Reflection
Reflection: 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...
beam-1.0-501b-a23bCatalog preview. Paid requests for this model are not enabled yet.
Pricing
~1%USD. No uRouter markup. Live prices can change.
- Input
- $0.297 / 1,000,000 tokens
- Output
- $0.99 / 1,000,000 tokens
- Cache read
- $0.0396 / 1,000,000 tokens
- Cache write
- $0.297 / 1,000,000 tokens
Model details
- Input
- text
- Output
- text
- Context window
- 1,048,576 tokens
- Maximum output
- 524,288 tokens
- Availability
- Uncapped capacity
- Updated
- 11/8/2026, 2:16:16 AM UTC
Capacity is reserved when your request is accepted.
Price history
Observed best prices · Last 24 hours · UTC
$0.297/ 1,000,000 tokens
Capabilities
chatstreamingtoolsreasoningjson mode
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pListed capabilities describe the model. uRouter execution support is verified separately.