MAI Code 2 vs MAI Code 2 Flash vs Hy4
No independent capability benchmark covers every model here yet. The score uses price and context window.
Price in rating: Included · Exclude price
Microsoft
MAI Code 2
53/100- ECI—
- Price$0.50 / $2.50
- Context1.05M
Microsoft
MAI Code 2 Flash
85/100- ECI—
- Price$0.05 / $0.25
- Context1.05M
Tencent
Hy4
49/100- ECI—
- Price$0.834 / $2.50
- Context1.05M
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (MAI Code 2 Flash 85/100, MAI Code 2 53/100, Hy4 49/100) compare the available specifications and price. The score weighs price 71%, context window 29%. 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 priceMAI Code 2 FlashMAI Code 2 Flash $0.10 · MAI Code 2 $1.00 · Hy4 $1.25 per 1M tokens (3:1 blend)
- Longest contextAbout the sameMAI Code 2 1,050,000 · MAI Code 2 Flash 1,050,000 · Hy4 1,048,576 tokens
- Widest inputsSame inputsMAI Code 2: Text, Images · MAI Code 2 Flash: Text, Images · Hy4: Text, Images
- Self-hostingNo confirmed open weightsAll three are available only through APIs
| Measure | Weight | MAI Code 2 | MAI Code 2 Flash | Hy4 |
|---|---|---|---|---|
| Price | 71% | 48 | 93 | 43 |
| Context window | 29% | 65 | 65 | 65 |
| Specs & price only | 100% | 53/100 | 85/100 | 49/100 |
Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Task | Coding | Coding | — |
| Published capabilities | Mixture-of-experts coding model for long-running engineering tasks and multi-file changes. | Smaller mixture-of-experts coding model for quick edits, explanations and iteration. | A next-generation multimodal productivity model with significantly enhanced Agent and complex task execution capabilities. |
| Model size | 80B active parameters | 12B active parameters | — |
| Access | GitHub Copilot | GitHub Copilot and limited-access Microsoft Foundry preview | — |
| Billing terms | Promotional GitHub Copilot token rates until May 17, 2027. | Promotional GitHub Copilot token rates until May 17, 2027. | — |
| Sources | Publisher documentation · Additional documentation · Pricing documentation | Publisher documentation · Additional documentation · Pricing documentation | — |
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.50 | $0.05 (best) | $0.834 |
| Output | $2.50 | $0.25 (best) | $2.50 |
| Cached input | $0.025 | $0.005 (best) | $0.042 |
| Blended (3:1) | $1.00 | $0.10 (best) | $1.25 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official GitHub Copilot API | Official GitHub Copilot API | Official Tencent TokenHub API |
| Limits | |||
| Context window | 1,050,000 tokens (best) | 1,050,000 tokens (best) | 1,048,576 tokens |
| Max output | 128,000 tokens (best) | 128,000 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | Yes | Yeshigh |
| Tool calling | Yes | Yes | Yes |
| Structured output | — | — | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | — | — | hy4 |
| API providers | — | — | 12 |
| Released | Nov 17, 2026 | Nov 17, 2026 | Nov 4, 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.
MAI Code 2$10.00
MAI Code 2 Flash$1.00
Hy4$13.34
Which should you choose?
Which is better: MAI Code 2, MAI Code 2 Flash or Hy4?
There is not enough shared capability evidence to name an overall winner. The scores (MAI Code 2 Flash 85/100, MAI Code 2 53/100, Hy4 49/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MAI Code 2, MAI Code 2 Flash or Hy4?
MAI Code 2 Flash is cheaper at $0.05 input / $0.25 output per million tokens (official GitHub Copilot API price). MAI Code 2 costs $0.50 input / $2.50 output per million tokens (official GitHub Copilot API price); Hy4 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 $0.10 per million tokens for MAI Code 2 Flash versus $1.00 for MAI Code 2 (10× as much) and $1.25 for Hy4 (13× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MAI Code 2 has not been scored yet, MAI Code 2 Flash has not been scored yet and Hy4 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MAI Code 2, MAI Code 2 Flash and Hy4 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?
Their context windows are effectively the same size: MAI Code 2 1,050,000, MAI Code 2 Flash 1,050,000 and Hy4 1,048,576 tokens. Maximum output per response: MAI Code 2 up to 128,000, MAI Code 2 Flash up to 128,000, Hy4 up to 65,536 tokens.
Which can read images, PDFs, audio or video?
MAI Code 2 accepts text and images; MAI Code 2 Flash accepts text and images; Hy4 accepts text and images. They handle the same number of input types.
Are any of these open source?
No. MAI Code 2, MAI Code 2 Flash and Hy4 are proprietary and only available through APIs and apps.
Which is newer?
MAI Code 2 is the newest, released Nov 17, 2026. MAI Code 2 Flash came out Nov 17, 2026; Hy4 came out Nov 4, 2026.
How do you decide the winner?
This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 19, 2026.