Models›Microsoft
Microsoft
Microsoft Research ships the compact Phi family and Copilot-tuned variants.
Models
1
on Gizmo
Free
0
plan limits apply
Open weights
1
downloadable
Largest context
16k
tokens
Models · 1
Compare Fast and Cheap modes, see the percentage saved, or filter to models with a verified discount. Select any model for its full pricing and API options.
Fast mode prioritizes response speed. Cheap mode uses lower-cost capacity and may be a little slower. Compare the same model’s input and output rates below.
| Model | Fast mode Input / output per 1M tokens | Cheap mode Input / output per 1M tokens | Discount | Run model |
|---|---|---|---|---|
| Phi 4Microsoft · 16K context | $0.0735 / $0.147 | $0.0588 / $0.1176 | 20% off |
1 of 1 models · Prices include your 5% platform fee.
Discounts compare current uncached input and output rates. Different percentages mean savings depend on your token mix. Fast rates are routing ceilings; actual charges and capacity may vary. No discount is shown without a verified quote.