A
AIverse
writing

Hermes 4

4.4/5Open weights / API via providers
Visit Website

Nous Research's open-weight Hermes 4 family (14B / 70B / 405B) — a steerable, neutrally-aligned reasoning model with a hybrid 'thinking' mode, strong function calling and structured JSON output for agentic builders.

What is Hermes 4?

Nous Research's open-weight Hermes 4 family (14B / 70B / 405B) — a steerable, neutrally-aligned reasoning model with a hybrid 'thinking' mode, strong function calling and structured JSON output for agentic builders.

Hermes 4 sits in the writing category and is listed in the AIverse AI tools directory, where it holds an editorial rating of 4.4 out of 5 based on its capabilities, usability, value for money and reliability. It is developed by Nous Research, founded in 2023.

Hermes 4 features and use cases

People typically use Hermes 4 for Custom agents with tool use, Structured JSON pipelines, Research and fine-tuning and Uncensored, neutral assistants.

It is often associated with LLM, Open Weights, Reasoning, Function Calling and Steerable. Developers can integrate Hermes 4 into their own products through its API.

Hermes 4 pricing

Hermes 4 offers a free plan, with paid tiers (Open weights / API via providers) that unlock more advanced features and higher usage limits.

As with any AI tool, the right plan depends on how heavily you use it. We recommend trying Hermes 4 before committing to a paid plan.

Is Hermes 4 worth it? Our bottom line

Overall, Hermes 4 is a strong choice in the writing category for 2026. Its standout strengths include Highly steerable, neutrally aligned and Hybrid reasoning (think vs. answer). Bear in mind Raw model — you handle safety/guardrails and Largest size is hardware-heavy. If it matches your workflow, Hermes 4 is well worth a try — especially since you can start on a free plan.

Our verdict

Hermes 4 is the model for builders who want maximum control and neutral alignment, with first-class function calling and JSON output. It rewards teams comfortable adding their own guardrails in exchange for a highly steerable open model.

👍 Pros

  • +Highly steerable, neutrally aligned
  • +Hybrid reasoning (think vs. answer)
  • +Excellent function calling & JSON mode
  • +Three sizes incl. 405B
  • +Fully open weights

👎 Cons

  • Raw model — you handle safety/guardrails
  • Largest size is hardware-heavy
  • Not as polished as hosted assistants
  • Smaller mainstream ecosystem

🎯 Use cases

Custom agents with tool useStructured JSON pipelinesResearch and fine-tuningUncensored, neutral assistants

💡 Expert tips

  • Use Hermes’ JSON and function-calling mode for reliable structured output in agents instead of parsing free text.
  • Because it is neutrally aligned, add your own safety guardrails before exposing it to end users.

ℹ️ Key facts

Company
Nous Research
Founded
2023
API
Yes

Last updated: Jun 2026

4.4
Rating
9.0k
Views
Freemium
Pricing

Try Hermes 4 Now

Nous Research's open-weight Hermes 4 family (14B / 70B / 405B) — a steerable, neutrally-aligned reasoning model with a hybrid 'thinking' mode, strong function calling and structured JSON output for agentic builders.

Frequently Asked Questions

Is Hermes 4 free?

Yes — Hermes 4 offers a free plan (Open weights / API via providers) plus a paid tier for advanced features and higher usage limits. You can start for free and upgrade only if you need more.

What is Hermes 4 used for?

Hermes 4 is an AI writing tool. Nous Research's open-weight Hermes 4 family (14B / 70B / 405B) — a steerable, neutrally-aligned reasoning model with a hybrid 'thinking' mode, strong function calling and structured JSON output for agentic builders. It currently holds a 4.4/5 rating on Aiverse from real users.

Is Hermes 4 worth it in 2026?

Hermes 4 is a solid choice with a 4.4/5 rating on Aiverse — a reliable option in the writing category, though it's worth comparing alternatives below for your specific needs.