Does Hermes 3 Llama 3.1 70B support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Hermes 3 Llama 3.1 70B is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Hermes 3 Llama 3.1 70B hosted?

Hermes 3 Llama 3.1 70B runs on US hosting routes through the Opper gateway.

Is Hermes 3 Llama 3.1 70B trained on prompts and outputs?

No. Every hosting route for Hermes 3 Llama 3.1 70B is configured so customer prompts and outputs are not used to train models by default.

Hermes 3 Llama 3.1 70B

by Nous Research

Hermes 3 Llama 3.1 70B from Nous Research — text model on the Opper gateway.

Try in chat Open in playground Compare

Key info

Input

Output

Features

Context window

131K

Max output

131K

Input price

$0.30 /1M

Output price

$0.30 /1M

US residency available
Zero data retention via Enterprise
No training by default

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#423 of 519 LLMs

TierEfficient

Output speed33 tok/s

First token0.35s

Intelligence Index10.6

MMLU-Pro

57%

GPQA Diamond

40%

Humanity's Last Exam

LiveCodeBench

19%

SciCode

23%

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Available routes

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.

Data handling per route

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.