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.
Kimi K2 0905 - Model - OpenSmartRoute
Modelv1.0.0
Kimi K2 0905
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
Reference model card from the OpenRouter listing - model moonshotai/kimi-k2-0905. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
Kimi K2 0905
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
Facts
Vendor
Moonshot AI
Context window
262,144 tokens
Max output
98,304 tokens
Input price
$0.60 / 1M tokens
Output price
$2.50 / 1M tokens
Input
text
Output
text
Tool calling
yes
Structured outputs
yes
Reasoning
no
Open weights
moonshotai/Kimi-K2-Instruct-0905
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model moonshotai/kimi-k2-0905
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-moonshotai-kimi-k2-0905", ...}
Installed into a catalogue, chosen by a router
Install Kimi K2 0905 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.
