Models22in catalog
Largest context131KDolphin 2 9 2 Qwen2 72b

Avg context

75K

Cheapest input

$0.070/M

Phi 4

Largest output

131K

Dolphin 2 9 2 Qwen2 72b

Speed tiers

deep 2fast 8balanced 12

Capabilities

What Microsoft models support across the catalog.

Vision

2 / 22

9% of models

Tool use

5 / 22

23% of models

Function calling

5 / 22

23% of models

Extended thinking

1 / 22

5% of models

Streaming

22 / 22

100% of models

Prompt caching

1 / 22

5% of models

All Microsoft models

Sorted by context window, largest first. Tap a row for full specs.

ModelContext
Dolphin 2 9 2 Qwen2 72b131K
Phi 4 Mini131K
Phi 4 Mini Reasoning131K
Phi 4 Multimodal131K
Phi 3 5 Mini128K
Phi 3 5 Moe128K
Phi 3 5 Vision128K
Phi 3 Medium 128k128K
Phi 3 Mini 128k128K
Phi 3 Small 128k128K
Phi 4 Mini Instruct128K
WizardLM-2 8x22B66K
Openorca 7b33K
Phi 4 Reasoning33K
Phi 3 Vision 128k32K
Chatdolphin16K
Dolphin16K
Phi 416K
Phi 3 Small 8k8K
Phi 3 Medium 4k4K
Phi 3 Mini 4k4K
Phi 2 3b2K

See rankings

How Microsoft models rank against the full catalog.