Platform status

Endpoint regions describe configuration, not independent geolocation. Mock inference runs no model weights and reports dev-mock. Real inference requires a backend configured for the endpoint region; European location and European ownership are distinct.

de-ber

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

de-fra

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

fr-par

ModelsRuntimePlatform statusuptime
measured over the last 1 hour · 12 checks
p50 latency
Mistral Small 4 (119B-A6B) mock Operational 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

This deployment may run mock inference: a response can come from a stand-in model rather than the model named in the request. When mock mode is on, the console and the trace say so, and no token charge is made.