Qwen-OCR text extraction models

POST

/compatible-mode/v1/chat/completions

from openai import OpenAI
import os

PROMPT_TICKET_EXTRACTION = """
Please extract the invoice number, train number, departure station, arrival station, departure date and time, seat number, seat class, ticket price, ID card number, and passenger name from the train ticket image.
You must accurately extract the key information. Do not omit or fabricate information. Replace any single character that is blurry or obscured by strong light with an English question mark (?).
Return the data in JSON format as follows: {'invoice_number': 'xxx', 'departure_station': 'xxx', 'arrival_station': 'xxx', 'departure_date_and_time':'xxx', 'seat_number': 'xxx','ticket_price':'xxx', 'id_card_number': 'xxx', 'passenger_name': 'xxx'},
"""

try:
  client = OpenAI(
    # If the environment variable is not configured, replace the following line with your API key: api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Singapore (ap-southeast-1). For another region, replace ap-southeast-1 in the URL.
    # API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
    base_url="https://ap-southeast-1.maas.qwencloudapi.com/compatible-mode/v1",
  )
  completion = client.chat.completions.create(
    model="qwen-vl-ocr-2025-11-20",
    messages=[
      {
        "role": "user",
        "content": [
          {
            "type": "image_url",
            "image_url": {"url":"https://img.alicdn.com/imgextra/i2/O1CN01ktT8451iQutqReELT_!!6000000004408-0-tps-689-487.jpg"},
            # The minimum pixel threshold for the input image. If the image has fewer pixels than this value, it is enlarged until its total pixel count exceeds min_pixels.
            "min_pixels": 32 * 32 * 3,
            # The maximum pixel threshold for the input image. If the image has more pixels than this value, it is reduced until its total pixel count is below max_pixels.
            "max_pixels": 32 * 32 * 8192
          },
          # The model supports passing a prompt in the following text field. If no prompt is passed, the default prompt is used: Please output only the text content from the image without any additional descriptions or formatting.
          {"type": "text",
                     "text": PROMPT_TICKET_EXTRACTION}
        ]
      }
    ])
  print(completion.choices[0].message.content)
except Exception as e:
  print(f"Error message: {e}")

{
  "id": "<string>",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": {},
      "message": {
        "content": "<string>",
        "refusal": "<string>",
        "role": "assistant",
        "audio": {},
        "function_call": {},
        "tool_calls": [],
        "annotations": null
      }
    }
  ],
  "created": 0,
  "model": "<string>",
  "object": "chat.completion",
  "service_tier": "<string>",
  "system_fingerprint": "<string>",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "text_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0,
      "image_tokens": 0,
      "text_tokens": 0
    }
  }
}

Authorizations

string

header

required

API key authentication. Get an API key from the QwenCloud console.

Body

application/json

string

required

The name of the model. See Qwen-OCR for a list of supported models.

Example:qwen-vl-ocr-2025-11-20

object[]

required

A sequence of messages that provides context to the model in conversational order.

Show child attributes

enum<string>

required

The role of the user message. The value must be user.

Available options:user

object[]

required

The content of the message.

Show child attributes

enum<string>

The content type. Use text for text input, image_url for image input.

Available options:text,image_url

string

The input text. Default: Please output only the text content from the image without any additional descriptions or formatting.

object

Information about the input image. Required when type is image_url.

Show child attributes

string

required

The URL or Base64-encoded Data URL of the image. For more information about passing a local file, see Text extraction.

integer

The minimum pixel threshold for the input image in pixels. If an input image has a pixel count below min_pixels, it is enlarged until its total pixel count exceeds min_pixels.

Conversion between image tokens and pixels:

qwen3.5-ocr and qwen-vl-ocr-2025-11-20: Each token corresponds to 32×32 pixels.
qwen-vl-ocr and earlier models: Each token corresponds to 28×28 pixels.

Value range:

qwen3.5-ocr and qwen-vl-ocr-2025-11-20: Default and minimum value is 3072 (3×32×32).
qwen-vl-ocr and earlier models: Default and minimum value is 3136 (4×28×28).

integer

The maximum pixel threshold for the input image in pixels. If the pixel count of the input image is within the [min_pixels, max_pixels] range, the model processes the original image without resizing. If the pixel count exceeds max_pixels, the image is scaled down until its pixel count is less than max_pixels.

Conversion between image tokens and pixels:

qwen3.5-ocr and qwen-vl-ocr-2025-11-20: Each token corresponds to 32×32 pixels.
qwen-vl-ocr and earlier models: Each token corresponds to 28×28 pixels.

Value range:

qwen3.5-ocr and qwen-vl-ocr-2025-11-20: Default 8388608 (8192×32×32), maximum 30720000 (30000×32×32).
qwen-vl-ocr and earlier models: Default 6422528 (8192×28×28), maximum 23520000 (30000×28×28).

boolean

defaultfalse

Specifies whether to return the response in streaming mode. false: returns the complete response at once. true: returns data blocks as the model generates them.

object

Configuration settings for streaming output. Applies only when stream is true.

Show child attributes

boolean

defaultfalse

Whether to include token usage information in the last data block of the stream.

integer

The maximum number of tokens to generate in the output. If the generated content exceeds this value, the response is truncated.

For qwen3.5-ocr, qwen-vl-ocr-2025-11-20, and qwen-vl-ocr-2024-10-28, the default and maximum values are the same as the model's maximum output length.

boolean

defaultfalse

Specifies whether to return the log probabilities of the output tokens.

integer

default0

Specifies the number of most likely tokens to return at each generation step. Value range: [0, 5]. Takes effect only when logprobs is true.

number

default0.01

The sampling temperature controls the diversity of the generated text. Higher = more diverse, lower = more deterministic. Value range: [0, 2). Only set one of temperature or top_p.

number

default0.001

Probability threshold for nucleus sampling. Higher = more diverse, lower = more deterministic. Value range: (0, 1.0]. Only set one of temperature or top_p.

integer

default1

Size of the candidate set for sampling. A larger value increases randomness. If None or greater than 100, only top_p takes effect. Must be >= 0. Non-standard OpenAI parameter — in Python SDK use extra_body={"top_k": xxx}.

number

default1

Penalty for repeated sequences. Higher values reduce repetition. 1.0 means no penalty.

number

default0

Controls content repetition. Range: [-2.0, 2.0]. Positive reduces repetition, negative increases it.

integer

A random number seed for reproducible results. Value range: [0, 2^31−1].

string

Stop words. When a specified string or token_id appears, generation stops immediately. Can be a string or array. If stop is an array, you cannot mix token_ids and strings as elements.

Response

200-application/json

string

The unique identifier for this request.

object[]

Show child attributes

enum<string>

The reason the model stopped generating. stop when complete, length when truncated.

Available options:stop,length

integer

The index in the choices array.

object | null

Log probability information. Null unless logprobs is enabled.

object

Show child attributes

string

The content returned by the model.

string | null

Always null.

enum<string>

Always assistant.

Available options:assistant

object | null

Always null.

object | null

Always null.

unknown[] | null

Always null.

unknown[]

Reserved field. Currently null.

integer

UNIX timestamp when this request was created.

string

The model used for this request.

enum<string>

Always chat.completion.

Available options:chat.completion

string | null

Always null.

string | null

Always null.

object

Token usage information.

Show child attributes

integer

Tokens in the model's output.

integer

Tokens in the input.

integer

Sum of prompt_tokens and completion_tokens.

object

Show child attributes

integer | null

Always null.

integer | null

Always null.

integer | null

Always null.

integer

Tokens for text output.

integer | null

Always null.

object

Show child attributes

integer | null

Always null.

integer | null

Always null.

integer

Tokens for image input.

integer

Tokens for text input.