Respan's behaviour-scoring model for evals, guardrails and monitoring. For each plain-language behaviour you define, it reads a conversation or agent trace and returns the probability the behaviour is present, absent or not observable, in one forward pass.
Together AI's Jev-style classifier. A LoRA fine-tune of Qwen3.5-4B that reads a state, a question and 2 to 24 options and returns one option letter. Served on Together's platform; recipe published.
Decides
noul, classify
choice, classify, route
Architecture
span
tev
Fine-tuned from
—
qwen/qwen3.5-4b
License
proprietary
Unspecified — weights licence being finalised
Availability
Hosted API
Open weights + hosted API
Hosted by
Respan
Together AI
Input price
$0.020/MTok
$0.042/MTok
Decision accuracy
—
88.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
Evaluation suite
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between span-01 and tev1?
span-01 is from Respan and tev1 from Together AI. span-01 is only available as a hosted API; tev1 has open weights and a hosted API. Both answer classify questions. Only span-01 answers noul. Only tev1 answers choice and route. span-01 is licensed proprietary; tev1, other.
Which is more accurate, span-01 or tev1?
Only tev1 publishes an accuracy figure (88.0% on Together development set (reused, not held out)); span-01 does not, so there is no comparison to make without your own test.
Which is cheaper, span-01 or tev1?
span-01: $0.02 / $0 per 1M. tev1: $0.042 / $0 per 1M, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run span-01 or tev1 locally?
tev1 yes — systemone pull together-ai/tev1 downloads its weights. The other is only served as a hosted API.
