Hermes 3 405B is the first full-parameter fine-tune of Meta's Llama 3.1 405B, Nous Research's largest Hermes 3 model, with a 131,072 token context window. The model brings advanced agentic capabilities, reliable function calling, and structured outputs, combined with much improved roleplaying, reasoning, and multi-turn conversation coherence over long contexts. Training emphasized high-quality instruction data designed to make the model follow system prompts adaptively and precisely. Nous Research positions Hermes 3 405B as competitive, if not superior, to Llama 3.1 Instruct on general capabilities, while unlocking stronger steerability toward individual alignment preferences. This model targets developers building sophisticated multi-agent systems, complex reasoning pipelines, and applications requiring deep context coherence. It uses the ChatML prompt format and works with OpenAI-compatible serving stacks such as vLLM and SGLang.
Hermes 3 Llama 3.1 405B runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| DeepInfra | US | Enterprise | No | $1.00 | $1.00 |
Training posture across routes: No training on prompts by default.
Each route hosting Hermes 3 Llama 3.1 405B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.
Call Hermes 3 Llama 3.1 405B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
