ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Fugu Max vs Gemini 4 Hydrogen vs Kimi K2.8 Preview

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Sakana AI

    Fugu Max

    Released Sep 11, 2026

    47/100
    • ECI—
    • Price$2.00 / $6.00
    • Context1M
  2. Google

    Gemini 4 Hydrogen

    Released Nov 12, 2026New

    56/100
    • ECI—
    • Price$1.50 / $7.50
    • Context1.05M
  3. Moonshot AI

    Kimi K2.8 Preview

    Released Sep 11, 2026

    52/100
    • ECI—
    • Price$1.00 / $4.00
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 4 Hydrogen 56/100, Kimi K2.8 Preview 52/100, Fugu Max 47/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceKimi K2.8 PreviewKimi K2.8 Preview $1.75 · Fugu Max $3.00 · Gemini 4 Hydrogen $3.00 per 1M tokens (3:1 blend)
  • Longest contextGemini 4 Hydrogen and Kimi K2.8 PreviewGemini 4 Hydrogen 1,048,576 · Kimi K2.8 Preview 1,048,576 · Fugu Max 1,000,000 tokens
  • Widest inputsGemini 4 HydrogenFugu Max: Text, Images, PDFs · Gemini 4 Hydrogen: Text, Images, PDFs, Audio, Video · Kimi K2.8 Preview: Text, Images, Video
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightFugu MaxGemini 4 HydrogenKimi K2.8 Preview
Price50%262637
Inputs & features30%7010070
Context window20%646565
Specs & price only100%47/10056/10052/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Fugu Max vs Gemini 4 Hydrogen vs Kimi K2.8 Preview specifications side by side
SpecificationFugu MaxSakana AIGemini 4 HydrogenGoogleKimi K2.8 PreviewMoonshot AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$2.00$1.50$1.00 (best)
Output$6.00$7.50$4.00 (best)
Cached input—$0.075—
Blended (3:1)$3.00$3.00$1.75 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 9 providersOfficial Google APIMedian of 2 providers
Limits
Context window1,000,000 tokens1,048,576 tokens (best)1,048,576 tokens (best)
Max output128,000 tokens (best)65,536 tokens—
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesNo
AudioNoYesNo
VideoNoYesYes
ReasoningYesYeslow · medium · high · xhighYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsProprietaryProprietaryProprietary
API model ID—gemini-4-hydrogen—
API providers917 (best)2
ReleasedSep 11, 2026Nov 12, 2026Sep 11, 2026
Knowledge cutoff—Mar 2026—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Fugu Max$32.00
  • Gemini 4 Hydrogen$30.00
  • Kimi K2.8 Preview$18.00
04 — Questions

Which should you choose?

Which is better: Fugu Max, Gemini 4 Hydrogen or Kimi K2.8 Preview?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 4 Hydrogen 56/100, Kimi K2.8 Preview 52/100, Fugu Max 47/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Fugu Max, Gemini 4 Hydrogen or Kimi K2.8 Preview?

Kimi K2.8 Preview is cheaper at $1.00 input / $4.00 output per million tokens (median across 2 API providers). Fugu Max costs $2.00 input / $6.00 output per million tokens (median across 9 API providers); Gemini 4 Hydrogen costs $1.50 input / $7.50 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $1.75 per million tokens for Kimi K2.8 Preview versus $3.00 for Fugu Max (1.7× as much) and $3.00 for Gemini 4 Hydrogen (1.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Fugu Max has not been scored yet, Gemini 4 Hydrogen has not been scored yet and Kimi K2.8 Preview has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Fugu Max, Gemini 4 Hydrogen and Kimi K2.8 Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Gemini 4 Hydrogen and Kimi K2.8 Preview have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for Fugu Max. Maximum output per response: Fugu Max up to 128,000, Gemini 4 Hydrogen up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Fugu Max accepts text, images and PDFs; Gemini 4 Hydrogen accepts text, images, PDFs, audio and video; Kimi K2.8 Preview accepts text, images and video. Gemini 4 Hydrogen handles the widest range of inputs.

Are any of these open source?

No. Fugu Max, Gemini 4 Hydrogen and Kimi K2.8 Preview are proprietary and only available through APIs and apps.

Which is newer?

Gemini 4 Hydrogen is the newest, released Nov 12, 2026. Fugu Max came out Sep 11, 2026; Kimi K2.8 Preview came out Sep 11, 2026. Knowledge cutoff: Gemini 4 Hydrogen Mar 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.