Phi-4-multimodal
azure/phi-4-multimodal · family phi · in: text, image, audio → out: text · price provider-declared (via models.dev). Capabilities: text image audio.
$0.14
Blended $/1M (3:1)
$0.08
Input $/1M
$0.32
Output $/1M
$0.40
1M in + 1M out
—
Cache read $/1M
#1228 of 7,708
Cheapest rank
- Provider
- Azure (
azure) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 4,096 tokens
- Capabilities
- text image audio
Same model, other providers
“Phi-4-multimodal” is offered by 2 providers — cheapest-effective first. This one (Azure) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Azure (this) | $0.08 | $0.32 | $0.14 | 128k |
| Azure Cognitive Services | $0.08 | $0.32 | $0.14 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Azure and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"phi-4-multimodal","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):