Choose AionLabs: Aion 3.5 if…
- you need to fit long inputs in one request — 262K tokens is roughly 393 pages, against 192
- you generate long outputs in one go — up to 33K tokens (about 24,600 words) per response
AionLabs: Aion 3.5 vs LiquidAI: LFM2.5-24B-A2B
Neither wins outright: AionLabs: Aion 3.5 is the pick when you need to fit long inputs in one request, LiquidAI: LFM2.5-24B-A2B when cost matters at scale.
Key numbers
| Spec | AionLabs: Aion 3.5 | LiquidAI: LFM2.5-24B-A2B |
|---|---|---|
| Provider | Aion Labs | Liquid |
| Input price (per 1M tokens) | $3.00 | $0.05 |
| Output price (per 1M tokens) | $6.00 | $0.70 |
| Blended price (3:1 input/output) | $3.75 | $0.21 |
| Cheaper than … of all models we track | 17% | 68% |
| Context window | 262K tokens (~393 pages) | 128K tokens (~192 pages) |
| Larger context than … of all models | 48% | 14% |
| Max output per response | 33K tokens (~24,600 words) | 8K tokens (~6,100 words) |
| Input types | text | text |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2026-09-23 | 2026-10-13 |
What it costs for real workloads
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 3.5 | LiquidAI: LFM2.5-24B-A2B | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $345 | $17.75 | LiquidAI: LFM2.5-24B-A2B saves $327 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $420 | $13.00 | LiquidAI: LFM2.5-24B-A2B saves $407 |
| 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) | $432 | $14.40 | LiquidAI: LFM2.5-24B-A2B saves $418 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $276 | $8.20 | LiquidAI: LFM2.5-24B-A2B saves $268 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $156 | $3.20 | LiquidAI: LFM2.5-24B-A2B saves $153 |
Capabilities side by side
| Capability | AionLabs: Aion 3.5 | LiquidAI: LFM2.5-24B-A2B | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | ✓ Yes | spend extra tokens thinking before answering hard problems |
| Image input | — | — | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | 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) | — | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | — | ✓ Yes | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Price history
- AionLabs: Aion 3.5: price unchanged since we started tracking it on 2026-09-24.
- LiquidAI: LFM2.5-24B-A2B: price unchanged since we started tracking it on 2026-10-14.
Which should you choose?
Choose LiquidAI: LFM2.5-24B-A2B if…
- cost matters at scale — it is 94% cheaper on a typical 3:1 input/output mix ($17.75 vs $345 a month for 50,000 support chats)
- you need seed (reproducible sampling) — to repeat a generation for tests and evals; AionLabs: Aion 3.5 does not advertise it
- you need log-probabilities — to read token confidence for classification and scoring; AionLabs: Aion 3.5 does not advertise it
Frequently asked questions
Is AionLabs: Aion 3.5 better than LiquidAI: LFM2.5-24B-A2B?
Neither wins outright: AionLabs: Aion 3.5 is the pick when you need to fit long inputs in one request, LiquidAI: LFM2.5-24B-A2B when cost matters at scale. In short: AionLabs: Aion 3.5 when you need to fit long inputs in one request, you generate long outputs in one go; LiquidAI: LFM2.5-24B-A2B when cost matters at scale, you need seed (reproducible sampling), you need log-probabilities.
Which is cheaper, AionLabs: Aion 3.5 or LiquidAI: LFM2.5-24B-A2B?
LiquidAI: LFM2.5-24B-A2B is cheaper: $0.21 vs $3.75 per 1M tokens at a typical 3:1 input/output mix, 94% less. For 50,000 support conversations a month that is $17.75 against $345.
How much do AionLabs: Aion 3.5 and LiquidAI: LFM2.5-24B-A2B cost per million tokens?
AionLabs: Aion 3.5 costs $3.00 per 1M input tokens and $6.00 per 1M output tokens; LiquidAI: LFM2.5-24B-A2B costs $0.05 input and $0.70 output. Output tokens are billed separately, so long answers shift the gap.
Which has the bigger context window, AionLabs: Aion 3.5 or LiquidAI: LFM2.5-24B-A2B?
AionLabs: Aion 3.5: 262K tokens, about 393 pages, against 128K (about 192 pages) for LiquidAI: LFM2.5-24B-A2B.
Do AionLabs: Aion 3.5 and LiquidAI: LFM2.5-24B-A2B support function calling and JSON output?
Tool calling — AionLabs: Aion 3.5: yes, LiquidAI: LFM2.5-24B-A2B: yes. JSON-schema structured output — AionLabs: Aion 3.5: yes, LiquidAI: LFM2.5-24B-A2B: yes.
Can AionLabs: Aion 3.5 or LiquidAI: LFM2.5-24B-A2B read images?
Neither accepts image input — both are text-in models.
Is AionLabs: Aion 3.5 or LiquidAI: LFM2.5-24B-A2B free to use?
No free variant is listed for either; both are pay-per-token.
What is the maximum output length of AionLabs: Aion 3.5 and LiquidAI: LFM2.5-24B-A2B?
AionLabs: Aion 3.5 can write up to 33K tokens (about 24,600 words) per response; LiquidAI: LFM2.5-24B-A2B up to 8K (about 6,100 words).
When were AionLabs: Aion 3.5 and LiquidAI: LFM2.5-24B-A2B released?
AionLabs: Aion 3.5 was listed on 2026-09-23; LiquidAI: LFM2.5-24B-A2B on 2026-10-13.
About the two models
AionLabs: Aion 3.5
Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...
Full AionLabs: Aion 3.5 specs →LiquidAI: LFM2.5-24B-A2B
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...
Full LiquidAI: LFM2.5-24B-A2B specs →