Nousresearch: Hermes 2 Pro Llama 3 8B

Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue

Model lab: Nousresearch
Model family: —

Model resources

Hugging Face

Modalitiestext → text

Context window8,192

Maximum output8,192

InputUSD 0.112 / 1M tokens

OutputUSD 0.112 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to nousresearch/hermes-2-pro-llama-3-8b.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "nousresearch/hermes-2-pro-llama-3-8b"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Hermes 2 Pro Llama 3 8B API Pricing

Type	Price information
Input	USD 0.112 / 1M tokens
Output	USD 0.112 / 1M tokens

Performance

Performance trends

Throughput91.4 tok/sCurrent

Time to first token3.2 sCurrent

End-to-end latency6.9 sCurrent

Throughput

Current91.4 tok/s

Window average90.0 tok/s

Time to first token

Current3.2 s

Window average1.5 s

End-to-end latency

Current6.9 s

Window average7.5 s

Tail latency (P99)

Current13.8 s

Window average16.5 s

Prompt cache hit rate

Current26.2%

Window average23.6%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Hermes 2 Pro Llama 3 8B Compare models

Model	Input price	Output price	Context window	Capabilities
Hermes 2 Pro Llama 3 8BThis page	USD 0.112 / 1M tokens	USD 0.112 / 1M tokens	8,192	Text output · Tool calling
Hermes 4 405B	USD 0.24 / 1M tokens · Context ≤ 128000 tokens · Maximum output 8192 tokens · Maximum input 128000 tokens	USD 0.96 / 1M tokens · Context ≤ 128000 tokens · Maximum output 8192 tokens · Maximum input 128000 tokens	131,072	Text output · Reasoning
Hermes 3 70B Instruct	USD 0.56 / 1M tokens	USD 0.56 / 1M tokens	131,072	Text output
Hermes 3 405B Instruct	USD 0.8 / 1M tokens	USD 0.8 / 1M tokens	131,072	Text output
Beam 1.0 501B A23B	USD 0.2 / 1M tokens	USD 0.8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 8,192
Maximum output: 8,192
Release date: 2024-04-30
Attachments: No
Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Hermes 2 Pro Llama 3 8B for?

Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue

What inputs and outputs does Hermes 2 Pro Llama 3 8B support?

Recorded inputs: text; outputs: text.

How is Hermes 2 Pro Llama 3 8B priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.112 / 1M tokens; Output USD 0.112 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Hermes 2 Pro Llama 3 8B?

Current model records list Context window 8,192 tokens; Maximum output 8,192 tokens.

What model parameter does the Quickstart use?

The example uses nousresearch/hermes-2-pro-llama-3-8b. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.