# Models, providers & cost

> Choose an inference route, set fallbacks, and keep the bill predictable.

Canonical: https://hermeswatcher.com/topics/models-cost

Hermes works with many providers and local models. The right choice depends on the task, your budget and how much you run unattended. These resources cover configuration, fallbacks, rate limits and the habits that keep spending under control.

## Guides, tools and workflows

- [Models and providers: configure the actual inference route](https://hermeswatcher.com/tools/models.md): Understand which model handles conversation and which auxiliary models handle supporting tasks before diagnosing quality or cost.
- [External memory providers: deeper long-term recall](https://hermeswatcher.com/tools/memory-providers.md): Add one external memory backend, such as Honcho, Mem0, Hindsight or Supermemory, on top of Hermes's built-in memory.
- [Fallback providers: keep working when your main model fails](https://hermeswatcher.com/tools/fallback-providers.md): Define a chain of backup model providers that Hermes switches to on rate limits, outages or auth errors.
- [How to choose a model for Hermes Agent](https://hermeswatcher.com/learn/models-and-effective-configuration.md): Separate model selection, provider access and tool configuration, then compare them using a representative task.
- [Hermes Agent still using the wrong model](https://hermeswatcher.com/troubleshoot/model-change-not-taking-effect.md): Compare effective settings with the running process before editing keys repeatedly.
- [How to keep Hermes Agent costs down](https://hermeswatcher.com/learn/keeping-costs-under-control.md): Where Hermes spends tokens, how to measure it, and the documented settings and habits that keep your provider bill predictable.
- [Hermes Agent rate limits and provider errors](https://hermeswatcher.com/troubleshoot/rate-limits-and-provider-errors.md): How to read 429s, quota errors, auth failures and stream errors from your model provider, and how retries, credential pools and fallback providers can keep Hermes working.
- [Hermes Agent SOUL.md and personalities explained](https://hermeswatcher.com/learn/soul-md-and-personalities.md): Use SOUL.md for the durable identity and tone of your agent, /personality for temporary modes, and AGENTS.md for project rules, so each layer does one job.
- [Hermes Agent local model won't start or goes silent](https://hermeswatcher.com/troubleshoot/local-model-context-too-small.md): Fix the context-window and tool-calling mismatches behind most local model failures with Ollama, llama.cpp, vLLM and LM Studio.
- [Hermes Agent OAuth login stuck or expired](https://hermeswatcher.com/troubleshoot/oauth-login-expired-or-stuck.md): Diagnose expired or revoked subscription logins, MCP OAuth that never returns, and logins that worked but landed in the wrong Hermes home.

## Questions

- [Which AI models and providers can I use?](https://hermeswatcher.com/faq#which-models-providers)
- [What is Nous Portal and do I need it?](https://hermeswatcher.com/faq#what-is-nous-portal)
- [Can I run Hermes with a local model, and which models fit my GPU or Mac?](https://hermeswatcher.com/faq#run-local-models)
- [How much does it cost to run?](https://hermeswatcher.com/faq#how-much-does-it-cost)
- [Does switching models mid-conversation cost extra?](https://hermeswatcher.com/faq#switching-models-mid-chat)
- [What happens when my model provider goes down or rate-limits me?](https://hermeswatcher.com/faq#provider-down-fallback)
- [How do I see what Hermes is costing me?](https://hermeswatcher.com/faq#track-spending)
- [Why do side tasks add to my bill, and can I give them, subagents and fallbacks their own models?](https://hermeswatcher.com/faq#auxiliary-models-cost)
- [Can I use my Claude Pro or Max subscription in Hermes?](https://hermeswatcher.com/faq#use-claude-subscription)
- [How can I keep token costs down?](https://hermeswatcher.com/faq#reduce-token-costs)
- [Which model is best for Hermes, and for side tasks like compression or the background review?](https://hermeswatcher.com/faq#best-model-for-hermes)
- [Is there a usage or rate limit, and can I tune how Hermes retries?](https://hermeswatcher.com/faq#rate-limits-and-retries)
- [How do I fix a Nous Portal subscription or billing problem, such as adding VAT details?](https://hermeswatcher.com/faq#portal-billing-help)
- [How does using my ChatGPT plan in Hermes work?](https://hermeswatcher.com/faq#chatgpt-plan-sign-in)

All answers: https://hermeswatcher.com/faq.md

---

HermesWatcher is an independent guide. It is not affiliated with or endorsed by Nous Research. The [official Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) and [repository](https://github.com/NousResearch/hermes-agent) from Nous Research are the authority; each page here lists the official sources it was written from. If this site and the official docs disagree, trust the official docs. Index for agents: https://hermeswatcher.com/llms.txt