Qwen: Qwen3.6 Flash
Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window.
- Input
- 68,320 Toman/M tokens
- Output
- 406,504 Toman/M tokens
- Context
- 1M
- Max output
- 66K
- Published
- Apr 27, 2026
- Maker
- Qwen
Free plan prices, in Toman at today's rate. Plans and prices
Price by plan
Toman per million tokens at today's rate. A plan lowers the price of your usage up to a limit each period. Up to 256K tokens.
| Plan | Input | Output |
|---|---|---|
| Free | 68,320 | 406,504 |
| Pro | 65,520 | 389,844 |
| Max | 62,720 | 373,184 |
Long prompts
This model costs more when a request's prompt is long: once the prompt reaches the size below, the whole request is billed at the higher price (as its provider bills it). Toman per million tokens, per plan.
| Plan | Input | Output |
|---|---|---|
| Free | 273,280 | 1,082,872 |
| Pro | 262,080 | 1,038,492 |
| Max | 250,880 | 994,112 |
Images and other units
Toman per million tokens of each kind, per plan, at today's rate. A generated 1024×1024 image is usually 1,100–1,300 image tokens on Gemini image models and up to about 6,000 on GPT image models at high quality; the exact count is in each response's usage.
| Unit | Free | Pro | Max |
|---|---|---|---|
| Prompt cache writes (5 minutes) | 85,400 | 81,900 | 78,400 |
Capabilities
- Text
- Vision
- Tools
- JSON
- Reasoning
What it takes and gives
- Text
- Image
- Video
- Text
Every input listed here works through the API and the playground: images and PDFs as data URLs or https links, audio as base64, video as a data URL or a link the model supports.
Call it
Pass qwen/qwen3.6-flash as the model name, or let router/auto choose for you.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://ai.fluxcdn.cloud/api/v1",
api_key=os.environ["FLUXCDN_API_KEY"],
)
resp = client.chat.completions.create(
model="router/auto",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
