Model Router
model-routerPricing
List prices at Azure OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.14 | $0.00 |
What it costs a month
At Azure OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$42.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$67.20
- Coding agent1,000 requests a day, 40K in / 2K out$168
- Overnight batch20,000 requests a day, 4K in / 0.4K out$336
Where to run it
2 hosts serve Model Router. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Azure OpenAICloud model-router | $0.14 / $0.00 Retires 20 May 2027 | model-router | Retires 20 May 2027 |
Azure AI FoundryCloud model-router | $0.14 / $0.00 Retires 20 May 2027 | model-router | Retires 20 May 2027 |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Azure AI Foundry | |||||||
| Alias model_router | $0.14 / $0.00 Retires 20 May 2027 | model_router | Retires 20 May 2027 | ||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Azure OpenAI.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 2% less
- 2% less
- 29% less
- 29% less
Call it
Using Azure OpenAI's API.
from litellm import completion
response = completion(
model="azure/model-router",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Model Router cost?
On Azure OpenAI, Model Router costs $0.14 per million input tokens.
Which APIs offer Model Router?
Model Router runs on 2 APIs: Azure OpenAI and Azure AI Foundry.
What is Model Router's context window?
200K tokens, with up to 33K tokens in one reply.
Is Model Router being retired?
Azure AI Foundry and Azure OpenAI retire it on 20 May 2027. No API serves it after that.
What are cheaper alternatives to Model Router?
Models that cost less and keep most of what it can do: Qwen3.6 35B A3B on Sail (2% less).
What is Model Router's API model id?
Use model-router with Azure OpenAI.
Sources
Raw catalog entry for model-router on Azure OpenAI
{
"comment": "The flat $0.14 per M input tokens is the router's own fee, the routed model is priced on top of it",
"deprecation_date": "2027-05-20",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
"input_cost_per_token": 1.4e-7,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 0,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/model-router/",
"supports_vision": true
}