Microsoft Models
Usage
3.1K
380
9 of 14
- mai-image-2.5-pro
- mai-image-2.5
- mai-image-2.5-flash
- aihub-Phi-4
- mai-thinking-1
- AiHubmix-Phi-4-mini-reasoning
- ahm-Phi-3-5-vision-instruct
- aihub-Phi-4-mini-instruct
- 1 more model
Which models that traffic went to
- Mai Thinking 1100.0%3.1K
- Mai Image 2.5 Pro31.3%119
- Mai Image 2.522.9%87
- Mai Image 2.5 Flash22.6%86
- Aihub Phi 47.9%30
- Mai Thinking 17.6%29
- Aihubmix Phi 4 Mini (reasoning)6.8%26
- Ahm Phi 3.5 Vision Instruct0.3%1
- Aihub Phi 4 Mini Instruct0.3%1
- 1 more model0.3%1
All 14 Microsoft Models
Open in model list| Modalities | ||||||
|---|---|---|---|---|---|---|
| mai-thinking-1 | Takes text, returns text. | 256K | — | $2.00$8.00/M | 42 tok/s | 6.67 s |
| aihub-Phi-4-mini-instruct | Takes text, returns text. | 128K | 4K | $0.12$0.48/M | — | — |
| aihub-Phi-4-multimodal-instruct | Takes text, vision, audio, returns text. | 128K | 4K | $0.12$0.48/M | — | — |
| AiHubmix-Phi-4-mini-reasoning | Takes text, returns text. | 128K | 4K | $0.12$0.12/M | — | — |
| aihub-Phi-4 | Takes text, returns text. | 16K | — | $0.12$0.48/M | 46 tok/s | 0.41 s |
| mai-image-2.5 | Takes text, vision, returns text, vision. | — | — | FreeFree/M | — | — |
| mai-image-2.5-flash | Takes text, vision, returns text, vision. | — | — | FreeFree/M | — | — |
| mai-image-2.5-pro | Takes text, vision, returns text, vision. | — | — | FreeFree/M | — | — |
| ahm-Phi-3-5-MoE-instruct | — | — | $0.40$1.60/M | — | — | |
| ahm-Phi-3-5-vision-instruct | Takes text, vision, returns text. | — | — | $0.40$1.60/M | — | — |
| ahm-Phi-3-5-mini-instruct | — | — | $1.00$3.00/M | — | — | |
| ahm-Phi-3-medium-4k | — | — | $1.00$3.00/M | — | — | |
| ahm-Phi-3-small-128k | — | — | $1.00$3.00/M | — | — | |
| ahm-Phi-3-medium-128k | — | — | $6.00$18.00/M | — | — |
Microsoft on AIHubMix
Which Microsoft model should I start with?
mai-image-2.5 is free on input — the cheapest entry here that declares a token price. Move up to ahm-Phi-3-medium-128k when answer quality matters more than cost, or to mai-thinking-1 for long-form reasoning.
Which of these models reason before answering?
1 of the 14 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.
Why are there several entries for the same model?
Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), and some differ only in capitalisation, kept so older integrations keep working.
The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.
Do I need a separate Microsoft account?
No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.
Start calling Microsoft in one line
One key, one endpoint, 859 models across 37 model authors.
AIHubMix