Reflection: Beam 1.0 501B A23B
reflection/beam-1.0-501b-a23b
Beam 1.0 is Reflection's open-weight, text-only mixture-of-experts model with 501B total parameters and 23B active per token. It supports coding, reasoning, and tool-driven agent workflows. Reasoning is always enabled, with configurable effort from minimal to max. Multi-turn applications should preserve prior assistant reasoning_content. The model is released under Apache 2.0.
Model specifications
- Input
- text
- Output
- text
- Context
- 1,048,000 tokens
- Max output
- 131,000 tokens
- Input price
- $1.3 / 1M tokens
- Output price
- $4.3 / 1M tokens
- Released
- 2026-10-17
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
1 available provider · tier input average $1.3 / 1M tokens · tier output average $4.3 / 1M tokens
Baseten
Tier: Standard · Region: US · Quantization: fp4
Pricing
- Input
- $1.3 / 1M tokens
- Output
- $4.3 / 1M tokens
- Cache read
- $0.13 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- Yes
- Data retention
- Zero retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Status · Support
Frequently asked questions
- What is Reflection: Beam 1.0 501B A23B?
- Beam 1.0 is Reflection's open-weight, text-only mixture-of-experts model with 501B total parameters and 23B active per token. It supports coding, reasoning, and tool-driven agent workflows. Reasoning is always enabled, with configurable effort from minimal to max. Multi-turn applications should preserve prior assistant reasoning_content. The model is released under Apache 2.0.
- How much does Reflection: Beam 1.0 501B A23B cost?
- Input costs start at $1.3 / 1M tokens and output costs start at $4.3 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Reflection: Beam 1.0 501B A23B?
- Reflection: Beam 1.0 501B A23B supports a 1,048,000 token context window and up to 131,000 output tokens.
- What capabilities does Reflection: Beam 1.0 501B A23B support?
- Reflection: Beam 1.0 501B A23B supports Streaming, Function calling, Vision, JSON mode.
- Which providers offer Reflection: Beam 1.0 501B A23B?
- Reflection: Beam 1.0 501B A23B is available from Baseten.
- How do providers handle data privacy for Reflection: Beam 1.0 501B A23B?
- 1 of 1 providers report that customer data is not used for training, and 1 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.