browse by creator
Microsoft models.
Access 1 model from Microsoft through the Impossibl API, including Phi-4. Compare API pricing, context windows, and capabilities.
filter by model type, supported inputs, and context window. select two or three models to compare specifications and estimate the same workload.
- Phi-4
microsoft/phi-4
Phi-4 is a text generation model from Microsoft, available through the Impossibl API. Its published context window is 16,000 tokens. The advertised input rate is $0.125 per million input tokens. The advertised output rate is $0.50 per million output tokens.
MicrosoftText generation
- context
- 16ktokens
- input price
- $0.125/1m tokens
- output price
- $0.50/1m tokens
frequently asked questions
Which Microsoft models are available through Impossibl?
The directory lists 1 model from Microsoft available through the Impossibl API, including Phi-4. Open each model page for its API identifier, capabilities, and current pricing.
How much do Microsoft models cost?
Microsoft model prices vary by model and usage. All rates below are published base API rates in USD. For token-priced models, published input rates start at $0.125 per million input tokens. Published output rates start at $0.50 per million output tokens. Input and output minima may refer to different models. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid.
What context windows do Microsoft models support?
Among Microsoft models with a published limit on Impossibl, the largest context window is 16,000 tokens, listed for Phi-4. Context limits vary by model and are separate from maximum output limits.
What inputs and capabilities do Microsoft models support?
Available model types include text generation. Published input support includes text; support varies by model. Tool calling is published as unsupported for 1 model.
How do I use Microsoft models through an API?
Use the exact model identifier from the model page with the Impossibl API. For example, select microsoft/phi-4 with /v1/chat/completions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request.