Phi 4 Multimodal Instruct
Phi-4-multimodal-instructPricing
List prices at Azure AI Foundry, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.08 | $0.32 |
What it costs a month
At Azure AI Foundry list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$48.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$49.92
- Coding agent1,000 requests a day, 40K in / 2K out$115
- Overnight batch20,000 requests a day, 4K in / 0.4K out$269
Where to run it
1 host serve Phi 4 Multimodal Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Azure AI FoundryCloud Phi-4-multimodal-instruct | $0.08 / $0.32 Retires 17 Jan 2027 | Phi-4-multimodal-instruct | Retires 17 Jan 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
- TextImagesAudio
- Produces
- Text
- Features
- Audio input
- Open weights
- License: MITRuntimes: Ollama, llama.cpp, vLLM
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 AI Foundry.
Smaller Microsoft models
No cheaper Microsoft 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 AI Foundry's API.
from litellm import completion
response = completion(
model="azure_ai/Phi-4-multimodal-instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Phi 4 Multimodal Instruct cost?
On Azure AI Foundry, Phi 4 Multimodal Instruct costs $0.08 per million input tokens and $0.32 per million output tokens.
Which APIs offer Phi 4 Multimodal Instruct?
Phi 4 Multimodal Instruct runs on 1 API: Azure AI Foundry.
What is Phi 4 Multimodal Instruct's context window?
131K tokens, with up to 4K tokens in one reply.
Is Phi 4 Multimodal Instruct being retired?
Azure AI Foundry retires it on 17 Jan 2027. No API serves it after that.
What are cheaper alternatives to Phi 4 Multimodal Instruct?
Models that cost less and keep most of what it can do: Qwen3.6 35B A3B on Sail (2% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Phi 4 Multimodal Instruct's API model id?
Use Phi-4-multimodal-instruct with Azure AI Foundry.
Sources
Raw catalog entry for Phi-4-multimodal-instruct on Azure AI Foundry
{
"deprecation_date": "2027-01-17",
"deprecation_source": "https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement",
"successor_model": "microsoft--phi-4",
"input_cost_per_audio_token": 0.000004,
"input_cost_per_token": 8e-8,
"litellm_provider": "azure_ai",
"max_input_tokens": 131072,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 3.2e-7,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supports_audio_input": true,
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_vision": true
}