Beam 1.0 501B A23B is Reflection's language model with a 1.0M context window and up to 944K output tokens, available from 4 providers, starting at $0.25 / 1M input and $1.00 / 1M output. A large mixture-of-experts reasoning model with 501B total and 23B active parameters, built for coding and agentic workflows.
Specifications
Canonical IDreflection-beam-1-501b-a23b
TypeLanguage
StatusActive
CreatorReflection
Providers
Context Window1.0M tokens
Max Output944K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters501B
HuggingFace Likes172
HuggingFace Downloads (30d)2,097
HuggingFace Downloads (all-time)2,097
Release Date · 18 days ago
Knowledge Cutoff · 4 months ago

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Hugging Face logo
Hugging Face
together_ai:reflection/Beam-1.0-501B-A23B
$0.4$1.20N/A
OpenRouter logo
OpenRouter
reflection/beam-1.0-501b-a23b
$0.25$1.00$0.05
Together AI logo
Together AI
together_ai/reflection/Beam-1.0-501B-A23B
$0.4$1.20$0.04
Weights & Biases logo
Weights & Biases
wandb/reflection/Beam-1.0-501B-A23B
$1.00$3.00$0.1

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Beam 1.0 501B A23B, ranked by cheapest on-demand price. The model needs about 1202 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_ND96is_MI300X_v5Azure8× AMD Instinct MI300X GPU (192GB)1536 GB$48.00/hr
Standard_ND96isr_MI300X_v5Azure8× AMD Instinct MI300X1536 GB$48.00/hr
p6-b200.48xlargeAWS8× B2001432 GB$113.93/hr
2 more instances can run Beam 1.0 501B A23B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Beam 1.0 501B A23B1.0M$0.250$1.00Current
Beam 1—1.0M$0.400$1.20Available
Beam 1.01.0M——Available
Beam 1.0 Free1.0M——Available

Model IDs

accounts/fireworks/models/beam-1p0-501b-a23b
huggingface-llm-beam-1-0-501b-a23b
huggingface-llm-beam-1-0-501b-a23b-fp8
huggingface-llm-beam-1-0-501b-a23b-nvfp4
reflection-beam-1-501b-a23b
reflection/beam-1.0-501b-a23b
together_ai/reflection/Beam-1.0-501B-A23B
wandb/reflection/Beam-1.0-501B-A23B