Skip to content

Status

Bee status

Live snapshot of the Bee Intelligence Engine. The dashboard polls /api/health every 15 seconds and reports backend liveness, round-trip latency, and the per-component view used by the operations team. For incident history beyond the rolling check, see the changelog.

Checking…

Awaiting backend response

Inference tiers

Cell

google/gemma-4-E4B-it on Modal CPU

Checking…

Brood

Modal CPU, scale-to-zero

Checking…

Comb

Modal L4 GPU

Checking…

Buzz

Modal A10G GPU

Checking…

Hive

Modal A100 40GB

Checking…

Swarm

Vercel fan-out router

Checking…

Enclave

On-prem / customer-managed

Checking…

Tiers currently share the parent backend probe. Per-tier health endpoints land with the observability roadmap milestone.

Platform & integrations

Bee API (chat completions)

Checking…

Audio — Whisper STT (Groq)

Checking…

Audio — Orpheus TTS (Groq)

Checking…

Vision (NVIDIA Build)

Checking…

RAG embeddings (NVIDIA NV-Embed)

Checking…

RAG reranker (NVIDIA Mistral 4B)

Checking…

Prompt-injection guard (Llama Prompt Guard)

Checking…

Content safety (Llama Guard 4)

Checking…

Billing (Stripe)

Checking…

SLA & incident notifications

Production availability targets are described per plan on the pricing page. SEV-1 incidents are notified to the account-owner email and posted as a changelog entry within 14 days; we do not sub-process incident details to a third-party status-page vendor.