Hermes 3 70B is a fine-tune of Llama 3.1 70B that delivers Nous Research's agentic capabilities at a more deployable scale than the 405B model. With a 131,072 token context window, it supports extended multi-turn conversations and long-form reasoning while keeping strong function calling and structured output support for tool-use applications. Built through fine-tuning on high-quality instruction data, Hermes 3 70B is positioned as competitive, if not superior, to Llama 3.1 Instruct on general tasks, with particular gains in roleplaying, multi-turn dialogue coherence, and reasoning. The model uses the ChatML prompt format and supports function calling within assistant turns. This model suits teams balancing capability against compute cost, especially for agentic systems, content generation that needs consistency over long contexts, and reasoning workloads where 70B parameters are sufficient. It works with common OpenAI-compatible serving stacks including vLLM and SGLang.
Hermes 3 Llama 3.1 70B 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 | $0.30 | $0.30 |
Training posture across routes: No training on prompts by default.
Each route hosting Hermes 3 Llama 3.1 70B 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.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Hermes 3 Llama 3.1 70B 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-3.1-70B",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
