MAI Code 2 Flash vs MAI-Code-1.1-Flash vs Hy4 flash
No independent capability benchmark covers every model here yet. The score uses context window.
Price in rating: Included · Exclude price
Microsoft
MAI Code 2 Flash
65/100- ECI—
- Price$0.05 / $0.25
- Context1.05M
Microsoft
MAI-Code-1.1-Flash
43/100- ECI—
- Price—
- Context256K
Tencent
Hy4 flash
65/100- ECI—
- Price$0.07 / $0.281
- Context1.05M
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (MAI Code 2 Flash 65/100, Hy4 flash 65/100, MAI-Code-1.1-Flash 43/100) compare the available specifications and price. The score weighs context window 100%. 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 · Hy4 flash $0.123 per 1M tokens (3:1 blend) · MAI-Code-1.1-Flash unpriced
- Longest contextMAI Code 2 Flash and Hy4 flashMAI Code 2 Flash 1,050,000 · Hy4 flash 1,048,576 · MAI-Code-1.1-Flash 256,000 tokens
- Widest inputsSame inputsMAI Code 2 Flash: Text, Images · MAI-Code-1.1-Flash: Text, Images · Hy4 flash: Text, Images
- Self-hostingNo confirmed open weightsAll three are available only through APIs
| Measure | Weight | MAI Code 2 Flash | MAI-Code-1.1-Flash | Hy4 flash |
|---|---|---|---|---|
| Context window | 100% | 65 | 43 | 65 |
| Specs & price only | 100% | 65/100 | 43/100 | 65/100 |
Left out because at least one model lacks the data: capability, price 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 | — | — |
| Published capabilities | Smaller mixture-of-experts coding model for quick edits, explanations and iteration. | Microsoft coding model with native vision support, optimized for fast and efficient software development | Tencent's lower-cost Hy4 tier for everyday agent and productivity tasks, with image understanding and a 1M-token context window. |
| Model size | 12B active parameters | — | — |
| Access | GitHub Copilot and limited-access Microsoft Foundry preview | — | — |
| Billing terms | Promotional GitHub Copilot token rates until May 17, 2027. | — | — |
| Sources | Publisher documentation · Additional documentation · Pricing documentation | — | — |
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.05 (best) | — | $0.07 |
| Output | $0.25 (best) | — | $0.281 |
| Cached input | $0.005 | — | — |
| Blended (3:1) | $0.10 (best) | — | $0.123 |
| Long-context rate | Same rate | — | Same rate |
| Price source | Official GitHub Copilot API | — | Median of 10 providers |
| Limits | |||
| Context window | 1,050,000 tokens (best) | 256,000 tokens | 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 | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | — | No | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | — | — | — |
| API providers | — | — | 11 |
| Released | Nov 17, 2026 | Aug 11, 2026 | Nov 16, 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 Flash$1.00
MAI-Code-1.1-Flash—
Hy4 flash$1.26
Which should you choose?
Which is better: MAI Code 2 Flash, MAI-Code-1.1-Flash or Hy4 flash?
There is not enough shared capability evidence to name an overall winner. The scores (MAI Code 2 Flash 65/100, Hy4 flash 65/100, MAI-Code-1.1-Flash 43/100) compare the available specifications and price. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MAI Code 2 Flash, MAI-Code-1.1-Flash or Hy4 flash?
MAI Code 2 Flash is cheaper at $0.05 input / $0.25 output per million tokens (official GitHub Copilot API price). Hy4 flash costs $0.07 input / $0.281 output per million tokens (median across 10 API providers). 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 $0.123 for Hy4 flash (1.2× as much). MAI-Code-1.1-Flash has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. MAI Code 2 Flash has not been scored yet, MAI-Code-1.1-Flash has not been scored yet and Hy4 flash has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MAI Code 2 Flash, MAI-Code-1.1-Flash and Hy4 flash 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?
MAI Code 2 Flash and Hy4 flash have the largest context windows (1,050,000 and 1,048,576 tokens), against 256,000 for MAI-Code-1.1-Flash. Maximum output per response: MAI Code 2 Flash up to 128,000, MAI-Code-1.1-Flash up to 128,000, Hy4 flash up to 65,536 tokens.
Which can read images, PDFs, audio or video?
MAI Code 2 Flash accepts text and images; MAI-Code-1.1-Flash accepts text and images; Hy4 flash accepts text and images. They handle the same number of input types.
Are any of these open source?
No. MAI Code 2 Flash, MAI-Code-1.1-Flash and Hy4 flash are proprietary and only available through APIs and apps.
Which is newer?
MAI Code 2 Flash is the newest, released Nov 17, 2026. Hy4 flash came out Nov 16, 2026; MAI-Code-1.1-Flash came out Aug 11, 2026.
How do you decide the winner?
This rating uses context window (100%, 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.