Reflection
Beam 1.0 501B A23B
Released 2026-10-16 · Knowledge up to 2026-06-30
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...
You send / 1M
$0.250
tokens in
It replies / 1M
$1.00
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0008
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| CoreWeave · fp4 | $0.300 | $1.00 | 100% | Read |
| Nebius · fp4 | $0.250 | $1.00 | 100% | Read |
| DigitalOcean | $0.400 | $1.20 | 100% | Read |
| BaseTen · fp4 | $0.400 | $1.20 | 100% | Read |
| Together | $0.400 | $1.20 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 131K tokens
- Repeated text is billed at $0.050 per 1M (prompt caching)
Similar models
- DeepSeek V3.1 TerminusDeepSeek · $0.270 in / $1.00 out per 1M
- MiniMax M2MiniMax · $0.255 in / $1.02 out per 1M
- DeepSeek V3.1DeepSeek · $0.250 in / $0.950 out per 1M
- GLM 4.5 AirZ.ai · $0.130 in / $0.850 out per 1M
- LongCat 2.0Meituan · $0.300 in / $1.20 out per 1M
- MiniMax M2.7MiniMax · $0.300 in / $1.20 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Zero Data Retention Long-Context AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Reasoning AI Models