uttapen
Create an API key

Hermes 4 70B API: toman pricing and code

nousresearch/hermes-4-70b

reasoningjson
Create a keyTry it
Input · per 1M tokens
37,716 toman
Output · per 1M tokens
116,050 toman
One 1,000-word request ≈
200 toman

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

Hermes 4 70B 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-4-70b",
    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 70B good for?

Hermes 4 70B is one of Nous Research's models. Put "nousresearch/hermes-4-70b" in the model field and the rest of your code stays as it is. Hermes 4 70B 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 "very cheap" band — cheaper than 71 and dearer than 335 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 37,716 toman per 1M tokens and output at 116,050 — output costs 3.1× 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 Llama 3.2 3B Instruct: Hermes 4 70B works out roughly 1.4× more expensive, and its context window is the same size. 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 500 thousand-word requests on Hermes 4 70B, and every 1,000 toman is about 5,000 words of round trip. A job with one million input tokens and one million output tokens comes to 153,766 toman in total. Filling this model's 131,072-token window costs 4,944 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-4-405b", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 7.5× cheaper (200 against 1,509 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: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, extracting data against a fixed schema.

Provider's own description

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

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 out103 toman
Summarising a ten-page document4,000 in + 600 out220 toman
Classifying a thousand short rows120,000 in + 20,000 out6,847 toman

Frequently asked

How do I call Hermes 4 70B 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-4-70b". Nothing else in your code changes.
What does Hermes 4 70B cost in toman?
37,716 toman per 1M input tokens and 116,050 toman per 1M output tokens; a 1,000-word request is around 200 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Hermes 4 70B take?
Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 117,964 tokens.
Can I stream Hermes 4 70B'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.