All models

COMPARE

Put models side by side.

What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.

Propertytogether-ai/tev1
SummaryTogether 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.
Decideschoice, classify, route
Architecturetev
Fine-tuned fromqwen/qwen3.5-4b
LicenseUnspecified — weights licence being finalised
AvailabilityOpen weights + hosted API
Hosted byTogether AI
Input price$0.042/MTok
Decision accuracy88.0%
Calibration error—
Valid action rate—
Median latency—
p95 latency—
Evaluation suiteTogether development set (reused, not held out)
Latest version2026.09
Variants—
Size of latest version8.7 GB
Files10
Downloads0
Stars0
Tagssystem-one, qwen, lora, together, 4b
UpdatedSep 25, 2026