← All models
microsoft/phi-4
Phi-4
RoutableGuaranteed 30%+ savingsMicrosoft
Phi-4 is a compact open-weight model from Microsoft Research, efficient for text tasks. Note: latency can be high under load on shared Azure Foundry capacity.
chatopen-weightazure-foundry
Context
16,384
Input / 1M
$0.13
Output / 1M
$0.5
Providers
| Provider | Input / 1M | Output / 1M | Context | Max output | RPM | TPM | TPD | Status |
|---|---|---|---|---|---|---|---|---|
| Azure AI Foundry (seldon-mvp-resource) | $0.13 | $0.5 | 16,384 | 4,096 | 7,000 | 7,000,000 | — | Routable |
Quickstart
curl http://api.seldon-ai.com/v1/chat/completions \
-H 'Authorization: Bearer $SELDON_API_KEY' \
-H 'Content-Type: application/json' \
# Phi-4 can be slow under load on shared Azure Foundry capacity; rate-limit headers may be absent.
-d '{
"model": "microsoft/phi-4",
"messages": [{"role": "user", "content": "Hello!"}],
"max_tokens": 256
}'