Multimodal model for analyzing text, images, documents, and rich media
Phi-4-multimodal by microsoft is offered by 4 providers on this page. Public prices are shown for 3 of them. Its official list price is $0.08 per 1M input tokens and $0.32 per 1M output tokens. The lowest paid channel is NanoGPT at $0.07 / $0.11 per 1M, about 1.8× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 128,000 tokens, with an output limit of 4,096 tokens. Accepted input modalities are Text, Image, and Audio. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2023-10.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia microsoft/phi-4-multimodal-instruct | Cloud | Free | — | — | 128,000 | 16,384 | deprecated | |
| NanoGPT phi-4-multimodal-instruct | Gateway | $0.07 | $0.11 | $0.035 | — | 128,000 | 16,384 | |
| Azure Cognitive ServicesOfficial | Cloud | $0.08 | $0.32 | — | — | 128,000 | 4,096 | |
| AzureOfficial | Cloud | $0.08 | $0.32 | — | — | 128,000 | 4,096 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
| Provider | Audio in | Audio out |
|---|---|---|
| Azure Cognitive Services | $4.0050.0× | — |
| Azure | $4.0050.0× | — |
Audio tokens are priced on a separate scale from text tokens, so these are not comparable with the text prices above. The multiplier compares each price with the same provider's text price for the same direction.
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.
Price history accumulates from each data sync; currently only 1 sample(s) (2026-10-19). Each future sync adds a point, and once accumulated a line is drawn here.