Beam 1.0 501B A23B
beam-1-0
Reflection's Apache 2.0 open-weight text model with 501.3B total and 23.4B active parameters, built for coding, reasoning and tool use. It supports a shared 1,048,576-token context window, up to 131,072 output tokens, JSON mode and structured output. Reasoning is always enabled with low, medium, high, xhigh and max effort; NanoGPT defaults to max. Knowledge cutoff: June 30, 2026.
Specification
most-agreed values
Price
US dollars per million tokens · most-agreed
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| baseten | $0.40 | $1.20 | $0.04 | — | 1M | 131K | — |
| nano-gpt · reflection | $0.50 | $1.50 | $0.05 | — | 1M | 131K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-10-17 | baseten | Cache read | $0.13 |
| 2026-10-22 | baseten | Cache read | $0.04 |
| 2026-10-17 | nano-gpt · reflection | Cache read | $0.04 |
| 2026-10-18 | nano-gpt · reflection | Cache read | $0.05 |
| 2026-10-17 | baseten | Input | $1.30 |
| 2026-10-22 | baseten | Input | $0.40 |
| 2026-10-17 | nano-gpt · reflection | Input | $0.45 |
| 2026-10-18 | nano-gpt · reflection | Input | $0.50 |
| 2026-10-17 | baseten | Output | $4.30 |
| 2026-10-22 | baseten | Output | $1.20 |
| 2026-10-17 | nano-gpt · reflection | Output | $1.25 |
| 2026-10-18 | nano-gpt · reflection | Output | $1.50 |
Other listings of this model
this page is one of them
The corpus files Beam 1.0 501B A23B under several keys. This page is the beam-1-0 listing. The full record — every host, every price and every benchmark score — is on the main Beam 1.0 501B A23B page.