Reflection
Reflection

Beam 1.0 501B A23B pricing & price history

reasoningtoolsreflection/beam-1.0-501b-a23b

Beam 1.0 501B A23B by Reflection costs $0.25 per 1M input tokens and $1.00 per 1M output tokens, with a 1M token context window.

$0.25Input / 1M tokens
$1.00Output / 1M tokens
1MContext window
—Intelligence index

Price history

$0.00$1.72$3.45 2026-10-16today input /1M output /1M
DateInputOutput
2026-10-22$0.30 → $0.25 -17%$1.00 → $1.00
2026-10-20$1.00 → $0.30 -70%$3.00 → $1.00 -67%
2026-10-17$0.25 → $1.00 +300%$1.00 → $3.00 +200%

Cost calculator

Cheaper alternatives to Beam 1.0 501B A23B

ModelInputOutputContextIntel.
Z.ai (Zhipu)
GLM 5.3 Flash
Z.ai (Zhipu)
$0.0149$0.151M27.8compare
$0.075$0.301M28.9compare
$0.12$0.241M—compare
Meta Llama
Llama 4 Scout
Meta Llama
$0.10$0.301.3M—compare
$0.045$0.501M—compare
$0.14$0.281.1M26.7compare
$0.18$0.18164K—compare
$0.10$0.501M36.2compare

About Beam 1.0 501B A23B

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...

FAQ

How much does Beam 1.0 501B A23B cost?

Beam 1.0 501B A23B by Reflection costs $0.25 per 1M input tokens and $1.00 per 1M output tokens, with a 1M token context window. A typical request with 2,000 input and 500 output tokens costs about $0.001.

What is the context window of Beam 1.0 501B A23B?

Beam 1.0 501B A23B supports up to 1,048,576 tokens of context and up to 131,072 output tokens per request.

Has Beam 1.0 501B A23B’s price changed?

Yes. ModelBank recorded 3 price changes; the latest on 2026-10-22.

Is Beam 1.0 501B A23B being deprecated?

No retirement date has been announced for Beam 1.0 501B A23B as of 2026-10-31.

What are cheaper alternatives to Beam 1.0 501B A23B?

Cheaper options include GLM 5.3 Flash ($0.0149/$0.15), MiniMax M3.1 Flash ($0.075/$0.30), DeepSeek V4 Flash 0731 ($0.12/$0.24), Llama 4 Scout ($0.10/$0.30).