Beam-1.0-501B-A23B
Hugging Face GitHub Launch Blog Documentation Technical Report (coming) License: Apache 2.0 Authors: Reflection
Params
501.3 B
Context
1,048,576
Downloads 30d
4 K
Likes
245
Download history
tracking started — chart appears after 7 days of snapshots (6 recorded)4 K downloads in the last 30 days
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 1,002.7 GB | 1,178.6 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 1024K ctx | 1,002.7 GB | 10,727.8 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/beam-1-0-501b-a23b
{
"hf_id": "reflection/Beam-1.0-501B-A23B",
"params_b": 501.27,
"context_length": 1048576,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 4432,
"vram_estimates": [
{ "quant": "bf16", "gb": 1178.6 }
],
"updated_at": "2026-10-19T06:01:58Z"
}
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-10-24$0.25
input / 1M
$1.00
output / 1M
$0.05
cached input / 1M
$1.25
1M in + 1M out
- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Providers
- 6
- Cheapest provider
- Io Net · $0.24 / $0.98
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / — / —
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✗ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- BeamForCausalLM
- Parameters
- 501.3 B
- Tensor type
- BF16
- Context length
- 1,048,576
- Vocabulary
- 151,936
- Layers / heads
- 52 / 48
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-07
- Training datasets
- undisclosed
- Added to our catalog
- 2026-10-20
Compare with any text-generation model