Reflection: Beam 1.0 501B A23B
by ReflectionReflection: Beam 1.0 501B A23B is a large language model from Reflection. It costs $0.250 per million input tokens and $1.00 per million output tokens. Its context window is 1.0M tokens.
- Input / 1M tokens
- $0.250
- Output / 1M tokens
- $1.00
- Cached input / 1M
- $0.050
- Context window
- 1.0M
On repeated prefixes
tokens
Who serves it cheapest
5 hosts serve Beam 1.0 501B A23B. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| NebiusCheapestfp4 | $0.250 | $1.00 | 1.0M | - | 98.1% |
| CoreWeavefp4 | $0.300 | $1.00 | 1.0M | - | 99.8% |
| DigitalOcean | $0.400 | $1.20 | 1.0M | - | 100.0% |
| BaseTenfp4 | $0.400 | $1.20 | 1.0M | - | 100.0% |
| Together | $0.400 | $1.20 | 1.0M | - | 100.0% |
The spread between Nebius and Together is 1.4× for identical weights. Quantization and context limits differ, so check both columns before switching.
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...
Specifications
| Model ID | reflection/beam-1.0-501b-a23b |
|---|---|
| Provider | Reflection |
| Context window | 1.0M tokens |
| Max output | 131K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2026-06-30 |
| Open weights | Yes - reflection/Beam-1.0-501B-A23B |
| Released | October 16, 2026 |
Cheaper alternatives
Models that cost less than Beam 1.0 501B A23B while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Reflection: Beam 1.0 501B A23B cost?
$0.250 per million input tokens and $1.00 per million output tokens. Cached input reads cost $0.050 per million tokens.
What is the context window of Reflection: Beam 1.0 501B A23B?
1.0M tokens, with up to 131K tokens of output per request.
Which provider serves Reflection: Beam 1.0 501B A23B cheapest?
Nebius at $0.250 per million input tokens - 1.4× cheaper than Together, the most expensive of the 5 hosts serving it.