Beam 1.0 501B A23B pricing
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... Live index: 3 priced offers. Best input $0.250 per million tokens from Openrouter. Best output $1.00 per million tokens from Openrouter.
Pricing across providers
Every row is a seller of Beam 1.0 501B A23B with token pricing we track. The cheapest input in this snapshot is from Openrouter. The bar chart shows the same input and output dollars per million for a quick scan.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.250 | $1.00 | — | — |
TA Together AI | $0.400 | $1.20 | $0.040 | — |
W Wandb | $1.00 | $3.00 | $0.100 | — |
Input vs output · per provider
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Beam 1.0 501B A23B cost scales with traffic.
Provider
0.025000¢ / req
0.050000¢ / req
Model specifications
These fields describe Beam 1.0 501B A23B as we store it (source: Reflection). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Oct 2026
- Primary provider
- Reflection
- Model family
- N/A
Compare Beam 1.0 501B A23B
These links open full side by side pages for Beam 1.0 501B A23B. We picked pairs that people often shop together. 6 ready to open.
Locked
Compare with
Pick a model on both sides.
Popular Beam 1.0 501B A23B comparisons
- Beam 1.0 501B A23B vs GPT-4o
Compare pricing side by side
- Beam 1.0 501B A23B vs Claude Sonnet 4.6
Compare pricing side by side
- Beam 1.0 501B A23B vs Gemini 2.0 Flash
Compare pricing side by side
- Beam 1.0 501B A23B vs Llama 3.1 70B
Compare pricing side by side
- Beam 1.0 501B A23B vs Mistral 7B
Compare pricing side by side
- Beam 1.0 501B A23B vs GLM 4.7
Compare pricing side by side
Frequently asked questions
Read these after the table if you want plain language around Beam 1.0 501B A23B rates. The short model note from our index: 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...
Related models
Models close to Beam 1.0 501B A23B by family, provider, and context window — each with live pricing in our catalog.