Nous Research Pro · $9/month 10 tokens / message Slow

Hermes 3 405B · Nous Research

Hermes 3 fine-tuned on Llama 3.1 405B by Nous Research. One of the most capable and least censored models available. Good for roleplay, creative writing, deep reasoning.

405B parameters Not overly censored Roleplay and creativity

Try it free

Hermes 3 405B requires the Pro plan

Create a free account to start, or subscribe to a plan for unlimited use of premium models.

No card to start · Cancel anytime

Open in full chat → Compare models side by side, save your sessions and memory

About Hermes 3 405B

Hermes 3 fine-tuned on Llama 3.1 405B by Nous Research. One of the most capable and least censored models available. Good for roleplay, creative writing, deep reasoning.

Where it shines: 405B parameters · Not overly censored · Roleplay and creativity.

How to use Hermes 3 405B

  1. 1

    Type or upload

    Type what you want in the box above — or upload the file if the tool asks for one.

  2. 2

    Generate

    Click the main button. Wait 2-30 seconds depending on the model and input size.

  3. 3

    Download or share

    Download the result or share the direct link. No watermark, ready to use.

Frequently asked questions

How much does it cost to use Hermes 3 405B?

Hermes 3 405B is a Pro model: it costs 10 tokens per use (~$0.05 real cost for us). You need a Pro plan ($9/month → 15,000 tokens) or a one-shot pack. If you already have tokens in the free account, you can also spend them directly.

How many Hermes 3 405B uses are included in the Pro plan?

Pro ($9/month) gives you 15,000 recurring tokens. At 10 tokens per Hermes 3 405B use, that's ~1,500 full uses per cycle. If you run out, one-shot packs (5,000 / 25,000 / 80,000 tokens) add to the balance without expiring before one year.

What makes Hermes 3 405B special?

Nous Research fine-tunes open models with fewer restrictions — good for roleplay, fiction, and deep reasoning, with specific strengths in 405b parameters, no excessive censorship, and roleplay and creativity.

How fast does Hermes 3 405B respond?

Hermes 3 405B is a "think" model: it reasons explicitly before responding, so it takes longer — waits 15-45 seconds.The actual time also depends on the length of the prompt and the load of the datacenter — models with huge context take longer when you enter very long texts.

How do I use Hermes 3 405B in ia.gratis?

You can use Hermes 3 405B from /chat/ by selecting Hermes 3 405B in the picker, or via the REST API with `model=hermes-3` in the POST body. Quick summary: Calls 405B fine-tuned by Nous. Uncensored. The internal model identifier is `hermes-3` — useful when integrating via API.