ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Apertus 1.5 70B vs Sakana Namazu vs Step 3.5 Flash 2603

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

Price in rating: Excluded · Include price

  1. Swiss AI

    Apertus 1.5 70B

    Released Jul 24, 2026

    59/100
    • ECI—
    • Price$1.16 / $3.94
    • Context262K
  2. Sakana AI

    Sakana Namazu

    Released Aug 3, 2026

    65/100
    • ECI—
    • Price$0.95 / $4.00
    • Context262K
  3. StepFun

    Step 3.5 Flash 2603

    Released Apr 2, 2026

    44/100
    • ECI—
    • Price$0.10 / $0.30
    • Context256K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Sakana Namazu 65/100, Apertus 1.5 70B 59/100, Step 3.5 Flash 2603 44/100) 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 priceStep 3.5 Flash 2603Step 3.5 Flash 2603 $0.15 · Sakana Namazu $1.71 · Apertus 1.5 70B $1.85 per 1M tokens (3:1 blend)
  • Longest contextApertus 1.5 70B and Sakana NamazuApertus 1.5 70B 262,144 · Sakana Namazu 262,144 · Step 3.5 Flash 2603 256,000 tokens
  • Widest inputsApertus 1.5 70B and Sakana NamazuApertus 1.5 70B: Text, Images, Audio · Sakana Namazu: Text, Images, PDFs · Step 3.5 Flash 2603: Text
  • Self-hostingApertus 1.5 70B and Step 3.5 Flash 2603Publishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightApertus 1.5 70BSakana NamazuStep 3.5 Flash 2603
Inputs & features60%708045
Context window40%434343
Specs only100%59/10065/10044/100

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 Sakana Namazu vs Step 3.5 Flash 2603 specifications side by side
SpecificationApertus 1.5 70BSwiss AISakana NamazuSakana AIStep 3.5 Flash 2603StepFun
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.16$0.95$0.10 (best)
Output$3.94$4.00$0.30 (best)
Cached input—$0.15$0.02 (best)
Blended (3:1)$1.85$1.71$0.15 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Sakana AI APIOfficial StepFun (Global) API
Limits
Context window262,144 tokens (best)262,144 tokens (best)256,000 tokens
Max output8,192 tokens65,536 tokens256,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoYesNo
AudioYesNoNo
VideoNoNoNo
ReasoningYesYesYeslow · high
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsOpenApache-2.0ProprietaryOpen
API model ID—sakana-namazustep-3.5-flash-2603
API providers17 (best)3
ReleasedJul 24, 2026Aug 3, 2026Apr 2, 2026
Knowledge cutoff——Jan 2025
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
  • Sakana Namazu$17.50
  • Step 3.5 Flash 2603$1.60
04 — Questions

Which should you choose?

Which is better: Apertus 1.5 70B, Sakana Namazu or Step 3.5 Flash 2603?

There is not enough shared capability evidence to name an overall winner. The scores (Sakana Namazu 65/100, Apertus 1.5 70B 59/100, Step 3.5 Flash 2603 44/100) 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, Apertus 1.5 70B, Sakana Namazu or Step 3.5 Flash 2603?

Step 3.5 Flash 2603 is cheaper at $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price). Sakana Namazu costs $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). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Step 3.5 Flash 2603 versus $1.71 for Sakana Namazu (11× as much) and $1.85 for Apertus 1.5 70B (12× 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, Sakana Namazu has not been scored yet and Step 3.5 Flash 2603 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Apertus 1.5 70B, Sakana Namazu and Step 3.5 Flash 2603 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 and Sakana Namazu have the largest context windows (262,144 and 262,144 tokens), against 256,000 for Step 3.5 Flash 2603. Maximum output per response: Apertus 1.5 70B up to 8,192, Sakana Namazu up to 65,536, Step 3.5 Flash 2603 up to 256,000 tokens.

Which can read images, PDFs, audio or video?

Apertus 1.5 70B accepts text, images and audio; Sakana Namazu accepts text, images and PDFs; Step 3.5 Flash 2603 accepts text. Apertus 1.5 70B handles the widest range of inputs.

Are any of these open source?

Apertus 1.5 70B and Step 3.5 Flash 2603 publishes its weights (Apache-2.0) and can be self-hosted; Sakana Namazu is proprietary.

Which is newer?

Sakana Namazu is the newest, released Aug 3, 2026. Apertus 1.5 70B came out Jul 24, 2026; Step 3.5 Flash 2603 came out Apr 2, 2026. Knowledge cutoff: Step 3.5 Flash 2603 Jan 2025.

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.