tbuy

qwen3.5-ocr API pricing & access

qwen3.5-ocr API pricing: $0.07 per 1M tokens. Alibaba Qwen 3.5 OCR model for text recognition in images and documents

qwen3.5-ocr API access

Alibaba Qwen 3.5 OCR model for text recognition in images and documents

Compare supported API endpoints and capabilities, then access qwen3.5-ocr through the unified API gateway.

Category
text
Supported APIs
OpenAI Chat Completions API, Anthropic Messages API
API endpoints
POST /v1/chat/completions, POST /v1/messages

qwen3.5-ocr API pricing

Base input price
$0.07 per 1M tokens
Base output price
$0.29 per 1M tokens

Base prices are shown in USD before group-specific adjustments. Open the live pricing page for current access-group prices.

About qwen3.5-ocr

Qwen3.5 OCR targets document parsing, text localization and key-information extraction for receipts, tables and scans. Direct PDF parsing uses the official Responses API and must be distinguished from image input through chat.

Use fixed cases for the tasks described above. Integration follows the listed endpoint, selected route parameters and current group pricing; official capabilities do not establish acceptance for every channel. Compare gui-plus.

Official reference 1, checked 2026-10-14.

Use cases and prompting

  1. Choose extraction, localization or parsing and validate the listed interface with a clear image.
  2. Confirm Responses support for direct PDF parsing rather than moving file fields into a Chat request.
  3. Review page order, reading order, tables and numbers, with manual checks for dense or low-resolution text.
  4. Save source material, parsed results and error IDs; validate follow-ups and long-file limits before batching.

API documentation.

How to call qwen3.5-ocr

qwen3.5-ocr is served through tbuy's unified gateway. Existing OpenAI or Anthropic SDK code keeps working: point base_url at https://modelsok.com and use your tbuy API key.

curl (OpenAI-compatible)

curl https://modelsok.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen3.5-ocr", "messages": [{"role": "user", "content": "Hello"}]}'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(base_url="https://modelsok.com/v1", api_key="YOUR_API_KEY")
response = client.chat.completions.create(
    model="qwen3.5-ocr",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Python (anthropic SDK)

from anthropic import Anthropic

client = Anthropic(base_url="https://modelsok.com", api_key="YOUR_API_KEY")
message = client.messages.create(
    model="qwen3.5-ocr",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

Frequently asked questions about qwen3.5-ocr

What is qwen3.5-ocr?

Alibaba Qwen 3.5 OCR model for text recognition in images and documents

How do I call qwen3.5-ocr?

Create an API key with access to qwen3.5-ocr, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is qwen3.5-ocr priced?

Pricing depends on the selected provider group and the model billing unit. Refer to the current input, output, request, or media prices in the pricing section.

How should I evaluate qwen3.5-ocr for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.

Back to AI model API pricing