DeepSeek lists 24 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.
| DeepSeek | Scaledown | |
|---|---|---|
| Models listed | 24 | 2 |
| Models with published pricing | 23 | 2 |
| Typical price (median, 3:1 blend per 1M) | $0.41 | $0.03 |
| Cheapest paid model | DeepSeek: DeepSeek V4 Flash 0423 ($0.11) | ScaleDown: Extract ($0.03) |
| Longest context | DeepSeek: DeepSeek V4 Flash 0423 (1.0M) | ScaleDown: Extract (1M) |
| Free models | 1 | 0 |
| Newest model | DeepSeek: DeepSeek V4.1 Flash (2026-09-10) | ScaleDown: Extract (2026-10-13) |
| Price changes in the last 90 days | 211 | 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) | DeepSeek | Scaledown |
|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation | $10.47 with DeepSeek: DeepSeek V4 Flash 0423 | $3.00 with ScaleDown: Extract |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages | $8.32 with DeepSeek: DeepSeek V4 Flash 0731 | $4.80 with ScaleDown: Extract |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context | $9.60 with DeepSeek: DeepSeek V4 Flash 0731 | no suitable model |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page | $5.12 with DeepSeek: DeepSeek V4 Flash 0731 | $3.20 with ScaleDown: Extract |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass | $1.44 with DeepSeek: DeepSeek V4 Flash 0731 | $2.00 with ScaleDown: Extract |
| You need | DeepSeek | Scaledown |
|---|---|---|
| Any model | DeepSeek: DeepSeek V4 Flash 0423 ($0.11) | ScaleDown: Extract ($0.03) |
| With tool calling | DeepSeek: DeepSeek V4 Flash 0423 ($0.11) | none listed |
| With image input | DeepSeek: DeepSeek V4 Flash Vision Exp (batch) ($0.17) | ScaleDown: Extract ($0.03) |
| With reasoning mode | DeepSeek: DeepSeek V4 Flash 0423 ($0.11) | none listed |
| 128K+ context | DeepSeek: DeepSeek V4 Flash 0423 ($0.11) | ScaleDown: Extract ($0.03) |
| 1M+ context | DeepSeek: DeepSeek V4 Flash 0423 ($0.11) | ScaleDown: Extract ($0.03) |
| Model type | DeepSeek | Scaledown |
|---|---|---|
| text+image+file->text | 0 | 2 |
| text+image->text | 4 | 0 |
| text->text | 20 | 0 |
| Price per 1M (3:1 blend) | DeepSeek | Scaledown |
|---|---|---|
| Free | 1 | 0 |
| Under $0.50 | 14 | 2 |
| $0.50 – $3 | 8 | 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 $0.41 for DeepSeek. The cheapest paid models are DeepSeek: DeepSeek V4 Flash 0423 at $0.11 and ScaleDown: Extract at $0.03.
It depends on the job: DeepSeek offers the broader line-up (24 models vs 2), Scaledown the lower typical price, DeepSeek the longest context (1.0M tokens). The workload table above shows which wins for chat, RAG, agents, batch jobs and long documents.
DeepSeek: DeepSeek lists 24 models and Scaledown lists 2.
DeepSeek: DeepSeek's longest is DeepSeek: DeepSeek V4 Flash 0423 at 1.0M tokens; Scaledown's is ScaleDown: Extract at 1M.
DeepSeek: 1 free model (e.g. DeepSeek: DeepSeek V4 Flash 0731 (free)). Scaledown: none.
DeepSeek: 4 of 24 models accept images. Scaledown: 2 of 2.