MiniMax-M2.5-highspeed vs Qwen3.5 9B vs DeepSeek OCR 2
Qwen3.5 9B comes out ahead, 79 to 41 and 32 on our weighted score, and it is the cheaper option too.
MiniMaxMiniMax-M2.5-highspeed
41/100- ECI—
- Price$0.60 / $2.40
- Context205K
- Our pick
Alibaba (Qwen)Qwen3.5 9B
79/100- ECI139.5
- Price$0.10 / $0.15
- Context262K
DeepSeekDeepSeek OCR 2
32/100- ECI—
- Price$0.89 / $1.47
- Context8K
Qwen3.5 9B is our pick
Qwen3.5 9B is the better all-round choice, scoring 79/100 against MiniMax-M2.5-highspeed (41) and 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 priceQwen3.5 9BQwen3.5 9B $0.113 · DeepSeek OCR 2 $1.03 · MiniMax-M2.5-highspeed $1.05 per 1M tokens (3:1 blend)
- Longest contextQwen3.5 9BQwen3.5 9B 262,144 · MiniMax-M2.5-highspeed 204,800 · DeepSeek OCR 2 8,192 tokens
- Widest inputsQwen3.5 9BMiniMax-M2.5-highspeed: Text · Qwen3.5 9B: Text, Images, Video · DeepSeek OCR 2: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | MiniMax-M2.5-highspeed | Qwen3.5 9B | DeepSeek OCR 2 |
|---|---|---|---|---|
| Price | 50% | 49 | 95 | 49 |
| Inputs & features | 30% | 35 | 80 | 25 |
| Context window | 20% | 32 | 37 | 0 |
| Overall | 100% | 41/100 | 79/100 | 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 | Qwen3.5 9BAlibaba (Qwen) | DeepSeek OCR 2DeepSeek |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 139.5 | — |
| ECI rank | — | #101 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 79.0% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 61.7% | — |
| Price per million tokens | |||
| Input | $0.60 | $0.10 (best) | $0.89 |
| Output | $2.40 | $0.15 (best) | $1.47 |
| Cached input | $0.06 | — | — |
| Blended (3:1) | $1.05 | $0.113 (best) | $1.03 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official MiniMax (minimax.io) API | Median of 14 providers | Median of 1 providers |
| Limits | |||
| Context window | 204,800 tokens | 262,144 tokens (best) | 8,192 tokens |
| Max output | 131,072 tokens (best) | 65,536 tokens | 8,192 tokens |
| 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 | Yes | No |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | MiniMax-M2.5-highspeed | — | — |
| API providers | 7 | 15 (best) | 2 |
| Released | Feb 13, 2026 | Feb 23, 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
- Qwen3.5 9B$1.30
- DeepSeek OCR 2$11.83
Which should you choose?
Which is better: MiniMax-M2.5-highspeed, Qwen3.5 9B or DeepSeek OCR 2?
Qwen3.5 9B is the better all-round choice, scoring 79/100 against MiniMax-M2.5-highspeed (41) and 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, MiniMax-M2.5-highspeed, Qwen3.5 9B or DeepSeek OCR 2?
Qwen3.5 9B is cheaper at $0.10 input / $0.15 output per million tokens (median across 14 API providers). 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 $0.113 per million tokens for Qwen3.5 9B versus $1.03 for DeepSeek OCR 2 (9.2× as much) and $1.05 for MiniMax-M2.5-highspeed (9.3× 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, Qwen3.5 9B has an ECI of 139.5 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, Qwen3.5 9B 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 DeepSeek OCR 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen3.5 9B has the largest context window at 262,144 tokens, against 204,800 for MiniMax-M2.5-highspeed and 8,192 for DeepSeek OCR 2. Maximum output per response: MiniMax-M2.5-highspeed up to 131,072, Qwen3.5 9B up to 65,536, DeepSeek OCR 2 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
MiniMax-M2.5-highspeed accepts text; Qwen3.5 9B accepts text, images and video; DeepSeek OCR 2 accepts text and images. Qwen3.5 9B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Qwen3.5 9B is the newest, released Feb 23, 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.
