Neither wins outright: AionLabs: Aion-1.0 is the pick when you need reasoning / thinking mode, ScaleDown: Summarize when cost matters at scale.
| Spec | AionLabs: Aion-1.0 | ScaleDown: Summarize |
|---|---|---|
| Provider | Aion Labs | Scaledown |
| Input price (per 1M tokens) | $4.00 | $0.04 |
| Output price (per 1M tokens) | $8.00 | $0 |
| Blended price (3:1 input/output) | $5.00 | $0.03 |
| Cheaper than … of all models we track | 10% | 89% |
| Context window | 131K tokens (~197 pages) | 1M tokens (~1,500 pages) |
| Larger context than … of all models | 23% | 69% |
| Max output per response | 33K tokens (~24,600 words) | 4K tokens (~3,000 words) |
| Input types | text | text, image, file |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-02-04 | 2026-10-13 |
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | AionLabs: Aion-1.0 | ScaleDown: Summarize | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $460 | $3.00 | ScaleDown: Summarize saves $457 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $560 | $4.80 | ScaleDown: Summarize saves $555 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $576 | $4.80 | ScaleDown: Summarize saves $571 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $368 | $3.20 | ScaleDown: Summarize saves $365 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $208 | $2.00 | ScaleDown: Summarize saves $206 |
| Capability | AionLabs: Aion-1.0 | ScaleDown: Summarize | What it lets you do |
|---|---|---|---|
| Tool / function calling | — | — | call your APIs and run agent loops |
| Structured output (JSON schema) | — | — | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | — | spend extra tokens thinking before answering hard problems |
| Image input | — | ✓ Yes | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | ✓ Yes | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | — | — | repeat a generation for tests and evals |
| Log-probabilities | — | — | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Neither wins outright: AionLabs: Aion-1.0 is the pick when you need reasoning / thinking mode, ScaleDown: Summarize when cost matters at scale. In short: AionLabs: Aion-1.0 when you need reasoning / thinking mode, you generate long outputs in one go; ScaleDown: Summarize when cost matters at scale, you need to fit long inputs in one request, you need image input, you need file / PDF input, you want the newer model.
ScaleDown: Summarize is cheaper: $0.03 vs $5.00 per 1M tokens at a typical 3:1 input/output mix, 99% less. For 50,000 support conversations a month that is $3.00 against $460.
AionLabs: Aion-1.0 costs $4.00 per 1M input tokens and $8.00 per 1M output tokens; ScaleDown: Summarize costs $0.04 input and $0 output. Output tokens are billed separately, so long answers shift the gap.
ScaleDown: Summarize: 1M tokens, about 1,500 pages, against 131K (about 197 pages) for AionLabs: Aion-1.0.
Tool calling — AionLabs: Aion-1.0: not advertised, ScaleDown: Summarize: not advertised. JSON-schema structured output — AionLabs: Aion-1.0: not advertised, ScaleDown: Summarize: not advertised.
Only ScaleDown: Summarize accepts image input; AionLabs: Aion-1.0 is text-only for input.
No free variant is listed for either; both are pay-per-token.
AionLabs: Aion-1.0 can write up to 33K tokens (about 24,600 words) per response; ScaleDown: Summarize up to 4K (about 3,000 words).
AionLabs: Aion-1.0 was listed on 2025-02-04; ScaleDown: Summarize on 2026-10-13.
Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree of Thoughts (ToT) and Mixture of Experts (MoE). It is Aion Lab's most powerful reasoning model.
Full AionLabs: Aion-1.0 specs →Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...
Full ScaleDown: Summarize specs →