Reflection lists 1 models and Scaledown 2. Scaledown is cheaper on a typical model ($0.03 per 1M tokens median). Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
| Reflection | Scaledown | |
|---|---|---|
| Models listed | 1 | 2 |
| Models with published pricing | 1 | 2 |
| Typical price (median, 3:1 blend per 1M) | $1.50 | $0.03 |
| Cheapest paid model | Reflection: Beam 1.0 501B A23B ($1.50) | ScaleDown: Extract ($0.03) |
| Longest context | Reflection: Beam 1.0 501B A23B (1.0M) | ScaleDown: Extract (1M) |
| Free models | 0 | 0 |
| Newest model | Reflection: Beam 1.0 501B A23B (2026-10-16) | ScaleDown: Extract (2026-10-13) |
| Price changes in the last 90 days | 0 | 0 |
For each workload: the cheapest model from each provider that can actually do it (fits the context window; tool calling required for the agent), and its monthly cost at list price.
| Workload (per month) | Reflection | Scaledown |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $135 with Reflection: Beam 1.0 501B A23B | $3.00 with ScaleDown: Extract |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $150 with Reflection: Beam 1.0 501B A23B | $4.80 with ScaleDown: Extract |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | $156 with Reflection: Beam 1.0 501B A23B | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $98.00 with Reflection: Beam 1.0 501B A23B | $3.20 with ScaleDown: Extract |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $53.00 with Reflection: Beam 1.0 501B A23B | $2.00 with ScaleDown: Extract |
| You need | Reflection | Scaledown |
|---|---|---|
| Any model | Reflection: Beam 1.0 501B A23B ($1.50) | ScaleDown: Extract ($0.03) |
| With tool calling | Reflection: Beam 1.0 501B A23B ($1.50) | none listed |
| With image input | none listed | ScaleDown: Extract ($0.03) |
| With reasoning mode | Reflection: Beam 1.0 501B A23B ($1.50) | none listed |
| 128K+ context | Reflection: Beam 1.0 501B A23B ($1.50) | ScaleDown: Extract ($0.03) |
| 1M+ context | Reflection: Beam 1.0 501B A23B ($1.50) | ScaleDown: Extract ($0.03) |
| Model type | Reflection | Scaledown |
|---|---|---|
| text+image+file->text | 0 | 2 |
| text->text | 1 | 0 |
| Price per 1M (3:1 blend) | Reflection | Scaledown |
|---|---|---|
| Free | 0 | 0 |
| Under $0.50 | 0 | 2 |
| $0.50 – $3 | 1 | 0 |
| $3 – $10 | 0 | 0 |
| $10 and up | 0 | 0 |
Scaledown is cheaper on a typical model: a median of $0.03 per 1M tokens (3:1 input/output) against $1.50 for Reflection. The cheapest paid models are Reflection: Beam 1.0 501B A23B at $1.50 and ScaleDown: Extract at $0.03.
It depends on the job: Scaledown offers the broader line-up (1 models vs 2), Scaledown the lower typical price, Reflection the longest context (1.0M tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Scaledown: Reflection lists 1 models and Scaledown lists 2.
Reflection: Reflection's longest is Reflection: Beam 1.0 501B A23B at 1.0M tokens; Scaledown's is ScaleDown: Extract at 1M.
Neither lists a free model; both are pay-per-token.
Reflection: 0 of 1 models accept images. Scaledown: 2 of 2.