togethercomputer
Together: Tev1 4B Experimental
togethercomputer/tev1-4b-experimental
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
togethercomputer/tev1-4b-experimental is an experimental 4B decision model from Together AI. The model documentation describes it as a supervised fine-tune of Qwen3.5-4B that receives a state, a question, and 2–24 labeled choices, then returns one option letter for application code to interpret. It is Jev-inspired but remains a conventional next-token model. OpenRouter lists text input and decision output. Author-reported development results were positive, but they are not independent and require workload validation.[1][2]
Strengths
Limitations
- Development results are author-reported, informed training, lack an untuned-Qwen baseline, and include synthetic policy-transfer data.[2]
- It can be wrong, may produce prose in general chat, and should not be the sole authority for high-impact decisions.[2]
- Prompt-injection, multilingual, calibration, out-of-distribution, and local-deployment behavior need validation; the fine-tuned-weight license is still being finalized.[2]
Where to use it
- A candidate for eligibility, policy, or routing checks that can be represented as a fixed set of labeled options.[2]
- Potentially useful when an application needs constrained selection and maps the returned letter itself.[2]
- Worth evaluating as a decision layer for classification-style workflows after validating domain data, outputs, and fallback handling.[2]
Sources
- [1] OpenRouter catalog · Together: Tev1 4B ExperimentalSources checked: Nov 13, 2026
- [2] Model documentation · Together: Tev1 4B ExperimentalSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Tev1 4B Experimental is an experimental decision model from Together AI, a supervised fine-tune of Qwen3.5-4B trained to choose one option from a structured state, question, and list of 2-24...
Specifications
- Model ID
- togethercomputer/tev1-4b-experimental
- Canonical ID
- togethercomputer/tev1-4b-experimental-20260923
- Creator
- togethercomputer
- Added to OpenRouter
- 30.09.2026
- Context length
- 32,768
- Modality
- text->decisions
- Input modalities
- text
- Output modalities
- decisions
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Together | 32,768 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.