limit on the project or workspace. That limit protects you at the provider, next to the cap you set in the worker. Two caps are better than one.
  • Its own usage report. You can see exactly what the worker used, separate from your other tools.
  • Its own revocation. If you ever want to stop, delete the key or the project, and nothing else you run is affected.
  • Least privilege. A key that can only do model calls cannot change billing or other settings. Give it no more access than it needs.

The names differ by provider. OpenAI has projects with project API keys and service accounts, and Anthropic has workspaces in the Console with their own keys and limits. Check your provider's console for the current names and limits. A team or lab doing a pilot should use this too (see the team guide). Keep the key out of the SpareTokens config as always: the worker reads it by name, such as env:OPENAI_API_KEY, and it never leaves your machine.

Provider terms

Consumer subscriptions are not supported. Anthropic's Consumer Terms bar access "through automated or non-human means, whether through a bot, script, or otherwise" except with an API key, and OpenAI's and Google's consumer terms restrict automated use too. So SpareTokens never uses a Claude, ChatGPT or Gemini plan login, and the worker refuses one with a message pointing here. API keys and local models are the way to contribute. Need a key? Create one step by step. Not sure you have API credit? Find your unused API credit: some plans include monthly credit you can claim, and it expires if unused. We re-check provider terms every month and will update this page if a provider explicitly permits more.

  • API keys are billed by the provider to you, and the key stays on your machine. Prepaid or expiring API credit is a good fit. Use a key with a spend limit, and set a budget in the worker.
  • Local models run on your hardware and cost you electricity and wall-clock time.
  • SpareTokens never pools, resells or transfers anyone's credit.
  • Your provider account and key are yours to protect. Use your own account, keep keys on your machine, follow your provider's terms, and set a spend limit at the provider too.

Names of providers belong to their owners. SpareTokens is independent and not affiliated with or endorsed by any of them.

Connecting a source

Keys are referenced by name, such as an environment variable, and never copied into the SpareTokens config. In the configuration commands, add a source with a provider and a credential reference:

sparetokens config add-source work-api --provider anthropic-api --credential env:ANTHROPIC_API_KEY

Then choose a rule for it on the giving styles page, and see every option in the CLI reference.

Edit this page on GitHub: available when the repository opens.