Openrouter lists 6 models and Scaledown 2. Openrouter is cheaper on a typical model ($-1000000.0000 per 1M tokens median). Below: line-up, price tiers, the cheapest model for each capability, and what each costs for five real workloads.
| Openrouter | Scaledown | |
|---|---|---|
| Models listed | 6 | 2 |
| Models with published pricing | 6 | 2 |
| Typical price (median, 3:1 blend per 1M) | $-1000000.0000 | $0.03 |
| Cheapest paid model | Auto Router ($-1000000.0000) | ScaleDown: Extract ($0.03) |
| Longest context | Auto Router (2M) | ScaleDown: Extract (1M) |
| Free models | 1 | 0 |
| Newest model | Auto Router (Beta) (2026-07-17) | 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) | Openrouter | Scaledown |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $-95000000.0000 with Auto Router | $3.00 with ScaleDown: Extract |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $-130000000.0000 with Auto Router | $4.80 with ScaleDown: Extract |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | $-132000000.0000 with Auto Router | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $-86000000.0000 with Auto Router | $3.20 with ScaleDown: Extract |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $-51000000.0000 with Auto Router | $2.00 with ScaleDown: Extract |
| You need | Openrouter | Scaledown |
|---|---|---|
| Any model | Auto Router ($-1000000.0000) | ScaleDown: Extract ($0.03) |
| With tool calling | Auto Router ($-1000000.0000) | none listed |
| With image input | Auto Router ($-1000000.0000) | ScaleDown: Extract ($0.03) |
| With reasoning mode | Auto Router ($-1000000.0000) | none listed |
| 128K+ context | Auto Router ($-1000000.0000) | ScaleDown: Extract ($0.03) |
| 1M+ context | Auto Router ($-1000000.0000) | ScaleDown: Extract ($0.03) |
| Model type | Openrouter | Scaledown |
|---|---|---|
| text+image+file+audio+video->text+image | 2 | 0 |
| text+image+file->text | 0 | 2 |
| text+image->text | 1 | 0 |
| text->text | 3 | 0 |
| Price per 1M (3:1 blend) | Openrouter | Scaledown |
|---|---|---|
| Free | 1 | 0 |
| Under $0.50 | 0 | 2 |
| $0.50 – $3 | 0 | 0 |
| $3 – $10 | 0 | 0 |
| $10 and up | 0 | 0 |
Openrouter is cheaper on a typical model: a median of $-1000000.0000 per 1M tokens (3:1 input/output) against $0.03 for Scaledown. The cheapest paid models are Auto Router at $-1000000.0000 and ScaleDown: Extract at $0.03.
It depends on the job: Openrouter offers the broader line-up (6 models vs 2), Openrouter the lower typical price, Openrouter the longest context (2M tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
Openrouter: Openrouter lists 6 models and Scaledown lists 2.
Openrouter: Openrouter's longest is Auto Router at 2M tokens; Scaledown's is ScaleDown: Extract at 1M.
Openrouter: 1 free model (e.g. Free Models Router). Scaledown: none.
Openrouter: 3 of 6 models accept images. Scaledown: 2 of 2.