Beam 1.0 501B A23B
Summary
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.
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Last verified 17 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Reflection |
|---|---|
| Release date | 16 Oct 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 501B [Hugging Face] |
| Context window | 1M (1,048,576 tokens) [models.dev] |
| Max output | 944K tokens [models.dev] |
| Knowledge cutoff | 30 Jun 2026 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | reflection/Beam-1.0-501B-A23B [Hugging Face] |
Beam 1.0 501B A23B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter reflection/beam-1.0-501b-a23b | $1 | $3 | $0.10 | 1M | OpenRouter, 17 Oct 2026 |
Running Beam 1.0 501B A23B locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 304 GB | 305 GB | 306 GB |
| Q8_0 (8-bit) | 533 GB | 534 GB | 535 GB |
| FP16 / BF16 (16-bit) | 1003 GB | 1004 GB | 1005 GB |
At 4-bit with an 8K conversation, Beam 1.0 501B A23B needs about 305 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware.
Frequently asked questions
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.
How much VRAM does Beam 1.0 501B A23B need?
About 305 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 534 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Change history
- License changed from none to apache-2.0
- Parameter count changed from none to 501B
- Now listed on OpenRouter
- Added to the directory