Standard Compute

Which API Provider Should You Use With Hermes Agent?

For an always-on Hermes Agent, connect a cost-optimized OpenAI-compatible API such as Standard Compute at https://api.stdcmpt.com/v1: its router sends each background job and scheduled task to the cheapest model that can do it (Claude Fable 5.1 or GPT-6 Astra only when it counts), and all of it draws from one enforced compute budget on a plan from $19/month. Nous Portal is the first-party option, combining models, hosted tools and hosting in one credit balance; OpenRouter or one vendor's key suits light, bursty use; a local model through llama.cpp costs nothing per token if your GPU can run it.

Guide updated 2026-10-15. Check each provider's current terms below.
Get your API key$0.25 trial for eligible new accounts, no card. Plans from $19/mo.

This page compares which API provider to connect to Hermes. For Nous Portal, ChatGPT and flat plans side by side with what each costs a month, see the best subscription for Hermes Agent.

Light or occasional use
Start by measuring your background tasks and model calls. Compare Portal's current credits, supported coding subscriptions such as OpenCode Go, and low-cost usage-based models on the same workload.
Daily use, cost-optimized
Standard Compute keeps each Hermes call cheap: the router picks the cheapest model that can do the step, and for every model we vet providers for price, uptime and speed, with automatic fallback. Opt-in Europe or US Compliance rules apply per key, team or company, and we don't train on your prompts or store them. The bill is one monthly plan, so check that your Hermes workload fits its compute budget, reduce unnecessary background runs and watch the remaining allowance; a subscription does not guarantee uninterrupted 24/7 use.

API and subscription options for Hermes

OptionPriceWhat you get
Nous Portal$0, $20, $100 or $200/moFirst-party Hermes account. Free covers free models only; Plus, Super and Ultra buy $22, $110 or $220 of monthly credits for models, hosted tools and cloud hosting, with $10 to $100 rolling over. Checked 2026-10-14. Source: portal.nousresearch.com
ChatGPT plan (Codex sign-in)$20 Plus, $100–$500 ProSign in with ChatGPT and the agent runs on Codex models within your plan's Codex allowance: five-hour windows on Plus, none on Pro, and weekly limits may apply. Only for agents that support ChatGPT sign-in. Source: learn.chatgpt.com
Standard Compute (us)From $19/moSmart routing sends each request to the cheapest model that can do it, or pin any model by its exact ID. Standard Compute starts at $19/month with a $20 monthly compute budget. Requests stop when that budget is exhausted until renewal or a plan change; there are no automatic overage charges. Requests are not slowed as the budget is used. It is a fixed bill with a finite allowance.
OpenCode Go$10 or $40/moNative OpenCode subscription: Go $10 a month, Go Plus $40. Each model has a monthly usage limit in dollars, with 5-hour and weekly windows set as shares of it. Single-member workspaces only. Source: opencode.ai
OpenRouterPay-as-you-goChoose models and providers through one API. Usage-based pricing can suit light or bursty work; estimate long agent sessions and review current fees and limits. Source: openrouter.ai
Local model (Ollama / vLLM)Hardware + electricityNo hosted per-token bill, but hardware, context capacity, throughput and maintenance still limit what you can run. Test task quality on your own hardware. Source: docs.ollama.com

Prices and allowances can change. OpenCode Go prices were checked against its linked public pages on October 13, 2026, DevPass prices on September 5, 2026; other entries link to current plans without quoting an unverified price. Spot an error? Tell us.

Or configure Hermes Agent by hand

hermes setup → Full setup → Custom OpenAI-compatible endpoint
Base URL  https://api.stdcmpt.com/v1
API key   your Standard Compute key
Model     standardcompute

Ask Hermes for one short reply, then check the dashboard's Logs page for the request and the model that answered. hermes doctor diagnoses most setup problems.

Setup for one model in Hermes: DeepSeek · Qwen 3.8 · Gemini

Hermes questions

How do I wire Hermes Agent up to a custom LLM endpoint in one sitting?
Two ways, each a few commands. Fastest: install the Standard Compute launcher (curl -fsSL https://standardcompute.com/cli/install.sh | sh, Node.js 20 or newer) and run standardcompute launch hermes; after a browser sign-in it opens Hermes on a separate saved profile whose main model and auxiliary slots (vision, compression, title generation) all point at standardcompute over Chat Completions, and your usual Hermes profile stays untouched. By hand: run hermes setup, choose Full setup, pick Custom OpenAI-compatible endpoint and enter the base URL https://api.stdcmpt.com/v1, your key and the model standardcompute. Plans start at $19 a month with a $20 compute budget, and Hermes runs on macOS, Linux and WSL.

Try one task before choosing a plan

  1. Check the API format and model configuration supported by your installed Hermes version.
  2. Run a small task on a clean branch and review the result, elapsed time and compute used.
  3. Estimate your actual monthly workload before selecting a larger allowance.
Get your API keyHermes setup guide →Compare compute budgets →

Record your own results with the workload CSV and report template. These are blank templates, not published benchmark results.

Disclosure: this guide is maintained by Standard Compute, one of the options above. Choose based on task quality, supported features and total cost for your workload. Light usage may cost less on a usage-based API; sustained workloads need enough allowance on any subscription.

All flat-rate plans compared →The cheapest-tokens math →Plan compute for your team →