ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Apertus v1.5 8B vs Ornith 1.5 122B vs Restyler 1

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 v1.5 8B

    Released Oct 15, 2026New

    80/100
    • ECI—
    • Price$0.024 / $0.119
    • Context262K
  2. DeepReinforce

    Ornith 1.5 122B

    Released Oct 20, 2026New

    63/100
    • ECI—
    • Price$0.16 / $0.64
    • Context262K
  3. Meragpt

    Restyler 1

    Released Sep 2, 2026

    50/100
    • ECI—
    • Price$0.04 / $0.16
    • Context4K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Apertus v1.5 8B 80/100, Ornith 1.5 122B 63/100, Restyler 1 50/100) 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 priceApertus v1.5 8BApertus v1.5 8B $0.048 · Restyler 1 $0.07 · Ornith 1.5 122B $0.28 per 1M tokens (3:1 blend)
  • Longest contextApertus v1.5 8B and Ornith 1.5 122BApertus v1.5 8B 262,144 · Ornith 1.5 122B 262,144 · Restyler 1 4,096 tokens
  • Widest inputsApertus v1.5 8BApertus v1.5 8B: Text, Images, Audio · Ornith 1.5 122B: Text, Images · Restyler 1: Text
  • Self-hostingApertus v1.5 8B and Ornith 1.5 122BPublishes downloadable weights (Apache-2.0 and MIT)
How the score is built
MeasureWeightApertus v1.5 8BOrnith 1.5 122BRestyler 1
Price50%10073100
Inputs & features30%70600
Context window20%43430
Specs & price only100%80/10063/10050/100

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 v1.5 8B vs Ornith 1.5 122B vs Restyler 1 specifications side by side
SpecificationApertus v1.5 8BSwiss AIOrnith 1.5 122BDeepReinforceRestyler 1Meragpt
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.024 (best)$0.16$0.04
Output$0.119 (best)$0.64$0.16
Cached input———
Blended (3:1)$0.048 (best)$0.28$0.07
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 1 providersMedian of 1 providers
Limits
Context window262,144 tokens (best)262,144 tokens (best)4,096 tokens
Max output—32,768 tokens (best)2,048 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoNoNo
AudioYesNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenApache-2.0OpenMITProprietary
API model ID———
API providers111
ReleasedOct 15, 2026Oct 20, 2026Sep 2, 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 v1.5 8B$0.476
  • Ornith 1.5 122B$2.88
  • Restyler 1$0.72
04 — Questions

Which should you choose?

Which is better: Apertus v1.5 8B, Ornith 1.5 122B or Restyler 1?

There is not enough shared capability evidence to name an overall winner. The scores (Apertus v1.5 8B 80/100, Ornith 1.5 122B 63/100, Restyler 1 50/100) 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 v1.5 8B, Ornith 1.5 122B or Restyler 1?

Apertus v1.5 8B is cheaper at $0.024 input / $0.119 output per million tokens (median across 1 API provider). Restyler 1 costs $0.04 input / $0.16 output per million tokens (median across 1 API provider); Ornith 1.5 122B costs $0.16 input / $0.64 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.048 per million tokens for Apertus v1.5 8B versus $0.07 for Restyler 1 (1.5× as much) and $0.28 for Ornith 1.5 122B (5.9× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Apertus v1.5 8B has not been scored yet, Ornith 1.5 122B has not been scored yet and Restyler 1 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Apertus v1.5 8B, Ornith 1.5 122B and Restyler 1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Restyler 1 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Apertus v1.5 8B and Ornith 1.5 122B have the largest context windows (262,144 and 262,144 tokens), against 4,096 for Restyler 1. Maximum output per response: Ornith 1.5 122B up to 32,768, Restyler 1 up to 2,048 tokens.

Which can read images, PDFs, audio or video?

Apertus v1.5 8B accepts text, images and audio; Ornith 1.5 122B accepts text and images; Restyler 1 accepts text. Apertus v1.5 8B handles the widest range of inputs.

Are any of these open source?

Apertus v1.5 8B and Ornith 1.5 122B publishes its weights (Apache-2.0 and MIT) and can be self-hosted; Restyler 1 is proprietary.

Which is newer?

Ornith 1.5 122B is the newest, released Oct 20, 2026. Apertus v1.5 8B came out Oct 15, 2026; Restyler 1 came out Sep 2, 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.