Loading…
Other
reflection/beam-1.0-501b-a23bHugging Face ↗
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...
Only tracked on Vercel AI Gateway.
Vercel AI Gateway share of tokens, by day.
Beam 1.0 holds 4.06% today, up from 0.10% at the start of the visible window.
Beam 1.0's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-10-20, Beam 1.0 holds 4.1% of Vercel AI Gateway token share, up 4.06pp over 30 days. Data: Vercel AI Gateway as of 2026-10-20. tidelines.ai
Where to run it
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Beam 1.0 is served by 5 tracked endpoints on OpenRouter. The cheapest output price is $1.00 per million tokens from Nebius, and the most expensive is $1.20 from Together. The largest context window offered is 1049k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| Nebius | $0.25 | $1.00 | 1049k | 100.00% |
| CoreWeave | $0.30 | $1.00 | 1049k | 100.00% |
| DigitalOcean | $0.40 | $1.20 | 1049k | — |
| BaseTen | $0.40 | $1.20 | 1049k | 100.00% |
| Together | $0.40 | $1.20 | 1049k | 100.00% |