uttapen

Qwen3.5 397B A17B API: toman pricing and code

qwen/qwen3.5-397b-a17b

visiontoolsreasoningjson
Input · per 1M tokens
113,149 toman
Output · per 1M tokens
678,893 toman
One 1,000-word request ≈
1,030 toman

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

Qwen3.5 397B A17B 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/qwen3.5-397b-a17b",
    "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"}}
      ]
    }]
  }'

What is Qwen3.5 397B A17B good for?

The id for Qwen3.5 397B A17B in our API is "qwen/qwen3.5-397b-a17b", served from Qwen (Alibaba). Context is 262,144 tokens; past that you have to summarise the history yourself. A single response can run to 65,536 tokens. On price it sits in the "mid-range" band — cheaper than 223 and dearer than 183 of the other paid models in the catalogue.

What it can do beyond plain text: 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; 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 113,149 toman per 1M input tokens and 678,893 per 1M output tokens. A 1,000-word round trip on Qwen3.5 397B A17B lands near 1,030 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 Kimi K2.5: Qwen3.5 397B A17B works out roughly 1× more expensive, 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 97 thousand-word requests on Qwen3.5 397B A17B, and every 1,000 toman is about 971 words of round trip. A job with one million input tokens and one million output tokens comes to 792,041 toman in total. Filling this model's 262,144-token window costs 29,661 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "qwen/qwen3.5-122b-a10b", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (1,030 and 1,015 toman). Maximum answer length differs as well: 65,536 against 81,920 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. By context size the nearest option from another provider is Trinity Large Thinking at 262,144 tokens.

Good fits: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, 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.

Provider's own description

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...

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 out441 toman
Summarising a ten-page document4,000 in + 600 out860 toman
Classifying a thousand short rows120,000 in + 20,000 out27,156 toman

Price history

DateInput (toman/1M)Output (toman/1M)
2026-09-07113,149678,893
2026-09-06159,5691,015,438

Every price change for this model is recorded. Toman figures use today's rate.

Frequently asked

How do I call Qwen3.5 397B A17B 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/qwen3.5-397b-a17b". Nothing else in your code changes.
What does Qwen3.5 397B A17B cost in toman?
113,149 toman per 1M input tokens and 678,893 toman per 1M output tokens; a 1,000-word request is around 1,030 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Qwen3.5 397B A17B take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 65,536 tokens.
Does Qwen3.5 397B A17B 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.