ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Mercury Edit 2 vs Kolibri 1 vs Trinity Large Thinking

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. Inception

    Mercury Edit 2

    Released Mar 30, 2026

    36/100
    • ECI—
    • Price$0.25 / $0.75
    • Context32K
  2. Aleph Alpha

    Kolibri 1

    Released Oct 3, 2026New

    60/100
    • ECI—
    • Price$0.167 / $0.588
    • Context1.05M
  3. Arcee AI

    Trinity Large Thinking

    Released Apr 1, 2026Beta

    55/100
    • ECI—
    • Price$0.25 / $0.80
    • Context524K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Kolibri 1 60/100, Trinity Large Thinking 55/100, Mercury Edit 2 36/100) 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 priceKolibri 1Kolibri 1 $0.272 · Mercury Edit 2 $0.375 · Trinity Large Thinking $0.388 per 1M tokens (3:1 blend)
  • Longest contextKolibri 1Kolibri 1 1,048,576 · Trinity Large Thinking 524,288 · Mercury Edit 2 32,000 tokens
  • Widest inputsSame inputsMercury Edit 2: Text · Kolibri 1: Text · Trinity Large Thinking: Text
  • Self-hostingKolibri 1 and Trinity Large ThinkingPublishes downloadable weights (Apache-2.0 and OpenMDW-1.1)
How the score is built
MeasureWeightMercury Edit 2Kolibri 1Trinity Large Thinking
Price50%677366
Inputs & features30%03535
Context window20%106554
Specs & price only100%36/10060/10055/100

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.

Mercury Edit 2 vs Kolibri 1 vs Trinity Large Thinking specifications side by side
SpecificationMercury Edit 2InceptionKolibri 1Aleph AlphaTrinity Large ThinkingArcee AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.25$0.167 (best)$0.25
Output$0.75$0.588 (best)$0.80
Cached input$0.025 (best)—$0.06
Blended (3:1)$0.375$0.272 (best)$0.388
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Inception APIMedian of 5 providersOfficial Arcee API
Limits
Context window32,000 tokens1,048,576 tokens (best)524,288 tokens
Max output8,192 tokens—262,144 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesYes
Tool callingNoYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenApache-2.0OpenOpenMDW-1.1
API model IDmercury-edit-2—trinity-large-thinking
API providers15 (best)2
ReleasedMar 30, 2026Oct 3, 2026Apr 1, 2026
Knowledge cutoff—Jun 18, 2026—
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.

  • Mercury Edit 2$4.00
  • Kolibri 1$2.85
  • Trinity Large Thinking$4.10
04 — Questions

Which should you choose?

Which is better: Mercury Edit 2, Kolibri 1 or Trinity Large Thinking?

There is not enough shared capability evidence to name an overall winner. The scores (Kolibri 1 60/100, Trinity Large Thinking 55/100, Mercury Edit 2 36/100) 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, Mercury Edit 2, Kolibri 1 or Trinity Large Thinking?

Kolibri 1 is cheaper at $0.167 input / $0.588 output per million tokens (median across 5 API providers). Mercury Edit 2 costs $0.25 input / $0.75 output per million tokens (official Inception API price); Trinity Large Thinking costs $0.25 input / $0.80 output per million tokens (official Arcee API price). At a typical mix of three input tokens to one output token, that is $0.272 per million tokens for Kolibri 1 versus $0.375 for Mercury Edit 2 (1.4× as much) and $0.388 for Trinity Large Thinking (1.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Mercury Edit 2 has not been scored yet, Kolibri 1 has not been scored yet and Trinity Large Thinking has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Mercury Edit 2, Kolibri 1 and Trinity Large Thinking yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Mercury Edit 2 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Kolibri 1 has the largest context window at 1,048,576 tokens, against 524,288 for Trinity Large Thinking and 32,000 for Mercury Edit 2. Maximum output per response: Mercury Edit 2 up to 8,192, Trinity Large Thinking up to 262,144 tokens.

Which can read images, PDFs, audio or video?

Mercury Edit 2 accepts text; Kolibri 1 accepts text; Trinity Large Thinking accepts text. They handle the same number of input types.

Are any of these open source?

Kolibri 1 and Trinity Large Thinking publishes its weights (Apache-2.0 and OpenMDW-1.1) and can be self-hosted; Mercury Edit 2 is proprietary.

Which is newer?

Kolibri 1 is the newest, released Oct 3, 2026. Trinity Large Thinking came out Apr 1, 2026; Mercury Edit 2 came out Mar 30, 2026. Knowledge cutoff: Kolibri 1 Jun 18, 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.