model
Kimi K3.1 Pro llm
A model record: onboarded once for the project and used by any eval's arms.
- aliases
eval-kimi-k31-pro- settings
reasoning_effortnone it reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all- onboarding
- vetted 2026-10-31
- best result per goal
- #30 of 55 Triage decisions on Orrery's error signals
01deployments and their onboarding
hosted · homelab LiteLLM (the fleet's gateway) · eval-kimi-k31-pro · onboarding pass 2026-10-31 · 11.0 tokens/s · 2 accepted
- where
- homelab LiteLLM (the fleet's gateway)
- build
eval-kimi-k31-pro- matches the record
- yes
- checked
- 2026-10-31
- onboarded on
- homelab LiteLLM (the fleet's gateway)
| probe | measurement | flag |
|---|---|---|
| endpoint | provider litellm · base url http://homelab:4001/v1 · model eval-kimi-k31-pro | — |
| digest found | None | — |
| default | s 5.54 · tokens out 106 · reasoned: yes · finish stop | — |
| chosen | s 3.08 · tokens out 34 · reasoned: no · finish stop · settings (reasoning effort none) | — |
| tokens per s | 11.0 | — |
| deterministic | no | — |
| json valid | yes | — |
Accepted: where it ran: a hosted gateway serves the provider's current build; there is no digest, revision or hash to pin; determinism: a hosted provider batches requests, so temperature 0 does not repeat exactly; repeats measure it
What it can do, across its deployments: reasons: yes · json mode: yes · reasoning off reasoning_effort: none
02settings history
| when | what changed | why |
|---|---|---|
| 2026-10-31 | reasoning_effort: (server default) → none | it reasoned by default on the onboarding probe (2026-10-31); off unless a task needs it (RUNBOOK §16): left at the server's default, one model reasons at length and the next not at all |
03arms
| arm | deployment | goal | its settings | arm smoke | result |
|---|---|---|---|---|---|
| triage_kimi_k31_pro_v1 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | — | none | triage_cost 0.646 |
| triage_kimi_k31_pro_v2 · rescored 5f2c057c orrery_triage_v1_labelled | hosted | Triage decisions on Orrery's error signals | max_tokens 1024 | pass 2026-10-31 | triage_cost 0.723 |