Reflection: Beam 1.0 501B A23Breflection
Bottom Line
Reflection: Beam 1.0 501B A23B: $0.25/1M input, $1.00/1M output, 1.0M context. 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...
API Pricing (per 1M tokens)
| Input | $0.25 |
| Output | $1.00 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.44 |
Specs & Performance
| Context Length | 1.0M |
| Max Output | 131K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Reflection: Beam 1.0 501B A23B API cost?
Reflection: Beam 1.0 501B A23B costs $0.25/1M input tokens and $1.00/1M output tokens. Blended cost at a 3:1 ratio is about $0.44/1M tokens.
What is the context window of Reflection: Beam 1.0 501B A23B?
Reflection: Beam 1.0 501B A23B supports a 1.0M token context window with up to 131K output tokens.
Is Reflection: Beam 1.0 501B A23B worth it?
Reflection: Beam 1.0 501B A23B has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.