uttapen
Create an API key

Qwen3 235B A22B Instruct 2507 API: toman pricing and code

qwen/qwen3-235b-a22b-2507

toolsjson
Create a keyTry it
Input · per 1M tokens
26,111 toman
Output · per 1M tokens
159,569 toman
One 1,000-word request ≈
241 toman

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

Qwen3 235B A22B Instruct 2507 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="qwen/qwen3-235b-a22b-2507",
    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 Qwen3 235B A22B Instruct 2507 good for?

Qwen (Alibaba) publishes this model; we expose it under the id "qwen/qwen3-235b-a22b-2507". Its context window is 262,144 tokens, roughly 197k English words in one request. A single response can run to 16,384 tokens. On price it sits in the "very cheap" band — cheaper than 92 and dearer than 314 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. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper.

Input runs at 26,111 toman per 1M tokens and output at 159,569 — output costs 6.1× 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 Hy3: Qwen3 235B A22B Instruct 2507 works out roughly 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 415 thousand-word requests on Qwen3 235B A22B Instruct 2507, and every 1,000 toman is about 4,149 words of round trip. A job with one million input tokens and one million output tokens comes to 185,680 toman in total. Filling this model's 262,144-token window costs 6,845 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-coder-next", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 1.4× cheaper (241 against 347 toman). Maximum answer length differs as well: 16,384 against 235,929 tokens. On parameters, this one takes 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 logit_bias, logprobs, min_p, repetition_penalty, top_k, top_logprobs — all through the standard request body. It does not support include_reasoning, reasoning, 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 Trinity Large Thinking at 262,144 tokens.

Where it makes sense: high-volume work such as classification, tagging and bulk summarising, 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

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

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 out103 toman
Summarising a ten-page document4,000 in + 600 out200 toman
Classifying a thousand short rows120,000 in + 20,000 out6,325 toman

Frequently asked

How do I call Qwen3 235B A22B Instruct 2507 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/qwen3-235b-a22b-2507". Nothing else in your code changes.
What does Qwen3 235B A22B Instruct 2507 cost in toman?
26,111 toman per 1M input tokens and 159,569 toman per 1M output tokens; a 1,000-word request is around 241 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Qwen3 235B A22B Instruct 2507 take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 16,384 tokens.
Does Qwen3 235B A22B Instruct 2507 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.