Model Router API Pricing
As of October 10, 2026, Model Router costs $0.14 per 1M input tokens and $0 per 1M output tokens from Azure OpenAI, the lowest of 2 providers. It has a 200,000-token context window and returns up to 32,768 tokens per response.
azure/model-router.- Input
- $0.14 / 1M tokens
- Output
- $0 / 1M tokens
- Context window
- 200,000 tokens
- Max output
- 32,768 tokens
- Providers
- 2
- Added to LiteLLM
- February 2026
Model Router pricing by provider
3 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Azure OpenAI | azure/model-router | $0.14 | $0 | 200K |
| Azure AI Foundry | azure_ai/model_router | $0.14 | $0 | 200K |
| Azure AI Foundry | azure_ai/model-router | $0.14 | $0 | 200K |
What Model Router costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Azure OpenAI | $0.28 |
| Azure AI Foundry | $0.28 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Azure OpenAI | $1.40 |
| Azure AI Foundry | $1.40 |
Model Router features
- Image input
Use Model Router with LiteLLM
Call Model Router through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="azure/model-router",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: model-router
litellm_params:
model: azure/model-router
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "model-router",
"messages": [{"role": "user", "content": "Hello!"}]
}'Model Router FAQ
How much does Model Router cost?
Model Router costs $0.14 per 1M input tokens and $0 per 1M output tokens from Azure OpenAI, the lowest of 2 providers.
What is the context window of Model Router?
Model Router has a 200,000-token context window and returns up to 32,768 tokens per response.
Which providers offer Model Router?
Model Router is available from 2 providers through LiteLLM: Azure OpenAI and Azure AI Foundry.
How do I call Model Router with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="azure/model-router", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Model Router support?
Model Router supports image input.
When did LiteLLM add Model Router?
Model Router was added to LiteLLM's model price file in February 2026.
Is Model Router being deprecated?
Azure OpenAI lists a deprecation date of May 20, 2027 for azure/model-router.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/
- azure.microsoft.com/en-us/pricing/details/ai-foundry-models/aoai/
LiteLLM docs: Azure OpenAI, Azure AI Foundry.
Provider pages: Azure OpenAI, Azure AI Foundry.
