jishie

Phi-4

azure/phi-4 · family phi · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.

$0.22
Blended $/1M (3:1)
$0.125
Input $/1M
$0.5
Output $/1M
$0.63
1M in + 1M out
—
Cache read $/1M
#1804 of 7,708
Cheapest rank
Provider
Azure (azure)
Kind
text (outputs text)
Context
128,000 tokens
Max output
4,096 tokens
Capabilities
text

Same model, other providers

“Phi-4” is offered by 2 providers — cheapest-effective first. This one (Azure) is the cheapest.

ProviderInputOutputBlendedContext
Azure (this)$0.125$0.5$0.22128k
Azure Cognitive Services$0.125$0.5$0.22128k

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","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Azure models · model index · JSON