Qwen 2.5 VL

VISION

Qwen · qwen/qwen-2.5-vl

Available

Vision-language model used for scanned NID, invoice and form extraction workloads. Placeholder availability.

Input / 1M tokens

৳54

Output / 1M tokens

৳66

Context length

32K

Max output

Placeholder rates. Final pricing is published per model before launch.

Suitable for

Vision
Bangla

Example request

cURL

curl https://padmarouter.com/v1/chat/completions \
  -H "Authorization: Bearer $PADMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen-2.5-vl",
    "messages": [{"role": "user", "content": "Hello from Dhaka!"}]
  }'

Try in Playground Docs for this model

Performance

Throughput58 tok/s

Time to first token1.9s

StreamingSupported

Tool callingSupported

Measured from Dhaka over the last 24h of prototype traffic.

Routing

Primary routeQwen direct

FallbackSecondary region

Prompt retentionNot retained