Beam 1.0 501B A23B
by Reflection · reflection/beam-1.0-501b-a23b · #164 cheapest of 452 paid models
Prices updated Nov 17, 2026, 5:30 PM UTC · refreshed nightly
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.30
per 1M tokens
Output
$1.00
per 1M tokens
Blended (3:1)
$0.475
3 input : 1 output
Cache read
$0.04
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Beam 1.0 501B A23B with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.475 | $0.0316 | — |
| 50% | $0.378 | $0.0186 | −41% |
| 90% | $0.299 | $0.0082 | −74% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00045 | $0.45 |
| Document summary | 8,000 | 1,000 | $0.0034 | $3.40 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.011 | $11.00 |
| Long-context analysis | 150,000 | 5,000 | $0.05 | $50.00 |
Performance
Intelligence Index
17.7
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,240 |
| UI components | 1,259 |
| 3D | 1,130 |
| Game dev | 1,189 |
| Code categories | 1,224 |
Specs
Context window
1.05M
tokens
Max output
944K
tokens
Input modalities
text
Tokenizer
Other