uttapen
Create an API key

Llama 3 8B Lunaris API: toman pricing and code

sao10k/l3-lunaris-8b

json
Create a keyTry it
Input · per 1M tokens
11,605 toman
Output · per 1M tokens
14,506 toman
One 1,000-word request ≈
34 toman

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

Llama 3 8B Lunaris 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="sao10k/l3-lunaris-8b",
    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 Llama 3 8B Lunaris good for?

The id for Llama 3 8B Lunaris in our API is "sao10k/l3-lunaris-8b", served from Sao10k. Context is 8,192 tokens; past that you have to summarise the history yourself. A single response can run to 7,372 tokens. On price it sits in the "very cheap" band — cheaper than 3 and dearer than 403 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. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

Input runs at 11,605 toman per 1M tokens and output at 14,506 — output costs 1.3× 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 MythoMax 13B: Llama 3 8B Lunaris works out roughly 1.3× cheaper, 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 2,941 thousand-word requests on Llama 3 8B Lunaris, and every 1,000 toman is about 29,412 words of round trip. A job with one million input tokens and one million output tokens comes to 26,111 toman in total. Filling this model's 8,192-token window costs 95 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "sao10k/l3.3-euryale-70b", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 15.5× cheaper (34 against 528 toman). The context windows differ too: 8,192 against 131,072 tokens. Maximum answer length differs as well: 7,372 against 16,384 tokens. On parameters, this one takes logit_bias, min_p, top_k.

Sao10k has 3 models in our catalogue; the cheapest is Llama 3 8B Lunaris at 34 toman per thousand words and the dearest Llama 3.1 Euryale 70B v2.2 at 641. Among the less common parameters it accepts logit_bias, logprobs, min_p, repetition_penalty, top_k, top_logprobs — all through the standard request body. It does not support include_reasoning, reasoning, tool_choice, tools, 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 R1 Distill Llama 70B at 8,192 tokens.

Where it makes sense: high-volume work such as classification, tagging and bulk summarising, extracting data against a fixed schema, short single-turn requests (the context window is small).

Provider's own description

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....

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 out23 toman
Summarising a ten-page document4,000 in + 600 out55 toman
Classifying a thousand short rows120,000 in + 20,000 out1,683 toman

Frequently asked

How do I call Llama 3 8B Lunaris 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 "sao10k/l3-lunaris-8b". Nothing else in your code changes.
What does Llama 3 8B Lunaris cost in toman?
11,605 toman per 1M input tokens and 14,506 toman per 1M output tokens; a 1,000-word request is around 34 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Llama 3 8B Lunaris take?
Up to 8,192 tokens per request, roughly 6k words. A single answer can reach 7,372 tokens.
Can I stream Llama 3 8B Lunaris'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.