Models and language routing

Laya Cloud runs two pinned checkpoints. /v1/models lists the public aliases; the model field in a System One response names the checkpoint that actually ran.

| Request model | Selection | Response model | |---|---|---| | jev-latest, jev-preview, jev-1.13.0, laya-latest | Detect language in the state when AUTO_ROUTE_MULTILINGUAL=true (the default) | laya-0.3.5 for English; laya-multilingual-0.3.9 for detected non-English | | laya-0.3.5 | English checkpoint, including non-English states | laya-0.3.5 | | laya-multilingual, laya-multilingual-0.3.9 | Multilingual checkpoint, including English states | laya-multilingual-0.3.9 |

The x-laya-routed-language response header is an ISO 639-1 code such as en, de, or fr; und means the text was too short or ambiguous to identify. Routing reads string values of state, not JSON field names or the question instructions. It uses a pinned, in-process, CPU-only classifier and makes no network request. Ambiguous text stays on English; choose laya-multilingual explicitly if you already know the state is non-English. Set AUTO_ROUTE_MULTILINGUAL=false to keep aliases on English.

Language and quality

The multilingual model card reports evaluations on about 50 languages; its “100+ languages” statement is unverified. The local quick check covers German, French and Spanish only: 11/12 correct versus 9/12 for the English checkpoint. On English, the multilingual checkpoint scored 8/12 versus 10/12. The larger, mostly English local corpus scored 59/78 (76%) on accepted short-state answers, below its provisional 80% gate. These samples are directional, and multilingual confidence is uncalibrated. Review decision thresholds on your own traffic before changing them.

Per-model limits

| Limit | English | Multilingual | |---|---:|---:| | Laya sequence window per question | 512 tokens | 1024 tokens | | Instruction and option head budget | 192 tokens | 256 tokens | | Typical state room | 437–478 tokens | 951–990 tokens | | Default processed-token cap per request | 3,500 | 6,000 | | Questions per request | 32 | 32 |

The worker rejects input that would be truncated. It bills the same Jev-style input-token count for either model; more questions increase processed compute tokens. Pricing is currently the same for both models. Both checkpoints have a 9-second API deadline, with 500 ms reserved for response and metering. The multilingual cap and 1.1 ms/token admission seed come from the shared-host CPU quick check; they need a fresh latency check on the deployment CPU.