Is Scaledown better than Stealth?
It depends on the job: Stealth offers the broader line-up (2 models vs 3), Stealth the longest context (1.0M tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Scaledown vs Stealth
Scaledown lists 2 models and Stealth 3. Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
At a glance
| Scaledown | Stealth | |
|---|---|---|
| Models listed | 2 | 3 |
| Models with published pricing | 2 | 3 |
| Typical price (median, 3:1 blend per 1M) | $0.03 | n/a |
| Cheapest paid model | ScaleDown: Extract ($0.03) | n/a |
| Longest context | ScaleDown: Extract (1M) | Ox Alpha (1.0M) |
| Free models | 0 | 3 |
| Newest model | ScaleDown: Extract (2026-10-13) | Space Bunny Alpha (2026-09-23) |
| Price changes in the last 90 days | 0 | 0 |
What each costs for real workloads
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) | Scaledown | Stealth |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $3.00 with ScaleDown: Extract | no suitable model |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $4.80 with ScaleDown: Extract | no suitable model |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | no suitable model | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $3.20 with ScaleDown: Extract | no suitable model |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $2.00 with ScaleDown: Extract | no suitable model |
Cheapest model for each capability
| You need | Scaledown | Stealth |
|---|---|---|
| Any model | ScaleDown: Extract ($0.03) | none listed |
| With tool calling | none listed | none listed |
| With image input | ScaleDown: Extract ($0.03) | none listed |
| With reasoning mode | none listed | none listed |
| 128K+ context | ScaleDown: Extract ($0.03) | none listed |
| 1M+ context | ScaleDown: Extract ($0.03) | none listed |
Line-up by type and price tier
| Model type | Scaledown | Stealth |
|---|---|---|
| text+image+file->text | 2 | 0 |
| text+image+video->text | 0 | 2 |
| text+image->text | 0 | 1 |
| Price per 1M (3:1 blend) | Scaledown | Stealth |
|---|---|---|
| Free | 0 | 3 |
| Under $0.50 | 2 | 0 |
| $0.50 – $3 | 0 | 0 |
| $3 – $10 | 0 | 0 |
| $10 and up | 0 | 0 |
Frequently asked questions
Which has more models, Scaledown or Stealth?
Stealth: Scaledown lists 2 models and Stealth lists 3.
Which provider has the longest context window?
Stealth: Scaledown's longest is ScaleDown: Extract at 1M tokens; Stealth's is Ox Alpha at 1.0M.
Do Scaledown or Stealth offer free models?
Scaledown: none. Stealth: 3 free models (e.g. Ox Alpha).
Which provider has models that can read images?
Scaledown: 2 of 2 models accept images. Stealth: 3 of 3.