ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemini 4 Hydrogen vs Kimi K2.8 Preview vs Sakana Namazu

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

Price in rating: Excluded · Include price

  1. Google

    Gemini 4 Hydrogen

    Released Nov 12, 2026New

    86/100
    • ECI—
    • Price$1.50 / $7.50
    • Context1.05M
  2. Moonshot AI

    Kimi K2.8 Preview

    Released Sep 11, 2026

    68/100
    • ECI—
    • Price$1.00 / $4.00
    • Context1.05M
  3. Sakana AI

    Sakana Namazu

    Released Aug 3, 2026

    65/100
    • ECI—
    • Price$0.95 / $4.00
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 4 Hydrogen 86/100, Kimi K2.8 Preview 68/100, Sakana Namazu 65/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceSakana NamazuSakana Namazu $1.71 · Kimi K2.8 Preview $1.75 · 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 · Sakana Namazu 262,144 tokens
  • Widest inputsGemini 4 HydrogenGemini 4 Hydrogen: Text, Images, PDFs, Audio, Video · Kimi K2.8 Preview: Text, Images, Video · Sakana Namazu: Text, Images, PDFs
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightGemini 4 HydrogenKimi K2.8 PreviewSakana Namazu
Inputs & features60%1007080
Context window40%656543
Specs only100%86/10068/10065/100

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.

Gemini 4 Hydrogen vs Kimi K2.8 Preview vs Sakana Namazu specifications side by side
SpecificationGemini 4 HydrogenGoogleKimi K2.8 PreviewMoonshot AISakana NamazuSakana AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.50$1.00$0.95 (best)
Output$7.50$4.00 (best)$4.00 (best)
Cached input$0.075 (best)—$0.15
Blended (3:1)$3.00$1.75$1.71 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Google APIMedian of 2 providersOfficial Sakana AI API
Limits
Context window1,048,576 tokens (best)1,048,576 tokens (best)262,144 tokens
Max output65,536 tokens—65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesNoYes
AudioYesNoNo
VideoYesYesNo
ReasoningYeslow · medium · high · xhighYesYes
Tool callingYesYesYes
Structured outputYesNoYes
Availability
WeightsProprietaryProprietaryProprietary
API model IDgemini-4-hydrogen—sakana-namazu
API providers17 (best)27
ReleasedNov 12, 2026Sep 11, 2026Aug 3, 2026
Knowledge cutoffMar 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.

  • Gemini 4 Hydrogen$30.00
  • Kimi K2.8 Preview$18.00
  • Sakana Namazu$17.50
04 — Questions

Which should you choose?

Which is better: Gemini 4 Hydrogen, Kimi K2.8 Preview or Sakana Namazu?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 4 Hydrogen 86/100, Kimi K2.8 Preview 68/100, Sakana Namazu 65/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Gemini 4 Hydrogen, Kimi K2.8 Preview or Sakana Namazu?

Sakana Namazu is cheaper at $0.95 input / $4.00 output per million tokens (official Sakana AI API price). Kimi K2.8 Preview costs $1.00 input / $4.00 output per million tokens (median across 2 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 $1.71 per million tokens for Sakana Namazu versus $1.75 for Kimi K2.8 Preview (1× as much) and $3.00 for Gemini 4 Hydrogen (1.8× as much).

Which scores higher on benchmarks?

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

Which is better for coding?

There are no published SWE-bench Verified results for Gemini 4 Hydrogen, Kimi K2.8 Preview and Sakana Namazu 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 262,144 for Sakana Namazu. Maximum output per response: Gemini 4 Hydrogen up to 65,536, Sakana Namazu up to 65,536 tokens.

Which can read images, PDFs, audio or video?

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

Are any of these open source?

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

Which is newer?

Gemini 4 Hydrogen is the newest, released Nov 12, 2026. Kimi K2.8 Preview came out Sep 11, 2026; Sakana Namazu came out Aug 3, 2026. Knowledge cutoff: Gemini 4 Hydrogen Mar 2026.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.