nousresearch/hermes-4-405b
131,072 context · $1.00/M input tokens · $3.00/M output tokens
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Pay-per-use
No upfront costs, pay only for what you use
Use the following code examples to integrate with our API:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="nousresearch/hermes-4-405b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Hermes 4 is a large-scale reasoning model built on Meta-Llama-3
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with <think>...</think> traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs
The model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.
| Specification | Value |
|---|---|
| Provider | Nousresearch |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 131072 tokens |
| Max Output | tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $1.1 |
| Output | $3.3 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: nousresearch/hermes-4-405b
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="nousresearch/hermes-4-405b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "nousresearch/hermes-4-405b",
"messages": [{"role": "user", "content": "Hello!"}]
}'nousresearch/hermes-4-405b
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Input
$1 /M
Output
$3 /M
Context
131K
Access Hermes 4 405b through our unified API — OpenAI-compatible, no cold starts, transparent pricing.
Pricing on WaveSpeedAI: $1.00 per million input tokens and $3.00 per million output tokens. Prompt caching and batch processing are billed separately and reduce effective cost on long, repetitive workloads.
Hermes 4 405b supports up to 131K tokens of context with up to — tokens of output per request.
Yes. WaveSpeedAI exposes Hermes 4 405b through an OpenAI-compatible endpoint at https://llm.wavespeed.ai/v1. Point the official OpenAI SDK at this base URL with your WaveSpeedAI API key — no other code changes required.
Sign in to WaveSpeedAI, create an API key in Access Keys, then send a request to https://llm.wavespeed.ai/v1/chat/completions with model id set to the value shown above. New accounts receive free credits to evaluate Hermes 4 405b before paying per token.