Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Qwen2.5 VL 72B Instruct - Model - OpenSmartRoute
Modelv1.0.0
Qwen2.5 VL 72B Instruct
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
Reference model card from the OpenRouter listing - model qwen/qwen2.5-vl-72b-instruct. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Qwen2.5 VL 72B Instruct
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
Facts
Vendor
Qwen
Context window
128,000 tokens
Max output
115,200 tokens
Input price
$0.80 / 1M tokens
Output price
$1.00 / 1M tokens
Input
text, image
Output
text
Tool calling
no
Structured outputs
yes
Reasoning
no
Open weights
Qwen/Qwen2.5-VL-72B-Instruct
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model qwen/qwen2.5-vl-72b-instruct
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "model-qwen-qwen2-5-vl-72b-instruct", ...}
Installed into a catalogue, chosen by a router
Install Qwen2.5 VL 72B Instruct and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
