- Services
vLLM Semantic Router is the AI lab behind the models on this page. Browse their full catalog ranked by benchmarks, popularity, and hardware fit.
Models tracked
13
Open weight
13
API only
0
Avg score
41.5
Top benchmark
71.6
Decision Index
Total HF downloads
21.0K
Context window
1K – 131K
First release
Sep 2026
Latest release
Oct 2026
Ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | decision | BB58.7 | 2.2B | — | |
| 2 | decision | BB55.3 | 26.1B | — |
The strongest model from this provider in each modality. Click a card to open the model page.
How this provider’s catalog splits across text, image, video, audio, embedding, and decision models.
When each model shipped, newest first.
Oct 26
Oct 3
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | decision | BB58.7 | 2.2B | — | |
| 2 | decision | BB55.3 | 26.1B |
vLLM Semantic Router ships 13 models that we track. Of those, 13 are open weight and 0 are accessed through their API.
It depends on the model. See the open-weight section above for models you can run locally, and the API-only section for closed models priced per token.
By composite score, d3-nano is currently the top vLLM Semantic Router model in our directory. Composite score blends benchmarks, popularity, efficiency, and versatility.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Open Directory
See every release in a family side by side, with a timeline and a leaderboard. Useful when you have already picked a series and want the right size.
Benchmark data sourced from: Hugging Face, Arena.ai, Artificial Analysis.
| 3 | decision | CC53.7 | 26.1B | Oct 2026 |
| 4 | decision | CC52.4 | 4.2B | Oct 2026 |
| 5 | decision | CC47.6 | 7.9B | Sep 2026 |
| 6 | decision | CC45.1 | 29.4B | Oct 2026 |
| 7 | decision | CC41.1 | 9.7B | Sep 2026 |
| 8 | decision | DD39.4 | — | — |
| 9 | decision | DD38.7 | 4.7B | Sep 2026 |
| 10 | decision | DD35.2 | — | Sep 2026 |
Sep 29
Sep 22
Sep 22
Sep 21
Sep 21
Sep 21
Sep 21
Composite grades across this provider’s catalog. Higher is better, blending benchmarks, popularity, and efficiency.
| — |
| 3 | decision | CC53.7 | 26.1B | Oct 2026 |
| 4 | decision | CC52.4 | 4.2B | Oct 2026 |
| 5 | decision | CC47.6 | 7.9B | Sep 2026 |
| 6 | decision | CC45.1 | 29.4B | Oct 2026 |
| 7 | decision | CC41.1 | 9.7B | Sep 2026 |
| 8 | decision | DD39.4 | — | — |
| 9 | decision | DD38.7 | 4.7B | Sep 2026 |
| 10 | decision | DD35.2 | — | Sep 2026 |
| 11 | decision | DD35.1 | 2.3B | Sep 2026 |
| 12 | decision | DD21.0 | — | Sep 2026 |
| 13 | decision | FF16.2 | — | Sep 2026 |
