Alibaba's efficient Mixture-of-Experts model with 30B total parameters and only 3B activated per token, optimized for fast inference.
Upstream Providers
ZDR only
Hugging Face
huggingface-byok
In$0Out$0TTFT—TPS—
No ZDRTools
Cloudflare AI Gateway
cloudflare
In$0.05Out$0.34TTFT350msTPS100.0 tps
ZDRTools
OpenRouter
openrouter-byok
In$0.10Out$0.30TTFT—TPS—
BYOKBYOKNo ZDRTools
API Details
Chat Completions API
/api/v1/chat/completions
OpenAI-compatible endpoint with a messages array. Standard interface for chat-based interactions.
Uptime & Health
Uptime %Finish ReasonsLatency
No uptime data yet
These providers haven't been health-probed for this model yet. The router still routes around upstreams that fail live requests — uptime fills in once probe history accrues.