ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Kimi K2.8 Preview vs Qwen3.8 2.4T A95B vs Sakana Namazu

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. Moonshot AI

    Kimi K2.8 Preview

    Released Sep 11, 2026

    52/100
    • ECI—
    • Price$1.00 / $4.00
    • Context1.05M
  2. Alibaba (Qwen)

    Qwen3.8 2.4T A95B

    Released Aug 12, 2026

    32/100
    • ECI—
    • Price$2.00 / $6.00
    • Context262K
  3. Sakana AI

    Sakana Namazu

    Released Aug 3, 2026

    51/100
    • 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 (Kimi K2.8 Preview 52/100, Sakana Namazu 51/100, Qwen3.8 2.4T A95B 32/100) 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 priceSakana NamazuSakana Namazu $1.71 · Kimi K2.8 Preview $1.75 · Qwen3.8 2.4T A95B $3.00 per 1M tokens (3:1 blend)
  • Longest contextKimi K2.8 PreviewKimi K2.8 Preview 1,048,576 · Qwen3.8 2.4T A95B 262,144 · Sakana Namazu 262,144 tokens
  • Widest inputsKimi K2.8 Preview and Sakana NamazuKimi K2.8 Preview: Text, Images, Video · Qwen3.8 2.4T A95B: Text · Sakana Namazu: Text, Images, PDFs
  • Self-hostingQwen3.8 2.4T A95BPublishes downloadable weights (qwen3.8-max)
How the score is built
MeasureWeightKimi K2.8 PreviewQwen3.8 2.4T A95BSakana Namazu
Price50%372637
Inputs & features30%703580
Context window20%654343
Specs & price only100%52/10032/10051/100

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.

Kimi K2.8 Preview vs Qwen3.8 2.4T A95B vs Sakana Namazu specifications side by side
SpecificationKimi K2.8 PreviewMoonshot AIQwen3.8 2.4T A95BAlibaba (Qwen)Sakana NamazuSakana AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.00$2.00$0.95 (best)
Output$4.00 (best)$6.00$4.00 (best)
Cached input——$0.15
Blended (3:1)$1.75$3.00$1.71 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 2 providersMedian of 26 providersOfficial Sakana AI API
Limits
Context window1,048,576 tokens (best)262,144 tokens262,144 tokens
Max output—131,072 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoYes
AudioNoNoNo
VideoYesNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryOpenqwen3.8-maxProprietary
API model ID——sakana-namazu
API providers226 (best)7
ReleasedSep 11, 2026Aug 12, 2026Aug 3, 2026
Knowledge cutoff———
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.

  • Kimi K2.8 Preview$18.00
  • Qwen3.8 2.4T A95B$32.00
  • Sakana Namazu$17.50
04 — Questions

Which should you choose?

Which is better: Kimi K2.8 Preview, Qwen3.8 2.4T A95B or Sakana Namazu?

There is not enough shared capability evidence to name an overall winner. The scores (Kimi K2.8 Preview 52/100, Sakana Namazu 51/100, Qwen3.8 2.4T A95B 32/100) 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, Kimi K2.8 Preview, Qwen3.8 2.4T A95B 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); Qwen3.8 2.4T A95B costs $2.00 input / $6.00 output per million tokens (median across 26 API providers). 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 Qwen3.8 2.4T A95B (1.8× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Kimi K2.8 Preview has not been scored yet, Qwen3.8 2.4T A95B 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 Kimi K2.8 Preview, Qwen3.8 2.4T A95B 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?

Kimi K2.8 Preview has the largest context window at 1,048,576 tokens, against 262,144 for Qwen3.8 2.4T A95B and 262,144 for Sakana Namazu. Maximum output per response: Qwen3.8 2.4T A95B up to 131,072, Sakana Namazu up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Kimi K2.8 Preview accepts text, images and video; Qwen3.8 2.4T A95B accepts text; Sakana Namazu accepts text, images and PDFs. Kimi K2.8 Preview handles the widest range of inputs.

Are any of these open source?

Qwen3.8 2.4T A95B publishes its weights (qwen3.8-max) and can be self-hosted; Kimi K2.8 Preview and Sakana Namazu is proprietary.

Which is newer?

Kimi K2.8 Preview is the newest, released Sep 11, 2026. Qwen3.8 2.4T A95B came out Aug 12, 2026; Sakana Namazu came out Aug 3, 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.