Prism Ml 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.
| Prism Ml | Scaledown | |
|---|---|---|
| Models listed | 1 | 2 |
| Models with published pricing | 1 | 2 |
| Typical price (median, 3:1 blend per 1M) | $0.18 | $0.03 |
| Cheapest paid model | PrismML: Ternary Bonsai 2 27B ($0.18) | ScaleDown: Extract ($0.03) |
| Longest context | PrismML: Ternary Bonsai 2 27B (262K) | ScaleDown: Extract (1M) |
| Free models | 0 | 0 |
| Newest model | PrismML: Ternary Bonsai 2 27B (2026-09-18) | 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) | Prism Ml | Scaledown |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $15.63 with PrismML: Ternary Bonsai 2 27B | $3.00 with ScaleDown: Extract |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $14.00 with PrismML: Ternary Bonsai 2 27B | $4.80 with ScaleDown: Extract |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | $15.00 with PrismML: Ternary Bonsai 2 27B | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $9.00 with PrismML: Ternary Bonsai 2 27B | $3.20 with ScaleDown: Extract |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $4.25 with PrismML: Ternary Bonsai 2 27B | $2.00 with ScaleDown: Extract |
| You need | Prism Ml | Scaledown |
|---|---|---|
| Any model | PrismML: Ternary Bonsai 2 27B ($0.18) | ScaleDown: Extract ($0.03) |
| With tool calling | PrismML: Ternary Bonsai 2 27B ($0.18) | none listed |
| With image input | PrismML: Ternary Bonsai 2 27B ($0.18) | ScaleDown: Extract ($0.03) |
| With reasoning mode | PrismML: Ternary Bonsai 2 27B ($0.18) | none listed |
| 128K+ context | PrismML: Ternary Bonsai 2 27B ($0.18) | ScaleDown: Extract ($0.03) |
| 1M+ context | none listed | ScaleDown: Extract ($0.03) |
| Model type | Prism Ml | Scaledown |
|---|---|---|
| text+image+file->text | 0 | 2 |
| text+image->text | 1 | 0 |
| Price per 1M (3:1 blend) | Prism Ml | Scaledown |
|---|---|---|
| Free | 0 | 0 |
| Under $0.50 | 1 | 2 |
| $0.50 – $3 | 0 | 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 $0.18 for Prism Ml. The cheapest paid models are PrismML: Ternary Bonsai 2 27B at $0.18 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, Scaledown the longest context (1M tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Scaledown: Prism Ml lists 1 models and Scaledown lists 2.
Scaledown: Prism Ml's longest is PrismML: Ternary Bonsai 2 27B at 262K tokens; Scaledown's is ScaleDown: Extract at 1M.
Neither lists a free model; both are pay-per-token.
Prism Ml: 1 of 1 models accept images. Scaledown: 2 of 2.