Qwen2.5 VL 32B Instruct API Pricing

Qwen2.5 VL 32B Instruct pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What Qwen2.5 VL 32B Instruct costs in practice

1,000 requests with 2,000 input and 500 output tokens each

100 long-document requests with 100,000 input and 2,000 output tokens each

Qwen2.5 VL 32B Instruct features

• Function calling
• Image input

Use Qwen2.5 VL 32B Instruct with LiteLLM

Call Qwen2.5 VL 32B Instruct through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="deepinfra/Qwen/Qwen2.5-VL-32B-Instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: qwen2.5-vl-32b-instruct
    litellm_params:
      model: deepinfra/Qwen/Qwen2.5-VL-32B-Instruct
      api_key: os.environ/DEEPINFRA_API_KEY

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "qwen2.5-vl-32b-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Qwen2.5 VL 32B Instruct FAQ

More Alibaba models

• Qwen2.5 14B Instruct$0.80 / $0.80 per 1M tokens
• Qwen2.5 32B Instruct$0.06 / $0.20 per 1M tokens
• Qwen2.5 Coder 7B$0.01 / $0.03 per 1M tokens
• Qwen2.5 7B Instruct$0.04 / $0.10 per 1M tokens
• Qwen2.5 VL 72B Instruct$0.25 / $0.75 per 1M tokens
• Qwen2.5 Coder 3B Instruct$0.01 / $0.03 per 1M tokens
• Qwen2.5 Coder 7B Instruct$0.01 / $0.03 per 1M tokens
• Qwen2.5 72B Instruct Turbo$1.20 / $1.20 per 1M tokens