uttapen
Create an API key

Hermes 4 405B API: toman pricing and code

nousresearch/hermes-4-405b

reasoningjson
Create a keyTry it
Input · per 1M tokens
290,125 toman
Output · per 1M tokens
870,375 toman
One 1,000-word request ≈
1,509 toman

You are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups

Hermes 4 405B example: JSON output against a schema

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="nousresearch/hermes-4-405b",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is Hermes 4 405B good for?

Hermes 4 405B is one of Nous Research's models. Put "nousresearch/hermes-4-405b" in the model field and the rest of your code stays as it is. Hermes 4 405B keeps 131,072 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 117,964 tokens. On price it sits in the "mid-range" band — cheaper than 242 and dearer than 164 of the other paid models in the catalogue.

What you get on top of text in, text out: it returns schema-valid JSON through response_format, ready to hand to your code; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.

Input runs at 290,125 toman per 1M tokens and output at 870,375 — output costs 3× input, so trimming the answer saves more than trimming the prompt. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is GPT-3.5 Turbo Instruct: Hermes 4 405B works out roughly 1.1× more expensive, and its context window is larger. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 66 thousand-word requests on Hermes 4 405B, and every 1,000 toman is about 663 words of round trip. A job with one million input tokens and one million output tokens comes to 1,160,500 toman in total. Filling this model's 131,072-token window costs 38,027 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "nousresearch/hermes-4-70b", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 7.5× dearer (1,509 against 200 toman).

Nous Research has 4 models in our catalogue; the cheapest is Hermes 4 70B at 200 toman per thousand words and the dearest Hermes 4 405B at 1,509. Among the less common parameters it accepts repetition_penalty, top_k — all through the standard request body. It does not support tool_choice, tools, seed, structured_outputs, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Aion-2.0 at 131,072 tokens.

Where it makes sense: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, extracting data against a fixed schema.

Provider's own description

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...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out783 toman
Summarising a ten-page document4,000 in + 600 out1,683 toman
Classifying a thousand short rows120,000 in + 20,000 out52,223 toman

Frequently asked

How do I call Hermes 4 405B from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "nousresearch/hermes-4-405b". Nothing else in your code changes.
What does Hermes 4 405B cost in toman?
290,125 toman per 1M input tokens and 870,375 toman per 1M output tokens; a 1,000-word request is around 1,509 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Hermes 4 405B take?
Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 117,964 tokens.
Can I stream Hermes 4 405B's output?
Yes — with stream=true you get SSE events as the tokens are produced. This model has no tool calling and no image input, so pick a different one if you need either.