Hermes 70B

Nous Research chat Free

API ID: nousresearch/nous-hermes-llama2-70b

Input Price
Free
/1M tokens
Output Price
Free
/1M tokens

About Hermes 70B

Nous Hermes is Nous Research's instruction-tuned model series, offering enhanced instruction following across various base models. The models excel at conversation, task completion, and creative writing. Nous Hermes variants span multiple generations and base models. For developers seeking well-tuned conversational AI, Nous Hermes provides reliable instruction following.

๐Ÿ†
Price Ranking
#1 lowest price among 950 Chat models โ€” Top 20% cheapest!

Model Specifications

Context Length
4k
Max Output
โ€”
Release Date
2023-10-20
Capabilities
chat
Input Modalities
text
Output Modalities
text

Best For

  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)
๐ŸŽ‰

This model is completely free!

No token costs - use it without worrying about API bills.

Estimate Token Usage

Nous Research Model Lineup

Compare all models from Nous Research to find the best fit

Model Input Output Context Capabilities
Hermes 70B Current Free Free 4k chat
Hermes 2 Theta 8B Free Free 16k chat
Hermes 2 Theta 8B Free Free 16k chat
Hermes 2 Mistral 7B DPO Free Free 8k chat
Hermes 2 Mistral 7B DPO Free Free 8k chat
Hermes 2 Mixtral 8x7B SFT Free Free 33k chat

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Google Gemma 3n 4B
Input: Free
Output: Free
Context: 33k
Meta Llama 3.2 3B Instruct
Input: Free
Output: Free
Context: 80k
Alibaba Qwen Qwen2.5-VL 7B Instruct
Input: Free
Output: Free
Context: 33k
ByteDance Seedream 4.5
Input: Free
Output: Free
Context: 4k

๐Ÿš€ Quick Start

Get started with Hermes 70B API

OpenAI-compatible SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="nousresearch/nous-hermes-llama2-70b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)