# Beam 1.0 501B A23B

> Beam 1.0 501B A23B is an open-weight language model from Reflection, released on 16 Oct 2026. It accepts text and generates text, with a 1M-token context window and up to 944K output tokens per response. As of 17 Oct 2026, the lowest listed API price is $1 per million input tokens and $3 per million output tokens (OpenRouter), across 1 provider we track.

Source page: https://www.aimodel.directory/models/beam-1-0-501b-a23b
Last verified: 17 Oct 2026

## Specifications

- **Developer:** Reflection
- **Release date:** 16 Oct 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/reflection/Beam-1.0-501B-A23B)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/reflection/Beam-1.0-501B-A23B)
- **Parameters:** 501B (source: Hugging Face, https://huggingface.co/reflection/Beam-1.0-501B-A23B)
- **Context window:** 1M (1,048,576 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Max output:** 944K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Knowledge cutoff:** 30 Jun 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openrouter/models/reflection/beam-1.0-501b-a23b.toml)
- **Hugging Face:** reflection/Beam-1.0-501B-A23B (source: Hugging Face, https://huggingface.co/reflection/Beam-1.0-501B-A23B)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $1 | $3 | $0.10 | 1M |

## FAQ

### What is the context window of Beam 1.0 501B A23B?

Beam 1.0 501B A23B has a context window of 1,048,576 tokens (1M) and can generate up to 943,718 tokens in a single response, according to models.dev.

### How much does the Beam 1.0 501B A23B API cost?

Beam 1.0 501B A23B is listed from $1 per million input tokens and $3 per million output tokens (OpenRouter). Prices last verified 17 Oct 2026.

### Is Beam 1.0 501B A23B open source?

Beam 1.0 501B A23B is an open-weight model: its weights are published on Hugging Face as reflection/Beam-1.0-501B-A23B under the apache-2.0 license. Check the license terms before commercial use.

### When was Beam 1.0 501B A23B released?

Reflection released Beam 1.0 501B A23B on 16 Oct 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Beam 1.0 501B A23B", https://www.aimodel.directory/models/beam-1-0-501b-a23b