When was Hermes 3 70B released?

Hermes 3 70B was released on August 15, 2024 by Nous Research. This is the official Hermes 3 70B release date tracked on LLM Stats.

How big is Hermes 3 70B?

Hermes 3 70B has 70 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Hermes 3 70B?

Hermes 3 70B was created by Nous Research.

What is the license for Hermes 3 70B?

Hermes 3 70B is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Where can I use Hermes 3 70B?

Hermes 3 70B is available through 1 provider including DeepInfra.

Where is the Hermes 3 70B paper or technical report?

Hermes 3 70B has a paper or technical report available at https://nousresearch.com/. Use that source for architecture, training, release and evaluation details.

What models should I compare Hermes 3 70B against?

Common Hermes 3 70B comparisons include Hermes 3 70B vs Phi 4 Reasoning, Hermes 3 70B vs Claude 3 Sonnet, Hermes 3 70B vs Ministral 3 (14B Base 2512). Compare them side by side for benchmark scores, pricing, context window, latency and API availability.

Hermes 3 70B API Pricing, Context Window & Benchmarks

Name: Hermes 3 70B
Author: Nous Research

Hermes 3 70B: API Pricing, Context Window & Benchmarks

Hermes 3 70B is a language model from Nous Research, released in August 2024.

Hermes 3 70B is Nous Research's flagship instruction-following model, fine-tuned for advanced reasoning, creative writing, and complex task completion. It features exceptional instruction adherence and strong performance across multiple

Input

Text

Output

Text

Hermes 3 70B benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

How Hermes 3 70B performs across real-world prompt categories.

Performance by conversation depth

How Hermes 3 70B holds up as conversations get longer.

Quality Tracker

Hermes 3 70B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Mon Aug 24 2026

Notice missing or incorrect data?

Hermes 3 70B pricing

Providers

Hermes 3 70B starts at $0.350 per million input tokens and $1.40 per million output tokens via DeepInfra.

Provider	Input $/M	Cached input $/M	Output $/M	Context in / out	TTFT p95 s	Output p5 c/s	Modalities in / out
DeepInfra	$0.350	—	$1.40	131.1K/16.4K	—	—	/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.

Hermes 3 70B model size

Hermes 3 70B has 70 billion parameters. See how it compares to other models in the same parameter range.

Parameters

70B

Large (30–80B)

70B

1B7B70B405B

Hermes 3 70B context window

Input and output token limits for Hermes 3 70B, plus how it ranks on long-context understanding.

InputOutput

131Ktokens

16Ktokens

≈ 197 pages of text

131K

8K128K1M

Hermes 3 70B latency

Hermes 3 70B time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Hermes 3 70B examples

Recent arena outputs from Hermes 3 70B, picked from the highest-ranked matchups.

Hermes 3 70B license

Hermes 3 70B is released under the Apache 2.0 license, which permits commercial use, has 70.0B parameters.

License: Apache 2.0; Commercial use allowed
Parameters: 70.0B

Apache License 2.0 - allows commercial use

Hermes 3 70B resources

Official sources for Hermes 3 70B: official launch post, source repository, model weights.

Hermes 3 70B vs other models

The most-compared alternatives to Hermes 3 70B are Phi 4 Reasoning, Claude 3 Sonnet, Ministral 3 (14B Base 2512). Open any pair side-by-side for benchmarks, pricing, context, and latency.