uttapen
Create an API key

Qwen3 30B A3B Thinking 2507 API: toman pricing and code

qwen/qwen3-30b-a3b-thinking-2507

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
58,025 toman
Output · per 1M tokens
696,300 toman
One 1,000-word request ≈
981 toman

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

Qwen3 30B A3B Thinking 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/qwen3-30b-a3b-thinking-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 30B A3B Thinking 2507 good for?

The id for Qwen3 30B A3B Thinking 2507 in our API is "qwen/qwen3-30b-a3b-thinking-2507", served from Qwen (Alibaba). Context is 81,920 tokens; past that you have to summarise the history yourself. A single response can run to 32,768 tokens. On price it sits in the "mid-range" band — cheaper than 224 and dearer than 182 of the other paid models in the catalogue.

What it can do beyond plain text: 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.

Pricing is 58,025 toman per 1M input tokens and 696,300 per 1M output tokens. A 1,000-word round trip on Qwen3 30B A3B Thinking 2507 lands near 981 toman. 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 GPT Audio Mini: Qwen3 30B A3B Thinking 2507 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 102 thousand-word requests on Qwen3 30B A3B Thinking 2507, and every 1,000 toman is about 1,019 words of round trip. A job with one million input tokens and one million output tokens comes to 754,325 toman in total. Filling this model's 81,920-token window costs 4,753 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "qwen/qwen3-235b-a22b-thinking-2507", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (981 and 954 toman). The context windows differ too: 81,920 against 131,072 tokens. Maximum answer length differs as well: 32,768 against 117,964 tokens. On parameters the other takes logprobs, repetition_penalty, top_logprobs.

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 Morph V3 Fast at 81,920 tokens.

Good fits: 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.

Provider's own description

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

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 out366 toman
Summarising a ten-page document4,000 in + 600 out650 toman
Classifying a thousand short rows120,000 in + 20,000 out20,889 toman

Frequently asked

How do I call Qwen3 30B A3B Thinking 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/qwen3-30b-a3b-thinking-2507". Nothing else in your code changes.
What does Qwen3 30B A3B Thinking 2507 cost in toman?
58,025 toman per 1M input tokens and 696,300 toman per 1M output tokens; a 1,000-word request is around 981 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Qwen3 30B A3B Thinking 2507 take?
Up to 81,920 tokens per request, roughly 61k words. A single answer can reach 32,768 tokens.
Does Qwen3 30B A3B Thinking 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.