Nous Research's subscription platform for Hermes Agent: 300+ models (Claude, GPT, Gemini, DeepSeek, and Nous's own Hermes series), a managed tool gateway (web search, image, TTS, browser), and monthly credits behind one auth flow.
Pricing: Plus $20/mo ($22 credit), Super $100/mo ($110 credit), Ultra $200/mo ($220 credit). A ~1.1x credit multiple. (Verified 2026-07-17.)
For a Hermes user, Nous Portal is the smoothest native experience — one login, 300+ models, real bundled tools. But its ~1.1x credit multiple means it's priced for convenience, not cheap tokens; heavy agents drain the credit fast. If raw cost-per-dollar or true unlimited is the goal, Standard Compute (flat-rate, no meter) or OpenCode Go (~6x open-weight) deliver far more inference per dollar — you just give up Portal's bundled tools and Hermes-native auth.
Standard Compute is an OpenAI-compatible API with unlimited frontier-model compute at a flat monthly price (from $9/mo) — no per-token billing, no rate-limit windows. Under extreme sustained load requests are paced smoothly instead of erroring or charging more.
Standard Compute is OpenAI-compatible, so any tool or SDK that lets you set a custom base URL migrates in minutes:
Base URL = https://api.stdcmpt.com/v1 API key = your Standard Compute key Model = standardcompute
Setup guides for every major agent — OpenClaw, Hermes, OpenCode, Cursor, Cline, Aider and more — on the integrations page. Free tier to test it, no card required.
No — its credit multiple is only ~1.1x, so you're paying mostly for the Hermes-native convenience and bundled tools. For cheapest tokens, OpenCode Go (~6x open-weight) wins; for unlimited always-on use, Standard Compute's flat-rate has no credit to run dry.
Nous Portal if you value the one-auth Hermes ecosystem and bundled tools and your usage is light. Standard Compute if cost or unlimited always-on runtime is the priority — Hermes' 24/7 background loops are exactly where a fixed credit balance fails and flat-rate unlimited wins.
Free tier, no card. Plans from $9/mo.