ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Granite 4.2 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. IBM

    Granite 4.2 8B

    Released Aug 25, 2026

    65/100
    • ECI—
    • Price$0.06 / $0.15
    • Context131K
  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 (Granite 4.2 8B 65/100, 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 priceRestyler 1Restyler 1 $0.07 · Granite 4.2 8B $0.083 · Ornith 1.5 122B $0.28 per 1M tokens (3:1 blend)
  • Longest contextOrnith 1.5 122BOrnith 1.5 122B 262,144 · Granite 4.2 8B 131,072 · Restyler 1 4,096 tokens
  • Widest inputsOrnith 1.5 122BGranite 4.2 8B: Text · Ornith 1.5 122B: Text, Images · Restyler 1: Text
  • Self-hostingGranite 4.2 8B and Ornith 1.5 122BPublishes downloadable weights (MIT)
How the score is built
MeasureWeightGranite 4.2 8BOrnith 1.5 122BRestyler 1
Price50%9773100
Inputs & features30%35600
Context window20%32430
Specs & price only100%65/10063/10050/100

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.

Granite 4.2 8B vs Ornith 1.5 122B vs Restyler 1 specifications side by side
SpecificationGranite 4.2 8BIBMOrnith 1.5 122BDeepReinforceRestyler 1Meragpt
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.06$0.16$0.04 (best)
Output$0.15 (best)$0.64$0.16
Cached input———
Blended (3:1)$0.083$0.28$0.07 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 7 providersMedian of 1 providersMedian of 1 providers
Limits
Context window131,072 tokens262,144 tokens (best)4,096 tokens
Max output117,964 tokens (best)32,768 tokens2,048 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenOpenMITProprietary
API model ID———
API providers7 (best)11
ReleasedAug 25, 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.

  • Granite 4.2 8B$0.90
  • Ornith 1.5 122B$2.88
  • Restyler 1$0.72
04 — Questions

Which should you choose?

Which is better: Granite 4.2 8B, Ornith 1.5 122B or Restyler 1?

There is not enough shared capability evidence to name an overall winner. The scores (Granite 4.2 8B 65/100, 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, Granite 4.2 8B, Ornith 1.5 122B or Restyler 1?

Restyler 1 is cheaper at $0.04 input / $0.16 output per million tokens (median across 1 API provider). Granite 4.2 8B costs $0.06 input / $0.15 output per million tokens (median across 7 API providers); 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 $0.07 per million tokens for Restyler 1 versus $0.083 for Granite 4.2 8B (1.2× as much) and $0.28 for Ornith 1.5 122B (4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Granite 4.2 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 Granite 4.2 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?

Ornith 1.5 122B has the largest context window at 262,144 tokens, against 131,072 for Granite 4.2 8B and 4,096 for Restyler 1. Maximum output per response: Granite 4.2 8B up to 117,964, Ornith 1.5 122B up to 32,768, Restyler 1 up to 2,048 tokens.

Which can read images, PDFs, audio or video?

Granite 4.2 8B accepts text; Ornith 1.5 122B accepts text and images; Restyler 1 accepts text. Ornith 1.5 122B handles the widest range of inputs.

Are any of these open source?

Granite 4.2 8B and Ornith 1.5 122B publishes its weights (MIT) and can be self-hosted; Restyler 1 is proprietary.

Which is newer?

Ornith 1.5 122B is the newest, released Oct 20, 2026. Restyler 1 came out Sep 2, 2026; Granite 4.2 8B came out Aug 25, 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.