Status

Live health signal for the API gateway and inference pool. Auto- refreshes every 30 seconds.

API Gateway

Down

Inference Pool

—

slots in use

Uptime

—

current process

Models

ModelTierStatus
Llama 3.2 3B
llama-3b
fastUnknown
Qwen 2.5 7B
qwen2.5-7b
fastUnknown
Mistral 7B
mistral-7b
fastUnknown
Hermes 3 8B
hermes-8b
fastUnknown
Llama 3.3 70B
llama-70b
frontierUnknown
Kimi K2.5
kimi-k2.5
frontierUnknown
Qwen3 235B
qwen3-235b
frontierUnknown
Hermes 3 405B
hermes-405b
frontierUnknown
Venice Uncensored
venice-uncensored
specialUnknown
GPT OSS 120B
gpt-oss-120b
specialUnknown

Per-model health checks are derived from the aggregate pool. Granular per-model probes ship in the next release.