AI Model Catalog: 3 Models Compared — Pricing, Context & Benchmarks

Reflection: Beam 1.0 501B A23B T

Reasoning Tools Open weights 36.1

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

reflection/beam-1.0-501b-a23b 2026-10-05 1.04858M context $0.24/M input $0.98/M output

9 providers

Sakana: Fugu T

Reasoning Tools JSON 21.7

Multi-agent model for routing expert agents across complex analytical tasks

sakana/fugu 2026-06-15 1M context Input not listed Output not listed

1 provider

Sakana: Fugu Ultra T

Reasoning Tools 20.6

Quality-first multi-agent model for hard research, analysis, and competitions

sakana/fugu-ultra 2026-06-15 1M context $5/M input $30/M output

14 providers

Filterable model directory
Model	Creator	Score	Inputs	Context	Input	Output	Released
Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b	Reflection	36.1	T	1.04858M	$0.24	$0.98	2026-10-05
Fugusakana/fugu	Sakana	21.7	T	1M	—	—	2026-06-15
Fugu Ultrasakana/fugu-ultra	Sakana	20.6	T	1M	$5	$30	2026-06-15