ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Apertus 1.5 70B 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. Swiss AI

    Apertus 1.5 70B

    Released Jul 24, 2026

    47/100
    • ECI—
    • Price$1.16 / $3.94
    • Context262K
  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 (Sakana Namazu 51/100, Apertus 1.5 70B 47/100, 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 · Apertus 1.5 70B $1.85 · Qwen3.8 2.4T A95B $3.00 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameApertus 1.5 70B 262,144 · Qwen3.8 2.4T A95B 262,144 · Sakana Namazu 262,144 tokens
  • Widest inputsApertus 1.5 70B and Sakana NamazuApertus 1.5 70B: Text, Images, Audio · Qwen3.8 2.4T A95B: Text · Sakana Namazu: Text, Images, PDFs
  • Self-hostingApertus 1.5 70B and Qwen3.8 2.4T A95BPublishes downloadable weights (Apache-2.0 and qwen3.8-max)
How the score is built
MeasureWeightApertus 1.5 70BQwen3.8 2.4T A95BSakana Namazu
Price50%362637
Inputs & features30%703580
Context window20%434343
Specs & price only100%47/10032/10051/100

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.

Apertus 1.5 70B vs Qwen3.8 2.4T A95B vs Sakana Namazu specifications side by side
SpecificationApertus 1.5 70BSwiss AIQwen3.8 2.4T A95BAlibaba (Qwen)Sakana NamazuSakana AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.16$2.00$0.95 (best)
Output$3.94 (best)$6.00$4.00
Cached input——$0.15
Blended (3:1)$1.85$3.00$1.71 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 26 providersOfficial Sakana AI API
Limits
Context window262,144 tokens262,144 tokens262,144 tokens
Max output8,192 tokens131,072 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoYes
AudioYesNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenApache-2.0Openqwen3.8-maxProprietary
API model ID——sakana-namazu
API providers126 (best)7
ReleasedJul 24, 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.

  • Apertus 1.5 70B$19.48
  • Qwen3.8 2.4T A95B$32.00
  • Sakana Namazu$17.50
04 — Questions

Which should you choose?

Which is better: Apertus 1.5 70B, Qwen3.8 2.4T A95B or Sakana Namazu?

There is not enough shared capability evidence to name an overall winner. The scores (Sakana Namazu 51/100, Apertus 1.5 70B 47/100, 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, Apertus 1.5 70B, 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). Apertus 1.5 70B costs $1.16 input / $3.94 output per million tokens (median across 1 API provider); 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 $1.85 for Apertus 1.5 70B (1.1× 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. Apertus 1.5 70B 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 Apertus 1.5 70B, 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?

Apertus 1.5 70B, Qwen3.8 2.4T A95B and Sakana Namazu share the same 262,144-token context window. Maximum output per response: Apertus 1.5 70B up to 8,192, Qwen3.8 2.4T A95B up to 131,072, Sakana Namazu up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Apertus 1.5 70B accepts text, images and audio; Qwen3.8 2.4T A95B accepts text; Sakana Namazu accepts text, images and PDFs. Apertus 1.5 70B handles the widest range of inputs.

Are any of these open source?

Apertus 1.5 70B and Qwen3.8 2.4T A95B publishes its weights (Apache-2.0 and qwen3.8-max) and can be self-hosted; Sakana Namazu is proprietary.

Which is newer?

Qwen3.8 2.4T A95B is the newest, released Aug 12, 2026. Sakana Namazu came out Aug 3, 2026; Apertus 1.5 70B came out Jul 24, 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.