Status tal-pjattaforma

Ir-reġjuni tal-endpoints jiddeskrivu konfigurazzjoni, mhux ġeolokazzjoni indipendenti. L-inferenza mock ma tmexxi l-ebda piż tal-mudell u tirrapporta dev-mock. L-inferenza reali teħtieġ backend konfigurat għar-reġjun tal-endpoint; il-post Ewropew u s-sjieda Ewropea huma distinti.

de-ber

MudelliRuntimeStatus tal-pjattaformauptime
measured over the last 1 hour · 12 checks
p50 latency
Devstral Small 2 (24B) mock Operattiv 100% 0 ms
EuroLLM-22B-Instruct (2512) mock Operattiv 100% 0 ms

de-fra

MudelliRuntimeStatus tal-pjattaformauptime
measured over the last 1 hour · 12 checks
p50 latency
EuroLLM-1.7B-Instruct mock Operattiv 100% 0 ms
EuroLLM-9B-Instruct (2512) mock Operattiv 100% 0 ms
Whisper large-v3 mock Operattiv 100% 0 ms

fr-par

MudelliRuntimeStatus tal-pjattaformauptime
measured over the last 1 hour · 12 checks
p50 latency
Mistral Small 4 (119B-A6B) mock Operattiv 100% 0 ms

Feature flags

FlagStateMeaning
gpu_enabled off First-party GPU inference is available (VLLM_BASE_URL set)
partner_endpoints off Partner endpoints may be routed to
public_playground on The public playground is rate limited and open
public_signup on Anyone may create an account
stripe_enabled off Card payments are enabled on this deployment

Dan l-użu jista' jmexxi inferenza mock: tweġiba tista' tiġi minn mudell sostitut minflok mill-mudell imsemmi fit-talba. Meta l-modalità mock tkun mixgħula, il-konsol u t-traċċa jgħidu hekk, u ma ssir l-ebda ħlas tat-token.