Qwen3 8B API: toman pricing and code
qwen/qwen3-8b
toolsreasoningjsonYou are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups
Qwen3 8B 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/qwen3-8b",
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/qwen3-8b",
"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/qwen3-8b",
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 8B good for?
The id for Qwen3 8B in our API is "qwen/qwen3-8b", served from Qwen (Alibaba). Context is 131,072 tokens; past that you have to summarise the history yourself. A single response can run to 8,192 tokens. On price it sits in the "very cheap" band — cheaper than 85 and dearer than 321 of the other paid models in the catalogue.
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 33,945 toman per 1M tokens and output at 132,007 — output costs 3.9× 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 DeepSeek V3.2 Exp: Qwen3 8B works out roughly 1.2× cheaper, and its context window is smaller. 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 463 thousand-word requests on Qwen3 8B, and every 1,000 toman is about 4,630 words of round trip. A job with one million input tokens and one million output tokens comes to 165,952 toman in total. Filling this model's 131,072-token window costs 4,449 toman on the input side alone, which is the real reason to keep conversation history short.
Its nearest relative in the catalogue is "qwen/qwen3-30b-a3b", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (216 and 234 toman). Maximum answer length differs as well: 8,192 against 16,384 tokens. On parameters the other takes logit_bias, min_p, repetition_penalty.
Qwen (Alibaba) has 53 models in our catalogue; the cheapest is Qwen3.7 Flash at 60 toman per thousand words and the dearest Qwen3.8 Max (0902) at 3,017. Among the less common parameters it accepts top_k — all through the standard request body. It does not support 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, agents that reach out to APIs and databases, extracting data against a fixed schema.
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...
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 | 104 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 215 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 6,713 toman |
Frequently asked
- How do I call Qwen3 8B 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/qwen3-8b". Nothing else in your code changes.
- What does Qwen3 8B cost in toman?
- 33,945 toman per 1M input tokens and 132,007 toman per 1M output tokens; a 1,000-word request is around 216 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Qwen3 8B take?
- Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 8,192 tokens.
- Does Qwen3 8B 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.