Benchable Open Beta

Nous: DeepHermes 3 Llama 3 8B Preview

0
Back
Text input Text output Free Option
Author's Description

DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one model. We have also improved LLM annotation, judgement, and function calling. DeepHermes 3 Preview is one of the first LLM models to unify both "intuitive", traditional mode responses and long chain of thought reasoning responses into a single model, toggled by a system prompt.

Key Specifications
Context
131K
Parameters
8B
Released
Feb 27, 2025
Hugging Face
Supported Parameters

This model supports the following parameters:

Top Logprobs Top P Seed Stop Logit Bias Temperature Presence Penalty Logprobs Min P Frequency Penalty Max Tokens
Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.01
Completion $0.05

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Chutes
Chutes | nousresearch/deephermes-3-llama-3-8b-preview 131K $0.01 / 1M tokens $0.05 / 1M tokens
Other Models by nousresearch
 Released Params Context
Speed Ability Cost
Nous: Hermes 4 70B Aug 26, 2025 70B 131K
Text input Text output
★★★★ ★★★ $$
Nous: Hermes 4 405B Aug 26, 2025 405B 131K
Text input Text output
★★★ ★★★★ $$$$
Nous: DeepHermes 3 Mistral 24B Preview May 09, 2025 24B 32K
Text input Text output
★★★★ ★★★ $$
Nous: Hermes 3 70B Instruct Aug 17, 2024 70B 131K
Text input Text output
★★★★ ★★★ $$
Nous: Hermes 3 405B Instruct Aug 15, 2024 405B 131K
Text input Text output
★★★ ★★★★ $$$$
NousResearch: Hermes 2 Pro - Llama-3 8B May 26, 2024 8B 131K
Text input Text output
★★★★★ ★★ $
Nous: Hermes 2 Mixtral 8x7B DPO Unavailable Jan 15, 2024 56B 32K
Text input Text output
★★★ ★★ $$$$