How much does Llama 3.3 Euryale 70B cost?

Billing is usage-based: $0.65 per million input tokens and $0.75 per million output tokens. There is no monthly minimum. You pay only for the tokens you actually use.

How do I access Llama 3.3 Euryale 70B from inside Iran?

Create a Hormouz account, generate an API key and point your client at Hormouz. Access to Llama 3.3 Euryale 70B is served from inside Iran, so you do not need a foreign credit card, a VPN or any sanction-circumvention tooling.

Is Llama 3.3 Euryale 70B compatible with the OpenAI SDK?

Yes. Hormouz exposes an OpenAI-compatible chat-completions API. Change the base URL to Hormouz and drop in your Hormouz key, and existing OpenAI SDK code runs unchanged.

What context window does Llama 3.3 Euryale 70B support?

Llama 3.3 Euryale 70B supports a context window of up to 131K tokens, which is enough for long documents and extended conversations in a single request.

What is Llama 3.3 Euryale 70B best suited for?

It is tuned for creative roleplay, character-driven dialogue and long-form fiction. It follows custom formats and reply styles well and is not restrictive during roleplay, which makes it popular for immersive storytelling rather than factual or tool-using tasks.

Does Euryale 70B support tool calling or vision?

No. It is a text-only model without tool calling or image input. If you need function calling, structured agents or multimodal input, a model like Grok 4.20 or a Nova model is a better fit.

Sao10K: Llama 3.3 Euryale 70B: AI model

Euryale 70B on Llama 3.3 is Sao10K's creative roleplay model with a 128K context window and strong prompt adherence. Reachable from inside Iran through Hormouz.

Context window:: 131,072 tokens
Input:: $0.65/1M tokens
Output:: $0.75/1M tokens
Type:: text

Streaming
Long context

Llama 3.3 Euryale 70B is a fine-tune from Sao10K focused on creative roleplay and long-form storytelling. Built on the Llama 3.3 70B base, it is the successor to the earlier Euryale releases and keeps the same emphasis: expressive, character-consistent writing that follows the prompt closely rather than steering the story on its own.

The model handles a context window of up to 128K tokens and can produce responses of up to about 16K tokens, which suits multi-scene roleplay, detailed character cards and long narrative threads that need to stay coherent across many turns. It is a text-in, text-out model and does not use tool calling, so it is aimed at writing rather than agentic automation.

Through Hormouz, Euryale 70B is served behind an OpenAI-compatible API. Point your base URL at Hormouz, add a Hormouz key, and existing SDK code works without changes. Access is provided from inside Iran, so no foreign card or circumvention tooling is needed.

Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2.

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sao10k/l3.3-euryale-70b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

Vendor	Sao10K
Type	Text
Context window	131,072 tokens
Pricing	$0.65/M in · $0.75/M out
API	Chat Completions
Capabilities	Streaming

Code example

cURL

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sao10k/l3.3-euryale-70b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="sao10k/l3.3-euryale-70b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "sao10k/l3.3-euryale-70b",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Sao10K: Llama 3.3 Euryale 70B API, paid in rial

Buy credit with an Iranian bank card; no foreign card or account needed.
One Hormouz key reaches Sao10K: Llama 3.3 Euryale 70B and 600+ other models, and you pay only for what you use.
No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.

Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Llama 3.3 Euryale 70B cost?: Billing is usage-based: $0.65 per million input tokens and $0.75 per million output tokens. There is no monthly minimum. You pay only for the tokens you actually use.
How do I access Llama 3.3 Euryale 70B from inside Iran?: Create a Hormouz account, generate an API key and point your client at Hormouz. Access to Llama 3.3 Euryale 70B is served from inside Iran, so you do not need a foreign credit card, a VPN or any sanction-circumvention tooling.
Is Llama 3.3 Euryale 70B compatible with the OpenAI SDK?: Yes. Hormouz exposes an OpenAI-compatible chat-completions API. Change the base URL to Hormouz and drop in your Hormouz key, and existing OpenAI SDK code runs unchanged.
What context window does Llama 3.3 Euryale 70B support?: Llama 3.3 Euryale 70B supports a context window of up to 131K tokens, which is enough for long documents and extended conversations in a single request.
What is Llama 3.3 Euryale 70B best suited for?: It is tuned for creative roleplay, character-driven dialogue and long-form fiction. It follows custom formats and reply styles well and is not restrictive during roleplay, which makes it popular for immersive storytelling rather than factual or tool-using tasks.
Does Euryale 70B support tool calling or vision?: No. It is a text-only model without tool calling or image input. If you need function calling, structured agents or multimodal input, a model like Grok 4.20 or a Nova model is a better fit.

Updated 2026-10-13