ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek OCR 2 vs Jamba Mini vs Trinity Large Preview

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

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek OCR 2

    Released Jan 27, 2026

    15/100
    • ECI—
    • Price$0.46 / $0.749
    • Context8K
  2. AI21 Labs

    Jamba Mini

    Released Jan 8, 2026

    38/100
    • ECI—
    • Price$0.20 / $0.40
    • Context256K
  3. Arcee AI

    Trinity Large Preview

    Released Jan 27, 2026

    37/100
    • ECI—
    • Price—
    • Context524K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Jamba Mini 38/100, Trinity Large Preview 37/100, DeepSeek OCR 2 15/100) 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 priceJamba MiniJamba Mini $0.25 · DeepSeek OCR 2 $0.532 per 1M tokens (3:1 blend) · Trinity Large Preview unpriced
  • Longest contextTrinity Large PreviewTrinity Large Preview 524,288 · Jamba Mini 256,000 · DeepSeek OCR 2 8,192 tokens
  • Widest inputsDeepSeek OCR 2DeepSeek OCR 2: Text, Images · Jamba Mini: Text · Trinity Large Preview: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDeepSeek OCR 2Jamba MiniTrinity Large Preview
Inputs & features60%253525
Context window40%04354
Specs only100%15/10038/10037/100

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.

DeepSeek OCR 2 vs Jamba Mini vs Trinity Large Preview specifications side by side
SpecificationDeepSeek OCR 2DeepSeekJamba MiniAI21 LabsTrinity Large PreviewArcee AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.46$0.20 (best)—
Output$0.749$0.40 (best)—
Cached input———
Blended (3:1)$0.532$0.25 (best)—
Long-context rateSame rateSame rate—
Price sourceMedian of 2 providersOfficial AI21 Labs API—
Limits
Context window8,192 tokens256,000 tokens524,288 tokens (best)
Max output8,192 tokens4,096 tokens262,144 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingNoYesYes
Structured outputNoYesNo
Availability
WeightsOpenOpenOpenOpenMDW-1.1
API model ID—jamba-mini—
API providers3 (best)11
ReleasedJan 27, 2026Jan 8, 2026Jan 27, 2026
Knowledge cutoff—Aug 22, 2024—
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.

  • DeepSeek OCR 2$6.10
  • Jamba Mini$2.80
  • Trinity Large Preview—
04 — Questions

Which should you choose?

Which is better: DeepSeek OCR 2, Jamba Mini or Trinity Large Preview?

There is not enough shared capability evidence to name an overall winner. The scores (Jamba Mini 38/100, Trinity Large Preview 37/100, DeepSeek OCR 2 15/100) 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, DeepSeek OCR 2, Jamba Mini or Trinity Large Preview?

Jamba Mini is cheaper at $0.20 input / $0.40 output per million tokens (official AI21 Labs API price). DeepSeek OCR 2 costs $0.46 input / $0.749 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.25 per million tokens for Jamba Mini versus $0.532 for DeepSeek OCR 2 (2.1× as much). Trinity Large Preview has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. DeepSeek OCR 2 has not been scored yet, Jamba Mini has not been scored yet and Trinity Large Preview has not been scored yet.

Which is better for coding?

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

Which has the bigger context window?

Trinity Large Preview has the largest context window at 524,288 tokens, against 256,000 for Jamba Mini and 8,192 for DeepSeek OCR 2. Maximum output per response: DeepSeek OCR 2 up to 8,192, Jamba Mini up to 4,096, Trinity Large Preview up to 262,144 tokens.

Which can read images, PDFs, audio or video?

DeepSeek OCR 2 accepts text and images; Jamba Mini accepts text; Trinity Large Preview accepts text. DeepSeek OCR 2 handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (OpenMDW-1.1), so you can self-host them.

Which is newer?

DeepSeek OCR 2 is the newest, released Jan 27, 2026. Trinity Large Preview came out Jan 27, 2026; Jamba Mini came out Jan 8, 2026. Knowledge cutoff: Jamba Mini Aug 22, 2024.

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.