uttapen
Create an API key

Qwen3 Next 80B A3B Thinking API: toman pricing and code

qwen/qwen3-next-80b-a3b-thinking

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
43,519 toman
Output · per 1M tokens
348,150 toman
One 1,000-word request ≈
509 toman

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

Qwen3 Next 80B A3B Thinking 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-next-80b-a3b-thinking",
    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)

What is Qwen3 Next 80B A3B Thinking good for?

Qwen3 Next 80B A3B Thinking comes from Qwen (Alibaba); in uttapen you reach it with the model id "qwen/qwen3-next-80b-a3b-thinking". It accepts up to 262,144 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 235,929 tokens. On price it sits in the "cheap" band — cheaper than 151 and dearer than 255 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 43,519 toman per 1M tokens and output at 348,150 — output costs 8× 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 KAT-Coder-Pro V2: Qwen3 Next 80B A3B Thinking works out roughly 1.1× 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 196 thousand-word requests on Qwen3 Next 80B A3B Thinking, and every 1,000 toman is about 1,965 words of round trip. A job with one million input tokens and one million output tokens comes to 391,669 toman in total. Filling this model's 262,144-token window costs 11,408 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. On a thousand-word request this variant works out 2.2× dearer (509 against 234 toman). The context windows differ too: 262,144 against 131,072 tokens. Maximum answer length differs as well: 235,929 against 16,384 tokens. On parameters, this one takes logprobs, structured_outputs, top_logprobs while the other takes logit_bias, min_p.

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 logprobs, repetition_penalty, top_k, top_logprobs — all through the standard request body. By context size the nearest option from another provider is Trinity Large Thinking at 262,144 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, analysing a long document or codebase in one request.

Provider's own description

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

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 out205 toman
Summarising a ten-page document4,000 in + 600 out383 toman
Classifying a thousand short rows120,000 in + 20,000 out12,185 toman

Frequently asked

How do I call Qwen3 Next 80B A3B Thinking 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-next-80b-a3b-thinking". Nothing else in your code changes.
What does Qwen3 Next 80B A3B Thinking cost in toman?
43,519 toman per 1M input tokens and 348,150 toman per 1M output tokens; a 1,000-word request is around 509 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Qwen3 Next 80B A3B Thinking take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 235,929 tokens.
Does Qwen3 Next 80B A3B Thinking 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.