Step 3.5 Flash vs Hy-MT2-30B-A3B vs GLM-4.7-FlashX
Step 3.5 Flash comes out ahead, 63 to 59 and 44 on our weighted score, though Hy-MT2-30B-A3B is 14% cheaper per token.
- Our pick
StepFunStep 3.5 Flash
63/100- ECI—
- Price$0.10 / $0.30
- Context256K
TencentHy-MT2-30B-A3B
44/100- ECI—
- Price$0.074 / $0.295
- Context8K
Z.ai (Zhipu)GLM-4.7-FlashX
59/100- ECI—
- Price$0.07 / $0.40
- Context200K
Step 3.5 Flash is our pick
Step 3.5 Flash is the better all-round choice, scoring 63/100 against GLM-4.7-FlashX (59) and Hy-MT2-30B-A3B (44). It leads on inputs & features and context window. Hy-MT2-30B-A3B 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 priceHy-MT2-30B-A3BHy-MT2-30B-A3B $0.129 · Step 3.5 Flash $0.15 · GLM-4.7-FlashX $0.152 per 1M tokens (3:1 blend)
- Longest contextStep 3.5 FlashStep 3.5 Flash 256,000 · GLM-4.7-FlashX 200,000 · Hy-MT2-30B-A3B 8,192 tokens
- Widest inputsSame inputsStep 3.5 Flash: Text · Hy-MT2-30B-A3B: Text · GLM-4.7-FlashX: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Step 3.5 Flash | Hy-MT2-30B-A3B | GLM-4.7-FlashX |
|---|---|---|---|---|
| Price | 50% | 85 | 88 | 85 |
| Inputs & features | 30% | 45 | 0 | 35 |
| Context window | 20% | 36 | 0 | 32 |
| Overall | 100% | 63/100 | 44/100 | 59/100 |
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 | Step 3.5 FlashStepFun | Hy-MT2-30B-A3BTencent | GLM-4.7-FlashXZ.ai (Zhipu) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.10 | $0.074 | $0.07 (best) |
| Output | $0.30 | $0.295 (best) | $0.40 |
| Cached input | $0.02 | — | $0.01 (best) |
| Blended (3:1) | $0.15 | $0.129 (best) | $0.152 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official StepFun (Global) API | Median of 3 providers | Official Z.AI API |
| Limits | |||
| Context window | 256,000 tokens (best) | 8,192 tokens | 200,000 tokens |
| Max output | 256,000 tokens (best) | 4,096 tokens | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yeslow · high | No | Yes |
| Tool calling | Yes | No | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | step-3.5-flash | — | glm-4.7-flashx |
| API providers | 13 (best) | 3 | 10 |
| Released | Jan 29, 2026 | May 21, 2026 | Jan 19, 2026 |
| Knowledge cutoff | Jan 2025 | — | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Step 3.5 Flash$1.60
- Hy-MT2-30B-A3B$1.33
- GLM-4.7-FlashX$1.50
Which should you choose?
Which is better: Step 3.5 Flash, Hy-MT2-30B-A3B or GLM-4.7-FlashX?
Step 3.5 Flash is the better all-round choice, scoring 63/100 against GLM-4.7-FlashX (59) and Hy-MT2-30B-A3B (44). It leads on inputs & features and context window. Hy-MT2-30B-A3B 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, Step 3.5 Flash, Hy-MT2-30B-A3B or GLM-4.7-FlashX?
Hy-MT2-30B-A3B is cheaper at $0.074 input / $0.295 output per million tokens (median across 3 API providers). Step 3.5 Flash costs $0.10 input / $0.30 output per million tokens (official StepFun (Global) API price); GLM-4.7-FlashX costs $0.07 input / $0.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $0.129 per million tokens for Hy-MT2-30B-A3B versus $0.15 for Step 3.5 Flash (1.2× as much) and $0.152 for GLM-4.7-FlashX (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Step 3.5 Flash has not been scored yet, Hy-MT2-30B-A3B has not been scored yet and GLM-4.7-FlashX has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Step 3.5 Flash, Hy-MT2-30B-A3B and GLM-4.7-FlashX yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Hy-MT2-30B-A3B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Step 3.5 Flash has the largest context window at 256,000 tokens, against 200,000 for GLM-4.7-FlashX and 8,192 for Hy-MT2-30B-A3B. Maximum output per response: Step 3.5 Flash up to 256,000, Hy-MT2-30B-A3B up to 4,096, GLM-4.7-FlashX up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Step 3.5 Flash accepts text; Hy-MT2-30B-A3B accepts text; GLM-4.7-FlashX accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Hy-MT2-30B-A3B is the newest, released May 21, 2026. Step 3.5 Flash came out Jan 29, 2026; GLM-4.7-FlashX came out Jan 19, 2026. Knowledge cutoff: Step 3.5 Flash Jan 2025, GLM-4.7-FlashX Apr 2025.
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.
