We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Nous: Hermes 4 405B
nousresearch/hermes-4-405bTry Nous: Hermes 4 405B now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Nous: Hermes 4 405B at a glance
- Input price is 122% higher than the median of 434 Text models.
- Context window of 131,072 tokens, enough for long documents and multi-turn conversations.
- Supports structured JSON output with a schema.
- Supports reasoning effort control.
- A typical request (1,000 input / 500 output tokens) costs about $0.00875.
About Nous: Hermes 4 405B
Nous: Hermes 4 405B is a text model from Nous Research, identified on api14 as nousresearch/hermes-4-405b. It is a large-scale reasoning model built on Meta-Llama-3.1-405B, and it was released by the provider on 2025-08-26. Its knowledge cutoff is 2024-08-31, so questions about events after that date may fall outside what it can answer reliably from training data alone.
The model accepts text input and returns text output. It has a context window of 131072 tokens, with a maximum output of 117964 tokens, which allows for long inputs and long generated responses in a single request. Hermes 4 introduces a hybrid reasoning mode, where the model can choose to deliberate internally before producing its answer, and this reasoning behaviour is exposed through the reasoning and include_reasoning parameters.
That combination of a large context window, long maximum output and hybrid reasoning suits work where the model needs room to think and then write at length. Typical fits include multi-step analysis of long documents, structured report generation, complex instruction following, and tasks where you want to inspect or control the model's internal deliberation. Because only text is accepted, it is not the right choice for image, audio or other non-text inputs.
You call it through api14's OpenAI-compatible API using the model id nousresearch/hermes-4-405b. The request parameters it supports are frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, temperature, top_k and top_p. The reasoning and include_reasoning parameters are the ones specific to its hybrid reasoning behaviour, while the others cover standard sampling, length and output formatting control.
If your task depends on non-text input, or on knowledge more recent than the 2024-08-31 cutoff, another model may fit better. The supported parameter list also does not include tool or function calling, so workloads that require that should look elsewhere. For long-context text reasoning and generation, though, Hermes 4 405B is a straightforward option to call from existing OpenAI-compatible client code.
How to call the Nous: Hermes 4 405B API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "nousresearch/hermes-4-405b".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "nousresearch/hermes-4-405b",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatstructured_outputstemperaturetop_ktop_logprobstop_pSpecifications
- Context length
- 131,072
- Max output
- 117,964
- Input
- text
- Output
- text
- Knowledge cutoff
- 2024-08-31
Requests on api14 · last 7 days
Nous: Hermes 4 405B: frequently asked questions
- How much does the Nous: Hermes 4 405B API cost?
- Nous: Hermes 4 405B costs Input $3.50 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Nous: Hermes 4 405B?
- Nous: Hermes 4 405B reads up to 131,072 tokens per request: prompt, history and documents together. It writes up to 117,964 output tokens per response.
- What can Nous: Hermes 4 405B do?
- Nous: Hermes 4 405B accepts text and returns text. It supports structured JSON output, reasoning effort control.
- How do I call Nous: Hermes 4 405B from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "nousresearch/hermes-4-405b". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Nous: Hermes 4 405B?
- Comparable Text models at a similar price: Pareto 26.10, Pareto Latest, Relace: Relace Search. Each runs through the same API key, so switching is one string.
Nous: Hermes 4 405B community
New topicThis community has no topics yet. Open the first one about Nous: Hermes 4 405B.