Model APIs and gateways · by Nous Research, Inc.

Nous Research (Nous Portal inference API)

Name: Nous Research (Nous Portal inference API)
Author: Nous Research, Inc.

An AI lab that trains the open-weight Hermes models and runs Nous Portal, an OpenAI-compatible inference API for its own Hermes 4 models and a catalog of other labs' models, with keys, credits and subscriptions, plus pay-per-request x402 payments in Solana USDC without an account.

You can call Hermes models through a standard OpenAI client, or download the same weights from Hugging Face and run them yourself.

APIDownloadFree tierCommercial: conditions

Open nousresearch.com ↗ agent.md

For your project

Official API: Official API · Free tier Free: 50 RPM, 500,000 TPM; Plus 400 RPM; Super 800 RPM; Ultra 1,600 RPM; default paid users 180 RPM, 720,000 TPM
“An OpenAI-compatible API for running completion requests on Nous Research's inference backend.” portal.nousresearch.com/api/openapi
Key: Needed
“Set the API key as a bearer token in the `Authorization` header in your requests.” portal.nousresearch.com/api/openapi
Formats: JSON
Data download: Yes safetensors
“[OpenAPI specification](https://portal.nousresearch.com/api/openapi): OpenAI-compatible inference API spec (JSON)” portal.nousresearch.com/llms.txt
Price: Free tier · from $20/mo Free: $0, free models only, standard rate limits, $0 monthly credits; pay-as-you-go top-ups and x402 per-request payments
“Plus 10% bonus $20 per month $22 monthly credits $10 rollover cap” portal.nousresearch.com/
License: Nous Research Terms of Service (API); model weights under their own licenses (e.g. Llama 3 license, Apache-2.0) Hosted inference API; you own AI outputs, but may not use the service to build a competing AI product
Commercial use: Commercial use with conditions
“you shall own all right, title, and interest in AI Outputs generated specifically for you through your use of the Nous Research Services” portal.nousresearch.com/terms
Credit: Not stated
Embedding: Embedding unclear
Using the website: Free tier

Read on Nous Research (Nous Portal inference API)'s own pages on Oct 24, 2026 · license or terms · API docs · pricing. Check the license page before you ship.

For your agent

A request your code or agent can make (add your key):

https://portal.nousresearch.com/api/openapi

Use any OpenAI client with base_url https://inference-api.nousresearch.com/v1 and a Portal API key as Bearer token; model ids like Hermes-4-70B; for Hermes 4 reasoning use the documented system prompt and read reasoning_content; set max_tokens explicitly when paying via x402.
Do not use the API to build or improve a competing AI model or service
Downloaded Hermes weights follow each model's own license (Llama 3 license for Hermes-4-70B/405B, Apache-2.0 for Hermes-4.3-36B)
With x402, you are charged for max_tokens whether or not they are used

llms.txt: portal.nousresearch.com/llms.txt

Paste into your agent: Read https://agentgid.com/resources/nous-research/agent.md before using Nous Research (Nous Portal inference API).

Quick answers

Does Nous Research (Nous Portal inference API) have an API?

Yes. Nous Research (Nous Portal inference API) has an official API documented at https://portal.nousresearch.com/api-docs.

Does the Nous Research (Nous Portal inference API) API need a key?

Yes, you need an API key. Limits: Free: 50 RPM, 500,000 TPM; Plus 400 RPM; Super 800 RPM; Ultra 1,600 RPM; default paid users 180 RPM, 720,000 TPM

Is Nous Research (Nous Portal inference API) free?

Yes, there is a free tier: Free: $0, free models only, standard rate limits, $0 monthly credits; pay-as-you-go top-ups and x402 per-request payments Paid plans start at $20 a month.

Can I use Nous Research (Nous Portal inference API) in a commercial project?

Yes, with conditions. Its terms say: "you shall own all right, title, and interest in AI Outputs generated specifically for you through your use of the Nous Research Services"

What you can build

A chat app on Hermes 4 through the OpenAI SDK, with a local fallback to the same open weights
A pay-per-request agent that buys inference with x402 USDC payments instead of an account
A reasoning-heavy assistant that shows Hermes 4's reasoning_content separately from the answer

Alternatives in Model APIs and gateways

All 7 →

Zro You can point an existing coding agent at cheaper open models by changing a base URL, without request bodies being stored or used for training. API (paid)Commercial OK Cohesor You can cut and cap agent model spend by swapping one base URL and key instead of rewriting code for each provider. API (paid)Commercial OK LLMTest A provider outage or a reply that is not valid JSON no longer breaks your feature, because the proxy retries on another model inside the same request, and you see what each AI feature costs. API (paid)Commercial OK Tokenwise You find out which prompts and models drive your LLM bill by changing one base URL, while your own provider keys pass through and are not stored. API (paid)Free tierCommercial OK Opper AI Switching or pooling model providers becomes a model-string change, and teams that must keep data in the EU get one sub-processor and one DPA instead of a contract per provider. APIFree tierCommercial OK RunInfra You can point Claude Code, Codex, Aider or an existing OpenAI/Anthropic SDK at open models by changing a base URL and key, without renting or tuning GPUs yourself. API (paid)Free tierCommercial OK

Something wrong or out of date? Tell us.