Skip to content
OpenSmartRoute
All vendors
Microsoft

Vendor

Microsoft models

2 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.

Models

2

0 routable here

Cheapest (blended)

$0.09

Phi 4

Median list price

$0.35

3:1 input to output per 1M tokens

Strongest

-

no published benchmarks

Every Microsoft model

Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.

ModelReleasedContextInput / 1MOutput / 1MIntelligenceCapabilities
Phi 4microsoft/phi-4Jan 10, 202516K$0.07$0.14-
open weights
WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22bApr 16, 202466K$0.62$0.62-
open weights

Frequently asked

What is the cheapest Microsoft model?
Phi 4 at $0.07 per 1M input tokens and $0.14 per 1M output tokens (vendor list price).
Which Microsoft model has the largest context window?
WizardLM-2 8x22B accepts 66K tokens of context.
How do I route to Microsoft models with OpenSmartRoute?
Declare a target in targets.yaml with metadata.model set to the catalogue id (for example microsoft/phi-4); the router scores it against every other target on cost, quality, latency and your policies for each request.

Route Microsoft with everything else

OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Microsoft flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.