Hy4 preview vs MiniMax-M2.5-highspeed vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B comes out ahead, 58 to 45 and 41 on our weighted score.
TencentHy4 preview
45/100- ECI—
- Price$0.834 / $2.50
- Context1.02M
MiniMaxMiniMax-M2.5-highspeed
41/100- ECI—
- Price$0.60 / $2.40
- Context205K
- Our pick
Alibaba (Qwen)Qwen3.5 122B-A10B
58/100- ECI—
- Price$0.40 / $3.20
- Context262K
Qwen3.5 122B-A10B is our pick
Qwen3.5 122B-A10B is the better all-round choice, scoring 58/100 against Hy4 preview (45) and MiniMax-M2.5-highspeed (41). It leads on inputs & features. Hy4 preview wins on 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 priceMiniMax-M2.5-highspeedMiniMax-M2.5-highspeed $1.05 · Qwen3.5 122B-A10B $1.10 · Hy4 preview $1.25 per 1M tokens (3:1 blend)
- Longest contextHy4 previewHy4 preview 1,024,000 · Qwen3.5 122B-A10B 262,144 · MiniMax-M2.5-highspeed 204,800 tokens
- Widest inputsQwen3.5 122B-A10BHy4 preview: Text · MiniMax-M2.5-highspeed: Text · Qwen3.5 122B-A10B: Text, Images, Audio, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Hy4 preview | MiniMax-M2.5-highspeed | Qwen3.5 122B-A10B |
|---|---|---|---|---|
| Price | 50% | 45 | 49 | 48 |
| Inputs & features | 30% | 35 | 35 | 90 |
| Context window | 20% | 60 | 32 | 37 |
| Overall | 100% | 45/100 | 41/100 | 58/100 |
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 | Hy4 previewTencent | MiniMax-M2.5-highspeedMiniMax | Qwen3.5 122B-A10BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.834 | $0.60 | $0.40 (best) |
| Output | $2.50 | $2.40 (best) | $3.20 |
| Cached input | $0.042 (best) | $0.06 | — |
| Blended (3:1) | $1.25 | $1.05 (best) | $1.10 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Tencent TokenHub API | Official MiniMax (minimax.io) API | Official Alibaba API |
| Limits | |||
| Context window | 1,024,000 tokens (best) | 204,800 tokens | 262,144 tokens |
| Max output | 64,000 tokens | 131,072 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yeshigh | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | hy4-preview | MiniMax-M2.5-highspeed | qwen3.5-122b-a10b |
| API providers | 13 | 7 | 19 (best) |
| Released | Aug 28, 2026 | Feb 13, 2026 | Feb 23, 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.
- Hy4 preview$13.34
- MiniMax-M2.5-highspeed$10.80
- Qwen3.5 122B-A10B$10.40
Which should you choose?
Which is better: Hy4 preview, MiniMax-M2.5-highspeed or Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the better all-round choice, scoring 58/100 against Hy4 preview (45) and MiniMax-M2.5-highspeed (41). It leads on inputs & features. Hy4 preview wins on 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, Hy4 preview, MiniMax-M2.5-highspeed or Qwen3.5 122B-A10B?
MiniMax-M2.5-highspeed is cheaper at $0.60 input / $2.40 output per million tokens (official MiniMax (minimax.io) API price). Qwen3.5 122B-A10B costs $0.40 input / $3.20 output per million tokens (official Alibaba API price); Hy4 preview costs $0.834 input / $2.50 output per million tokens (official Tencent TokenHub API price). At a typical mix of three input tokens to one output token, that is $1.05 per million tokens for MiniMax-M2.5-highspeed versus $1.10 for Qwen3.5 122B-A10B (1× as much) and $1.25 for Hy4 preview (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Hy4 preview has not been scored yet, MiniMax-M2.5-highspeed has not been scored yet and Qwen3.5 122B-A10B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Hy4 preview, MiniMax-M2.5-highspeed and Qwen3.5 122B-A10B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Hy4 preview has the largest context window at 1,024,000 tokens, against 262,144 for Qwen3.5 122B-A10B and 204,800 for MiniMax-M2.5-highspeed. Maximum output per response: Hy4 preview up to 64,000, MiniMax-M2.5-highspeed up to 131,072, Qwen3.5 122B-A10B up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Hy4 preview accepts text; MiniMax-M2.5-highspeed accepts text; Qwen3.5 122B-A10B accepts text, images, audio and video. Qwen3.5 122B-A10B 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?
Hy4 preview is the newest, released Aug 28, 2026. Qwen3.5 122B-A10B came out Feb 23, 2026; MiniMax-M2.5-highspeed came out Feb 13, 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.
