Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
9 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
23 providers
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
13 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Reflection: Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | 78.2 | 1.04858M | $0.25 | $1 | 2026-10-05 | |||
| Tencent: Hy3tencent/hy3 | Tencent |
73.4 | 262.144K | $0.083 | $0.33 | 2026-07-06 | ||
| NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | NVIDIA |
52.0 | 262.144K | $0.07 | $0.2 | 2026-08-11 |