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.
Multi-agent model for routing expert agents across complex analytical tasks
1 provider
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
14 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Reflection: Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | 36.1 | 1.04858M | $0.25 | $1 | 2026-10-05 | |||
| Fugusakana/fugu | Sakana |
21.7 | 1M | — | — | 2026-06-15 | ||
| Sakana: Fugu Ultrasakana/fugu-ultra | Sakana |
20.6 | 1M | $5 | $30 | 2026-06-15 |