Tev1-0.8B-experimental
Tev1-0.8B-experimental by Together is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 12.0 on the Jev Decision Index (rank 135).
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- Together
- Parameters
- 873M
- Released
- Sep 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Decoder LM with a decision readout
- Backbone
- Qwen/Qwen3.5-0.8B-Base
- Jev-compatible request
- No
- Runs on CPU
- Yes
- License
- —
- Hugging Face
- togethercomputer/Tev1-0.8B-experimental
Benchmarks
- Jev Decision IndexECE 0.126
- 12.0
Jev Decision Index: public 13.1, ECE 0.126, Brier 0.607. Lower ECE means its probabilities can be taken at face value.
Speed & latency
Compare Tev1-0.8B-experimental with…
FAQ
How much does Tev1-0.8B-experimental cost?
Tev1-0.8B-experimental has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can Tev1-0.8B-experimental answer?
Tev1-0.8B-experimental answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is Tev1-0.8B-experimental well calibrated?
On the Jev Decision Index its expected calibration error (ECE) is 0.126; below about 0.05, a stated 80% confidence is right roughly 80% of the time.
Is Tev1-0.8B-experimental open weight, and can it run on a CPU?
Yes, Tev1-0.8B-experimental has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Enterprise Decision Arena, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.