Beam 1.0 (Reasoning)

by Reflection AI

Beam 1.0 (Reasoning) is a reasoning model from Reflection AI, released on October 16, 2026. It has a 1M-token context window and can generate up to 131K output tokens. API pricing is $0.4 per 1M input tokens and $1.2 per 1M output tokens. It ranks #44 of 247 models by Intelligence Score with a score of 44.2.

Beam 1.0 is Reflection AI's first open-weight model: a sparse Mixture-of-Experts reasoning model with 501.3B total parameters and 23.4B active per token (52 layers: 3 dense + 49 MoE; 256 experts; gated GQA with sliding-window attention; 152K vocabulary), pretrained on 23.8T tokens and post-trained with large-scale asynchronous RL. It targets coding, long-horizon agentic work, and tool use, with a 1M-token context window, up to 128K output tokens on the Reflection API, text-only input/output, and mandatory reasoning with low/medium/high/xhigh/max effort levels. Released under Apache 2.0 in BF16, FP8, and NVFP4 with a DFlash speculative-decoding drafter; available on Hugging Face, the Reflection API (Beam-1.0-501B-A23B), OpenRouter, and other partners.

Key specs

ProviderReflection AI
Release date2026-10-16
Licenseopen source
Context window1M tokens
Max output131K tokens
Input price$0.4 / 1M tokens
Output price$1.2 / 1M tokens
Intelligence Score44.2
Coding index33.8

Quick answers

What is the context window of Beam 1.0 (Reasoning)?

Beam 1.0 (Reasoning) has a context window of 1M tokens, with a maximum output of 131K tokens per response.

How much does Beam 1.0 (Reasoning) cost?

Beam 1.0 (Reasoning) costs $0.4 per 1M input tokens and $1.2 per 1M output tokens through the API.

Is Beam 1.0 (Reasoning) open source?

Yes. Beam 1.0 (Reasoning) is an open model released under the open source license.

When was Beam 1.0 (Reasoning) released?

Reflection AI released Beam 1.0 (Reasoning) on October 16, 2026.

How does Beam 1.0 (Reasoning) compare to Claude Opus 5.5 (Reasoning)?

Beam 1.0 (Reasoning) scores 44.2 on the Intelligence Score versus 59.9 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.4 vs $4 per 1M tokens.

Compare on the AI leaderboard · All AI models