Qwen3 VL 235B A22B Instruct API: toman pricing and code
qwen/qwen3-vl-235b-a22b-instruct
visiontoolsjsonYou are billed for the usage the request actually reported. Prices follow the market. Cached input: 29,013 toman / 1M.Pricing and top-ups
Qwen3 VL 235B A22B Instruct example: reading an image into JSON
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3-vl-235b-a22b-instruct",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "Return only the invoice number and the total, as JSON."},
{"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
]
}]
}'import base64, json
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
img = base64.b64encode(open("factor.jpg", "rb").read()).decode()
resp = client.chat.completions.create(
model="qwen/qwen3-vl-235b-a22b-instruct",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "Return the invoice number, the date and the total as JSON."},
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img}"}},
],
}],
response_format={"type": "json_object"},
)
print(json.loads(resp.choices[0].message.content))import OpenAI from "openai";
import { readFileSync } from "node:fs";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const img = readFileSync("factor.jpg").toString("base64");
const resp = await client.chat.completions.create({
model: "qwen/qwen3-vl-235b-a22b-instruct",
messages: [{
role: "user",
content: [
{ type: "text", text: "Return the invoice number, the date and the total as JSON." },
{ type: "image_url", image_url: { url: `data:image/jpeg;base64,${img}` } },
],
}],
response_format: { type: "json_object" },
});
console.log(JSON.parse(resp.choices[0].message.content));What is Qwen3 VL 235B A22B Instruct good for?
Qwen3 VL 235B A22B Instruct comes from Qwen (Alibaba); in uttapen you reach it with the model id "qwen/qwen3-vl-235b-a22b-instruct". 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 32,768 tokens. On price it sits in the "cheap" band — cheaper than 195 and dearer than 211 of the other paid models in the catalogue.
What you get on top of text in, text out: it reads images directly, which makes it a real option for invoices, forms and screenshots; 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 60,926 toman per 1M tokens and output at 551,238 — output costs 9× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 29,013 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 Gemini 3.6 Flash (batch): Qwen3 VL 235B A22B Instruct works out roughly 1.1× 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 126 thousand-word requests on Qwen3 VL 235B A22B Instruct, and every 1,000 toman is about 1,256 words of round trip. A job with one million input tokens and one million output tokens comes to 612,164 toman in total. Filling this model's 262,144-token window costs 15,971 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-vl-30b-a3b-instruct", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 2.8× dearer (796 against 283 toman). Maximum answer length differs as well: 32,768 against 16,384 tokens.
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, pulling text and fields out of images, agents that reach out to APIs and databases, extracting data against a fixed schema, analysing a long document or codebase in one request.
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
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 | 312 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 574 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 18,336 toman |
Frequently asked
- How do I call Qwen3 VL 235B A22B Instruct 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-vl-235b-a22b-instruct". Nothing else in your code changes.
- What does Qwen3 VL 235B A22B Instruct cost in toman?
- 60,926 toman per 1M input tokens and 551,238 toman per 1M output tokens; a 1,000-word request is around 796 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Qwen3 VL 235B A22B Instruct take?
- Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 32,768 tokens.
- Does Qwen3 VL 235B A22B Instruct support streaming and tool calling?
- Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.