Neither wins outright: Google: Gemini 2.5 Pro is the pick when you need audio input, Sakana: Fugu Max when cost matters at scale.
| Spec | Google: Gemini 2.5 Pro | Sakana: Fugu Max |
|---|---|---|
| Provider | Sakana | |
| Input price (per 1M tokens) | $1.25 | $2.00 |
| Output price (per 1M tokens) | $10.00 | $6.00 |
| Blended price (3:1 input/output) | $3.44 | $3.00 |
| Cheaper than … of all models we track | 18% | 20% |
| Context window | 1.0M tokens (~1,573 pages) | 1M tokens (~1,500 pages) |
| Larger context than … of all models | 80% | 68% |
| Max output per response | 66K tokens (~49,200 words) | 128K tokens (~96,000 words) |
| Input types | text, image, file, audio, video | text, image, file |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-06-17 | 2026-09-11 |
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) | Google: Gemini 2.5 Pro | Sakana: Fugu Max | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $294 | $270 | Sakana: Fugu Max saves $23.75 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $250 | $300 | Google: Gemini 2.5 Pro saves $50.00 |
| 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) | $270 | $312 | Google: Gemini 2.5 Pro saves $42.00 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $160 | $196 | Google: Gemini 2.5 Pro saves $36.00 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $72.50 | $106 | Google: Gemini 2.5 Pro saves $33.50 |
| Capability | Google: Gemini 2.5 Pro | Sakana: Fugu Max | 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 | ✓ Yes | ✓ Yes | read screenshots, charts and scanned pages |
| Audio input | ✓ Yes | — | take speech or audio directly |
| File / PDF input | ✓ Yes | ✓ Yes | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | ✓ Yes | ✓ Yes | answer from live web results |
| Seed (reproducible sampling) | ✓ Yes | — | 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: Google: Gemini 2.5 Pro is the pick when you need audio input, Sakana: Fugu Max when cost matters at scale. In short: Google: Gemini 2.5 Pro when you need audio input, you need seed (reproducible sampling); Sakana: Fugu Max when cost matters at scale, you generate long outputs in one go, you want the newer model.
Sakana: Fugu Max is cheaper: $3.00 vs $3.44 per 1M tokens at a typical 3:1 input/output mix, 13% less. For 50,000 support conversations a month that is $270 against $294.
Google: Gemini 2.5 Pro costs $1.25 per 1M input tokens and $10.00 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.
Google: Gemini 2.5 Pro: 1.0M tokens, about 1,573 pages, against 1M (about 1,500 pages) for Sakana: Fugu Max.
Tool calling — Google: Gemini 2.5 Pro: yes, Sakana: Fugu Max: yes. JSON-schema structured output — Google: Gemini 2.5 Pro: yes, Sakana: Fugu Max: yes.
Yes, both accept image input.
No free variant is listed for either; both are pay-per-token.
Google: Gemini 2.5 Pro can write up to 66K tokens (about 49,200 words) per response; Sakana: Fugu Max up to 128K (about 96,000 words).
Google: Gemini 2.5 Pro was listed on 2025-06-17; Sakana: Fugu Max on 2026-09-11.
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
Full Google: Gemini 2.5 Pro specs →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 →