Phi 4 Mini Instruct
Provider: wandb ·
wandb/microsoft/Phi-4-mini-instruct Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $8000 |
| Output | $35.0k |
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$15.0k
per month
Medium
10M in / 2000k out
$150.0k
per month
Large
100M in / 20000k out
$1500.0k
per month
Context
- Input window
- 128,000 tokens
- Max output
- 128,000 tokens
Capabilities
- ⬜ Vision (image input)
- ⬜ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Phi 4 Mini Instruct with similar models
Gpt Oss 120b
wandb
$15.0k in
/ $60.0k out
Gpt Oss 20b
wandb
$5000 in
/ $20.0k out
Qwen3 235B A22B Instruct 2507
wandb
$10.0k in
/ $10.0k out
Qwen3 235B A22B Thinking 2507
wandb
$10.0k in
/ $10.0k out
Llama 3.1 8B Instruct
wandb
$22.0k in
/ $22.0k out
Llama 4 Scout 17B 16E Instruct
wandb
$17.0k in
/ $66.0k 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.