//Compare>Nous Portal vs OpenRouter

Nous Portal API keys bill per token from a credit balance, at the prices on the models page, and no subscription is needed for the API. API keys always use your credits, not a plan's included usage. Top-ups are paid by card through Stripe. For API calls, x402 (beta) lets you pay per request in Solana USDC with no account, API key or prepaid credits.

OpenRouter bills inference at the provider's list price and charges its fee when you buy credits: 5.5% on Standard card purchases (with a minimum), 5% on crypto purchases and 8% on the Business plan. Enterprise pricing is set by contract.

On Aug 19, 2026, Stripe announced an agreement to acquire OpenRouter. OpenRouter said it would keep operating under the same name and product. Its announcement, read on Nov 9, 2026, still described the deal as subject to customary closing conditions.

Nous Portal offers free models, and the Free filter on the models page shows the current list. On Nov 9, 2026, Solar Mini 4, Step 3.7 Flash and Beam 1.0 were free on Nous Portal and listed as paid on OpenRouter, and LongCat 2.5 was free on Nous Portal and not listed on OpenRouter. The Free plan covers free models with standard rate limits.

OpenRouter has its own free models, capped at 50 requests a day, or 1,000 a day once an account has bought a set amount of credits.

Nous Portal lists hundreds of models, with new frontier models the day they launch, including Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Kimi, GLM and MiniMax, with prices per million tokens. Selected models sell below their list price, and the Discounted filter on the models page shows the current list.

On Nov 9, 2026, Tencent Hy4 cost 60% less on Nous Portal than on OpenRouter, and GLM-5.3 Flash cost 20% less. Other discounted models, such as Gemini 4 Argon, cost the same on both. OpenRouter's pricing page says it does not discount inference.

Nous Portal is one account for Hermes Agent, the Nous inference API and Hermes Cloud. The Hermes Agent docs call Nous Portal the recommended way to run Hermes Agent. One command, hermes setup --portal, signs Hermes Agent in, lets you pick a model and turns on the Tool Gateway. Hermes Desktop does the same in one click.

Plus, Super and Ultra include Hermes Agent usage, within limits that reset daily, weekly and monthly. You can use any model, and pricier models use your included usage faster. If you use it up, you can switch to a free model, wait for the reset or continue with pay-as-you-go credits. Hermes Business gives a team a shared Hermes Agent deployment with one balance and per-member caps.

Any account can link an eligible ChatGPT account for supported inference, with no paid Nous subscription. Tools and Hermes Cloud hosting are charged separately, and ChatGPT plan limits still apply.

On paid plans, the Tool Gateway gives Hermes Agent web search, page extraction, image generation, text-to-speech, speech-to-text and a cloud browser, with no separate vendor accounts or keys. Hermes Agent can switch any single tool to your own vendor key whenever you want.

OpenRouter's server tools let any model call web search, web fetch, image generation or a sandboxed shell during a request. They are in beta, and OpenRouter says their API and behavior may change.

Every paid Nous Portal plan includes one Hermes Cloud agent, up to the plan's included size: up to 4 GB RAM and 25 GB disk on Plus, 4 GB RAM and 100 GB disk on Super, and 8 GB RAM and 100 GB disk on Ultra. Larger or extra agents bill daily from credits.

Hermes Cloud runs Hermes Agent around the clock in the nearest available region. Each agent gets its own hardened container, and its files, memory and configuration persist whether it is running or stopped.

OpenRouter's Ori page says the Ori CLI is live, Ori Intern, which deploys agents into Slack, is in private testing, and Ori Desktop is on a waitlist. Ori Harness starts agent CLIs, including Hermes Agent, on your own machine.