Phi 4
Provider: deepinfra ·
deepinfra/microsoft/phi-4 Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $0.07 |
| Output | $0.14 |
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$0.10
per month
Medium
10M in / 2000k out
$0.98
per month
Large
100M in / 20000k out
$9.80
per month
Context
- Input window
- 16,384 tokens
- Max output
- 16,384 tokens
Capabilities
- ⬜ Vision (image input)
- ✅ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Phi 4 with similar models
Qwen2.5 72B Instruct
deepinfra
$0.12 in
/ $0.39 out
Qwen2.5 7B Instruct
deepinfra
$0.04 in
/ $0.10 out
L3 8B Lunaris V1 Turbo
deepinfra
$0.04 in
/ $0.05 out
Mistral Small 24B Instruct 2501
deepinfra
$0.05 in
/ $0.08 out
MythoMax L2 13b
deepinfra
$0.08 in
/ $0.09 out
Qwen3 14B
deepinfra
$0.06 in
/ $0.24 out
Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.