MiniMax-M2 Her vs Perceptron Mk1 vs DeepSeek OCR 2
Too close to call on our weighted score (Perceptron Mk1 45, MiniMax-M2 Her 43, DeepSeek OCR 2 38). The right pick depends on what you value most.
MiniMaxMiniMax-M2 Her
43/100- ECI—
- Price$0.30 / $1.20
- Context66K
Perceptron
Perceptron Mk1
45/100- ECI—
- Price$0.15 / $1.50
- Context33K
DeepSeekDeepSeek OCR 2
38/100- ECI—
- Price$0.46 / $0.749
- Context8K
Too close to call
It is close. Our weighted score puts them within 1 points (Perceptron Mk1 45/100, MiniMax-M2 Her 43/100, DeepSeek OCR 2 38/100), so choose by what matters most for your work: Perceptron Mk1 on price and MiniMax-M2 Her for long inputs. 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 pricePerceptron Mk1Perceptron Mk1 $0.487 · MiniMax-M2 Her $0.525 · DeepSeek OCR 2 $0.532 per 1M tokens (3:1 blend)
- Longest contextMiniMax-M2 HerMiniMax-M2 Her 65,536 · Perceptron Mk1 32,768 · DeepSeek OCR 2 8,192 tokens
- Widest inputsPerceptron Mk1MiniMax-M2 Her: Text · Perceptron Mk1: Text, Images, Video · DeepSeek OCR 2: Text, Images
- Self-hostingDeepSeek OCR 2Publishes downloadable weights
| Measure | Weight | MiniMax-M2 Her | Perceptron Mk1 | DeepSeek OCR 2 |
|---|---|---|---|---|
| Price | 50% | 60 | 62 | 60 |
| Inputs & features | 30% | 35 | 45 | 25 |
| Context window | 20% | 12 | 0 | 0 |
| Overall | 100% | 43/100 | 45/100 | 38/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | MiniMax-M2 HerMiniMax | Perceptron Mk1Perceptron | DeepSeek OCR 2DeepSeek |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.15 (best) | $0.46 |
| Output | $1.20 | $1.50 | $0.749 (best) |
| Cached input | — | — | — |
| Blended (3:1) | $0.525 | $0.487 (best) | $0.532 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 3 providers | Median of 3 providers | Median of 2 providers |
| Limits | |||
| Context window | 65,536 tokens (best) | 32,768 tokens | 8,192 tokens |
| Max output | 2,048 tokens | 8,192 tokens (best) | 8,192 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | No | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Open |
| API model ID | — | — | — |
| API providers | 3 | 3 | 3 |
| Released | Jan 23, 2026 | May 12, 2026 | Jan 27, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- MiniMax-M2 Her$5.40
- Perceptron Mk1$4.50
- DeepSeek OCR 2$6.10
Which should you choose?
Which is better: MiniMax-M2 Her, Perceptron Mk1 or DeepSeek OCR 2?
It is close. Our weighted score puts them within 1 points (Perceptron Mk1 45/100, MiniMax-M2 Her 43/100, DeepSeek OCR 2 38/100), so choose by what matters most for your work: Perceptron Mk1 on price and MiniMax-M2 Her for long inputs. 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, MiniMax-M2 Her, Perceptron Mk1 or DeepSeek OCR 2?
Perceptron Mk1 is cheaper at $0.15 input / $1.50 output per million tokens (median across 3 API providers). MiniMax-M2 Her costs $0.30 input / $1.20 output per million tokens (median across 3 API providers); 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 $0.487 per million tokens for Perceptron Mk1 versus $0.525 for MiniMax-M2 Her (1.1× as much) and $0.532 for DeepSeek OCR 2 (1.1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniMax-M2 Her has not been scored yet, Perceptron Mk1 has not been scored yet and DeepSeek OCR 2 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniMax-M2 Her, Perceptron Mk1 and DeepSeek OCR 2 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Perceptron Mk1 and DeepSeek OCR 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
MiniMax-M2 Her has the largest context window at 65,536 tokens, against 32,768 for Perceptron Mk1 and 8,192 for DeepSeek OCR 2. Maximum output per response: MiniMax-M2 Her up to 2,048, Perceptron Mk1 up to 8,192, DeepSeek OCR 2 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
MiniMax-M2 Her accepts text; Perceptron Mk1 accepts text, images and video; DeepSeek OCR 2 accepts text and images. Perceptron Mk1 handles the widest range of inputs.
Are any of these open source?
DeepSeek OCR 2 publishes its weights and can be self-hosted; MiniMax-M2 Her and Perceptron Mk1 is proprietary.
Which is newer?
Perceptron Mk1 is the newest, released May 12, 2026. DeepSeek OCR 2 came out Jan 27, 2026; MiniMax-M2 Her came out Jan 23, 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 Nov 2, 2026.
