ZMIME
Comparison · 2 models · Updated Oct 4, 2026

DeepSeek OCR 2 vs Hy3 preview

Hy3 preview comes out ahead, 56 to 32 on our weighted score, and it is the cheaper option too.

  1. DeepSeek

    DeepSeek OCR 2

    Released Jan 27, 2026

    32/100
    • ECI—
    • Price$0.89 / $1.47
    • Context8K
    Full specs Remove DeepSeek OCR 2
  2. Our pick

    Tencent

    Hy3 preview

    Released Apr 20, 2026

    56/100
    • ECI—
    • Price$0.176 / $0.586
    • Context256K
    Full specs Remove Hy3 preview

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Hy3 preview is our pick

Hy3 preview is the better all-round choice, scoring 56/100 against DeepSeek OCR 2 (32). It leads on price, inputs & features and context window. 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 priceHy3 previewHy3 preview $0.279 · DeepSeek OCR 2 $1.03 per 1M tokens (3:1 blend)
  • Longest contextHy3 previewHy3 preview 256,000 · DeepSeek OCR 2 8,192 tokens
  • Widest inputsDeepSeek OCR 2DeepSeek OCR 2: Text, Images · Hy3 preview: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDeepSeek OCR 2Hy3 preview
Price50%4976
Inputs & features30%2535
Context window20%036
Overall100%32/10056/100

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 Hy3 preview specifications side by side
SpecificationDeepSeek OCR 2DeepSeekHy3 previewTencent
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input$0.89$0.176 (best)
Output$1.47$0.586 (best)
Cached input——
Blended (3:1)$1.03$0.279 (best)
Long-context rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 4 providers
Limits
Context window8,192 tokens256,000 tokens (best)
Max output8,192 tokens64,000 tokens (best)
Inputs and features
TextYesYes
ImagesYesNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningNoYeslow · medium · high
Tool callingNoYes
Structured outputNoNo
Availability
WeightsOpenOpen
API model ID—hy3-preview
API providers25 (best)
ReleasedJan 27, 2026Apr 20, 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.

  • DeepSeek OCR 2$11.83
  • Hy3 preview$2.93
04 — Questions

Which should you choose?

Which is better: DeepSeek OCR 2 or Hy3 preview?

Hy3 preview is the better all-round choice, scoring 56/100 against DeepSeek OCR 2 (32). It leads on price, inputs & features and context window. 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, DeepSeek OCR 2 or Hy3 preview?

Hy3 preview is cheaper at $0.176 input / $0.586 output per million tokens (median across 4 API providers; free on Tencent TokenHub). DeepSeek OCR 2 costs $0.89 input / $1.47 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.279 per million tokens for Hy3 preview versus $1.03 for DeepSeek OCR 2 (3.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. DeepSeek OCR 2 has not been scored yet and Hy3 preview has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek OCR 2 and Hy3 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?

Hy3 preview has the largest context window at 256,000 tokens, against 8,192 for DeepSeek OCR 2. Maximum output per response: DeepSeek OCR 2 up to 8,192, Hy3 preview up to 64,000 tokens.

Which can read images, PDFs, audio or video?

DeepSeek OCR 2 accepts text and images; Hy3 preview accepts text. DeepSeek OCR 2 handles the widest range of inputs.

Are any of these open source?

Yes, both publish their weights, so you can self-host them.

Which is newer?

Hy3 preview is the newest, released Apr 20, 2026. DeepSeek OCR 2 came out Jan 27, 2026.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons