AionLabs: Aion 3.5 Mini vs Sakana: Fugu Max

Neither wins outright: AionLabs: Aion 3.5 Mini is the pick when cost matters at scale, Sakana: Fugu Max when you need to fit long inputs in one request.

Key numbers

SpecAionLabs: Aion 3.5 MiniSakana: Fugu Max
ProviderAion LabsSakana
Input price (per 1M tokens)$0.70$2.00
Output price (per 1M tokens)$1.40$6.00
Blended price (3:1 input/output)$0.87$3.00
Cheaper than … of all models we track42%20%
Context window262K tokens (~393 pages)1M tokens (~1,500 pages)
Larger context than … of all models47%68%
Max output per response33K tokens (~24,600 words)128K tokens (~96,000 words)
Input typestexttext, image, file
Output typestexttext
Free variantNoNo
Listed since2026-09-232026-09-11
Advertisement

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 MiniSakana: Fugu MaxDifference
Customer-support chatbot
50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens)
$80.50$270AionLabs: Aion 3.5 Mini saves $190
RAG search over documents
20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens)
$98.00$300AionLabs: Aion 3.5 Mini saves $202
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)
$101$312AionLabs: Aion 3.5 Mini saves $211
Batch summarisation
10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens)
$64.40$196AionLabs: Aion 3.5 Mini saves $132
Long-document analysis
500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens)
$36.40$106AionLabs: Aion 3.5 Mini saves $69.60

Capabilities side by side

CapabilityAionLabs: Aion 3.5 MiniSakana: Fugu MaxWhat it lets you do
Tool / function calling✓ Yes✓ Yescall your APIs and run agent loops
Structured output (JSON schema)✓ Yes✓ Yesreturn JSON that validates against your schema
Reasoning / thinking mode✓ Yes✓ Yesspend extra tokens thinking before answering hard problems
Image input—✓ Yesread screenshots, charts and scanned pages
Audio input——take speech or audio directly
File / PDF input—✓ Yesaccept documents without your own parsing step
Image output——generate images, not just text
Built-in web search—✓ Yesanswer 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.

Price history

Which should you choose?

Choose AionLabs: Aion 3.5 Mini if…

  • cost matters at scale — it is 71% cheaper on a typical 3:1 input/output mix ($80.50 vs $270 a month for 50,000 support chats)

Choose Sakana: Fugu Max if…

  • you need to fit long inputs in one request — 1M tokens is roughly 1,500 pages, against 393
  • you need image input — to read screenshots, charts and scanned pages; AionLabs: Aion 3.5 Mini does not advertise it
  • you need file / PDF input — to accept documents without your own parsing step; AionLabs: Aion 3.5 Mini does not advertise it
  • you need built-in web search — to answer from live web results; AionLabs: Aion 3.5 Mini does not advertise it
  • you generate long outputs in one go — up to 128K tokens (about 96,000 words) per response

Frequently asked questions

Is AionLabs: Aion 3.5 Mini better than Sakana: Fugu Max?

Neither wins outright: AionLabs: Aion 3.5 Mini is the pick when cost matters at scale, Sakana: Fugu Max when you need to fit long inputs in one request. In short: AionLabs: Aion 3.5 Mini when cost matters at scale; Sakana: Fugu Max when you need to fit long inputs in one request, you need image input, you need file / PDF input, you need built-in web search, you generate long outputs in one go.

Which is cheaper, AionLabs: Aion 3.5 Mini or Sakana: Fugu Max?

AionLabs: Aion 3.5 Mini is cheaper: $0.87 vs $3.00 per 1M tokens at a typical 3:1 input/output mix, 71% less. For 50,000 support conversations a month that is $80.50 against $270.

How much do AionLabs: Aion 3.5 Mini and Sakana: Fugu Max cost per million tokens?

AionLabs: Aion 3.5 Mini costs $0.70 per 1M input tokens and $1.40 per 1M output tokens; Sakana: Fugu Max costs $2.00 input and $6.00 output. Output tokens are billed separately, so long answers shift the gap.

Which has the bigger context window, AionLabs: Aion 3.5 Mini or Sakana: Fugu Max?

Sakana: Fugu Max: 1M tokens, about 1,500 pages, against 262K (about 393 pages) for AionLabs: Aion 3.5 Mini.

Do AionLabs: Aion 3.5 Mini and Sakana: Fugu Max support function calling and JSON output?

Tool calling — AionLabs: Aion 3.5 Mini: yes, Sakana: Fugu Max: yes. JSON-schema structured output — AionLabs: Aion 3.5 Mini: yes, Sakana: Fugu Max: yes.

Can AionLabs: Aion 3.5 Mini or Sakana: Fugu Max read images?

Only Sakana: Fugu Max accepts image input; AionLabs: Aion 3.5 Mini is text-only for input.

Is AionLabs: Aion 3.5 Mini or Sakana: Fugu Max 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 Mini and Sakana: Fugu Max?

AionLabs: Aion 3.5 Mini can write up to 33K tokens (about 24,600 words) per response; Sakana: Fugu Max up to 128K (about 96,000 words).

When were AionLabs: Aion 3.5 Mini and Sakana: Fugu Max released?

AionLabs: Aion 3.5 Mini was listed on 2026-09-23; Sakana: Fugu Max on 2026-09-11.

About the two models

Sakana

Sakana: Fugu Max

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

Full Sakana: Fugu Max specs →

Compare AionLabs: Aion 3.5 Mini with other models

Compare Sakana: Fugu Max with other models

Advertisement