MiniMax-M2.5-highspeed vs Mercury Edit 2 vs DeepSeek OCR 2
MiniMax-M2.5-highspeed comes out ahead, 41 to 35 and 32 on our weighted score, though Mercury Edit 2 is 2.8× cheaper per token.
- Our pick
MiniMaxMiniMax-M2.5-highspeed
41/100- ECI—
- Price$0.60 / $2.40
- Context205K
InceptionMercury Edit 2
35/100- ECI—
- Price$0.25 / $0.75
- Context32K
DeepSeekDeepSeek OCR 2
32/100- ECI—
- Price$0.89 / $1.47
- Context8K
MiniMax-M2.5-highspeed is our pick
MiniMax-M2.5-highspeed is the better all-round choice, scoring 41/100 against Mercury Edit 2 (35) and DeepSeek OCR 2 (32). It leads on inputs & features and context window. Mercury Edit 2 wins on 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 priceMercury Edit 2Mercury Edit 2 $0.375 · DeepSeek OCR 2 $1.03 · MiniMax-M2.5-highspeed $1.05 per 1M tokens (3:1 blend)
- Longest contextMiniMax-M2.5-highspeedMiniMax-M2.5-highspeed 204,800 · Mercury Edit 2 32,000 · DeepSeek OCR 2 8,192 tokens
- Widest inputsDeepSeek OCR 2MiniMax-M2.5-highspeed: Text · Mercury Edit 2: Text · DeepSeek OCR 2: Text, Images
- Self-hostingMiniMax-M2.5-highspeed and DeepSeek OCR 2Publishes downloadable weights
| Measure | Weight | MiniMax-M2.5-highspeed | Mercury Edit 2 | DeepSeek OCR 2 |
|---|---|---|---|---|
| Price | 50% | 49 | 70 | 49 |
| Inputs & features | 30% | 35 | 0 | 25 |
| Context window | 20% | 32 | 0 | 0 |
| Overall | 100% | 41/100 | 35/100 | 32/100 |
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-M2.5-highspeedMiniMax | Mercury Edit 2Inception | DeepSeek OCR 2DeepSeek |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.60 | $0.25 (best) | $0.89 |
| Output | $2.40 | $0.75 (best) | $1.47 |
| Cached input | $0.06 | $0.025 (best) | — |
| Blended (3:1) | $1.05 | $0.375 (best) | $1.03 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official MiniMax (minimax.io) API | Official Inception API | Median of 1 providers |
| Limits | |||
| Context window | 204,800 tokens (best) | 32,000 tokens | 8,192 tokens |
| Max output | 131,072 tokens (best) | 8,192 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | No | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | MiniMax-M2.5-highspeed | mercury-edit-2 | — |
| API providers | 7 (best) | 1 | 2 |
| Released | Feb 13, 2026 | Mar 30, 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-M2.5-highspeed$10.80
- Mercury Edit 2$4.00
- DeepSeek OCR 2$11.83
Which should you choose?
Which is better: MiniMax-M2.5-highspeed, Mercury Edit 2 or DeepSeek OCR 2?
MiniMax-M2.5-highspeed is the better all-round choice, scoring 41/100 against Mercury Edit 2 (35) and DeepSeek OCR 2 (32). It leads on inputs & features and context window. Mercury Edit 2 wins on 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, MiniMax-M2.5-highspeed, Mercury Edit 2 or DeepSeek OCR 2?
Mercury Edit 2 is cheaper at $0.25 input / $0.75 output per million tokens (official Inception API price). DeepSeek OCR 2 costs $0.89 input / $1.47 output per million tokens (median across 1 API provider); MiniMax-M2.5-highspeed costs $0.60 input / $2.40 output per million tokens (official MiniMax (minimax.io) API price). At a typical mix of three input tokens to one output token, that is $0.375 per million tokens for Mercury Edit 2 versus $1.03 for DeepSeek OCR 2 (2.8× as much) and $1.05 for MiniMax-M2.5-highspeed (2.8× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MiniMax-M2.5-highspeed has not been scored yet, Mercury Edit 2 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-M2.5-highspeed, Mercury Edit 2 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 Mercury Edit 2 and DeepSeek OCR 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
MiniMax-M2.5-highspeed has the largest context window at 204,800 tokens, against 32,000 for Mercury Edit 2 and 8,192 for DeepSeek OCR 2. Maximum output per response: MiniMax-M2.5-highspeed up to 131,072, Mercury Edit 2 up to 8,192, DeepSeek OCR 2 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
MiniMax-M2.5-highspeed accepts text; Mercury Edit 2 accepts text; DeepSeek OCR 2 accepts text and images. DeepSeek OCR 2 handles the widest range of inputs.
Are any of these open source?
MiniMax-M2.5-highspeed and DeepSeek OCR 2 publishes its weights and can be self-hosted; Mercury Edit 2 is proprietary.
Which is newer?
Mercury Edit 2 is the newest, released Mar 30, 2026. MiniMax-M2.5-highspeed came out Feb 13, 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.
