Nousresearch

Nous: Hermes 4 70B

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

Context Window
131K tokens
Parameters
70B
Input Price
$0.13/1M
Output Price
$0.40/1M
Price Tier
budget
Provider
Nousresearch

How to Use Nous: Hermes 4 70B

With CoreAI, you can start chatting with Nous: Hermes 4 70B instantly — no separate subscription needed. CoreAI lets you chat with Nous: Hermes 4 70B alongside 300+ other AI models from Nousresearch and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select Nous: Hermes 4 70B from the model selector
  3. Start chatting, comparing, or creating with AI

Nous: Hermes 4 70B at a Glance

Nous: Hermes 4 70B holds the #273 spot for context size out of 392 chat models in the CoreAI catalog — 131K tokens, roughly 98,304 words or 197 pages of text in a single conversation. On price, it is the #76 cheapest of 128 budget-tier models by input cost. It joined the catalog on 2025-08-26. It supports step-by-step reasoning (thinking mode).

Nous: Hermes 4 70B Compared to Its Closest Alternatives

SpecNous: Hermes 4 70BNous: Hermes 3 70B InstructGoogle: Gemma 4 26B A4B (free)inclusionAI: Ling-2.6-flash
ProviderNousresearchNousresearchGoogleInclusionai
Input $/1M tokens$0.13$0.7Free$0.01
Output $/1M tokens$0.4$0.7Free$0.03
Context window131K131K131K262K
Reasoning modeYesNoYesNo
Image inputNoNoYesNo
Price tierbudgetbudgetbudgetbudget

Every model in this table is available on CoreAI — open the web app and run the same prompt through Nous: Hermes 4 70B and Nous: Hermes 3 70B Instruct side by side to judge with your own eyes.

What Nous: Hermes 4 70B Actually Costs in Practice

A typical question (about 1,000 tokens in, 500 out) runs $0.00033 on Nous: Hermes 4 70B's raw per-token rates; a heavy session with a 50K-token document costs about $0.009. On CoreAI you don't juggle these numbers — one subscription covers Nous: Hermes 4 70B and 300+ other models under a plan usage limit, with no API keys. See plans.

More Nousresearch Models

Nousresearch

Nous: Hermes 4 405B

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the
131K standard
Nousresearch

Nous: Hermes 3 70B Instruct

Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced
131K budget
Nousresearch

Nous: Hermes 3 405B Instruct

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reason
131K standard

Frequently Asked Questions about Nous: Hermes 4 70B

What is Nous: Hermes 4 70B's context window?

Nous: Hermes 4 70B handles 131K tokens of context — roughly 98,304 words, or about 197 pages of text in one conversation.

How much does Nous: Hermes 4 70B cost?

Nous: Hermes 4 70B's underlying rates are $0.13 per 1M input tokens and $0.4 per 1M output tokens. On CoreAI it is included in one subscription alongside 300+ models, so there is no per-token billing to manage.

Can Nous: Hermes 4 70B process images?

No — Nous: Hermes 4 70B is text-only. If you need image understanding, its budget-tier peers with vision are listed in the comparison table above.

Does Nous: Hermes 4 70B support reasoning or thinking mode?

Yes. Nous: Hermes 4 70B can work through problems step by step before answering; on CoreAI you can toggle thinking mode per message.

How can I use Nous: Hermes 4 70B without an API key?

Open the CoreAI web app or the iOS/Android app, pick Nous: Hermes 4 70B in the model selector, and chat — no API key, no per-token billing. One subscription covers Nous: Hermes 4 70B and 300+ other models.

What are the best alternatives to Nous: Hermes 4 70B?

The closest alternatives on CoreAI are Nous: Hermes 3 70B Instruct, Google: Gemma 4 26B A4B (free), inclusionAI: Ling-2.6-flash — similar tier and capability. The fastest way to choose is running one prompt through them side by side in CoreAI's Compare view.

Try Nous: Hermes 4 70B Now

Chat with Nous: Hermes 4 70B and 300+ other AI models — all in one app.

Use Web App Download App →