AI
Inference.
Routing strategies: price, latency, reputation, weighted. The router picks a provider per request and tracks usage.
- STATUS
- Testnet
- CRATE
- tenzro-model
- STABILITY
- Stable
- TYPE
- Component
01
Strategies
price cheapest provider
latency fastest provider
reputation highest-reputation provider
weighted blended score (price + latency + reputation)02
Modality dispatch
InferenceRouter::route() reads model.modality and dispatches to Chat, Forecast, VisionEmbed, VisionSimilarity, TextEmbed, Segment, Detect, Transcribe, or VideoEmbed runtimes.
03
Usage tracking
Every successful inference records a UsageRecord with input tokens, output tokens, cost, and latency. Persisted in CF_MODELS under usage: prefix.
04
Request
tenzro inference request qwen3-0.6b "hello"
tenzro chat qwen3-0.6b
# Interactive REPL on the chosen modelRelated