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
Nessun costo iniziale, paga solo per ciò che usi
Usa i seguenti esempi di codice per integrare la nostra 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
Contesto
131K
Accedi a Hermes 4 405b tramite la nostra API unificata — compatibile con OpenAI, senza cold start, prezzi trasparenti.
Prezzi su WaveSpeedAI: $1.00 per milione di token in input e $3.00 per milione di token in output. Prompt caching e batch processing sono fatturati separatamente e riducono il costo effettivo su carichi lunghi e ripetitivi.
Hermes 4 405b supporta fino a 131K token di contesto e fino a — token di output per richiesta.
Sì. WaveSpeedAI espone Hermes 4 405b tramite un endpoint compatibile con OpenAI all'indirizzo https://llm.wavespeed.ai/v1. Punta l'SDK ufficiale di OpenAI a questa base URL con la tua API key WaveSpeedAI — senza altre modifiche al codice.
Accedi a WaveSpeedAI, crea una API key in Access Keys, poi invia una richiesta a https://llm.wavespeed.ai/v1/chat/completions con il model id mostrato sopra. I nuovi account ricevono crediti gratuiti per testare Hermes 4 405b.