Reflection
Beam 1.0 501B A23B
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.
At a glance
- Input / 1M
- $0.25
- Output / 1M
- $1
- Context
- 1.05M
- Max output
- 131K
- Intelligence
- 17.7
- Released
- Oct 2026
Pricing
Beam 1.0 501B A23B API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.25 |
|---|---|
| Output tokensPer 1M tokens | $1 |
| Cached input (read)Per 1M tokens | $0.05 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$1
per 1,000 requests
Coding task
30K in, 4K out
$11.50
per 1,000 requests
Long document summary
150K in, 2K out
$39.50
per 1,000 requests
Benchmarks
Beam 1.0 501B A23B benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
17.7
Coding index
Not available
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 1.05M tokens
- Max output
- 131K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Max, Extra high, High, Medium, Low
- Release date
- October 16, 2026
- Knowledge cutoff
- June 30, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Beam 1.0 501B A23B vs other models
See how Beam 1.0 501B A23B stacks up head to head on price, benchmarks, and features.
VS
Beam 1.0 501B A23B vs DeepSeek V4.1 Flash 1017
Reflection vs DeepSeek
See comparisonVS
Beam 1.0 501B A23B vs GPT-6 Luna
Reflection vs OpenAI
See comparisonVSBeam 1.0 501B A23B vs DeepSeek V4 Pro 0813
Reflection vs DeepSeek
See comparisonVS
Beam 1.0 501B A23B vs Qwen3.8 27B
Reflection vs Qwen
See comparisonVSBeam 1.0 501B A23B vs MiniMax M3
Reflection vs MiniMax
See comparisonVSBeam 1.0 501B A23B vs Kimi K3
Reflection vs Moonshot AI
See comparisonAlternatives
Beam 1.0 501B A23B alternatives
Similar models worth considering, and where each one has the edge.
DeepSeek
DeepSeek V4.1 Flash 1017
OpenAI
GPT-6 Luna
DeepSeek
DeepSeek V4 Pro 0813
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Beam 1.0 501B A23B cost?
Beam 1.0 501B A23B costs $0.25 per 1M input tokens and $1 per 1M output tokens through the API. A typical chat message costs about $1 per 1,000 messages.
What is the context window of Beam 1.0 501B A23B?
Beam 1.0 501B A23B accepts up to 1.05M tokens of input and can write up to 131K tokens in a single response.
What is the best alternative to Beam 1.0 501B A23B?
DeepSeek V4.1 Flash 1017 from DeepSeek is a strong alternative. It offers: 1.7x cheaper output, higher intelligence score, accepts image.
Can I use Beam 1.0 501B A23B alongside other models?
Yes. Shortcut Chat sends one prompt to Beam 1.0 501B A23B and any other models you pick at the same time, so you can compare answers side by side.
Try Beam 1.0 501B A23B next to every other model.
Use Beam 1.0 501B A23B alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.