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.
DeepSeek V3.2 - Model - OpenSmartRoute
Modelv1.0.0
DeepSeek V3.2
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
Reference model card from the OpenRouter listing - model deepseek/deepseek-v3.2. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
DeepSeek V3.2
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Facts
Vendor
DeepSeek
Context window
163,840 tokens
Max output
65,536 tokens
Input price
$0.28 / 1M tokens
Output price
$0.42 / 1M tokens
Input
text
Output
text
Tool calling
yes
Structured outputs
yes
Reasoning
yes
Open weights
deepseek-ai/DeepSeek-V3.2
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model deepseek/deepseek-v3.2
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-deepseek-deepseek-v3-2", ...}
Installed into a catalogue, chosen by a router
Install DeepSeek V3.2 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.
