Qwen3.8 2.4T A95B API: toman pricing and code
qwen/qwen3.8-2.4t-a95b
You are billed for the usage the request actually reported. Prices follow the market. Cached input: 86,555 toman per 1M tokens.Pricing and top-ups
Qwen3.8 2.4T A95B example: a multi-step problem with reasoning
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
resp = client.chat.completions.create(
model="qwen/qwen3.8-2.4t-a95b",
messages=[{"role": "user", "content": (
"A shop has 3 warehouses. A ships 120 orders a day, B ships 85 and C ships 40. "
"If C closes and its load is split between A and B in proportion to their capacity, how many does each ship a day? "
"Work through it step by step and give just the two numbers at the end."
)}],
reasoning_effort="medium", # low | medium | high
)
print(resp.choices[0].message.content)
# reasoning tokens count as output tokens too:
print(resp.usage.completion_tokens_details)curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3.8-2.4t-a95b",
"messages": [{"role": "user", "content": "120 and 85 daily orders split across two warehouses; work through it step by step."}],
"reasoning": {"effort": "medium"}
}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const resp = await client.chat.completions.create({
model: "qwen/qwen3.8-2.4t-a95b",
messages: [{ role: "user", content: "120 and 85 daily orders are split between two warehouses; work through it step by step and give just the two numbers at the end." }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);
console.log(resp.usage.completion_tokens_details);What is Qwen3.8 2.4T A95B good for?
Qwen3.8 2.4T A95B comes from Qwen (Alibaba); in uttapen you reach it with the model id "qwen/
What you get on top of text in, text out: it supports tool calling, so it can invoke your own functions with valid arguments; 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 692,439 toman per 1M tokens and output at 2,077,316 — output costs 3× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 86,555 toman per 1M, which matters a lot if your system prompt is long. 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 Aion-3.0: Qwen3.8 2.4T A95B works out about 9% cheaper, 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 28 thousand-word requests on Qwen3.8 2.4T A95B, and every 1,000 toman is about 278 words of round trip. A job with one million input tokens and one million output tokens comes to 2,769,755 toman in total. Filling this model's 1,048,576-token window costs 726,075 toman on the input side alone, which is the real reason to keep conversation history short.
Its nearest relative in the catalogue is "qwen/
Qwen (Alibaba) has 42 models in our catalogue; the cheapest is Qwen3.7 Flash at 72 toman per thousand words and the dearest Qwen3.8 Max Prime at 7,201. Among the less common parameters it accepts logprobs, presence_penalty, reasoning_effort, repetition_penalty, top_k, top_logprobs — all through the standard request body. By context size the nearest option from another provider is DeepSeek V4 Flash 0423 at 1,048,576 tokens.
Where it makes sense: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, agents that reach out to APIs and databases, extracting data against a fixed schema, analysing a long document or codebase in one request.
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 1,870 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 4,016 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 124,639 toman |
Frequently asked
- How do I call Qwen3.8 2.4T A95B 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 "qwen/ qwen3.8-2.4t-a95b". Nothing else in your code changes. - What does Qwen3.8 2.4T A95B cost in toman?
- 692,439 toman per 1M input tokens and 2,077,316 toman per 1M output tokens; a 1,000-word request is around 3,601 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Qwen3.8 2.4T A95B take?
- Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 131,072 tokens.
- Does Qwen3.8 2.4T A95B support streaming and tool calling?
- Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.