Model prices / Microsoft / Phi 4 Mini
Phi 4 MiniOpen weights
Microsoft · released 2025-02-26
No price from the maker itself is on record for Phi 4 Mini. The lowest of 1 providers is NanoGPT: $0.17 per 1M input tokens and $0.68 per 1M output tokens (as of 2026-11-12). Context window: 128K tokens, up to 16.4K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestphi-4-mini-instruct | $0.17 | $0.68 | $0.085 | Lowest | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Compact GPT model for low-latency assistance and high-volume workloads
Description from models.dev.
Specs
- Type
- Text
- Context
- 128K
- Max output
- 16.4K
- Input
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- No
- Structured output
- No
- Knowledge cutoff
- 2024-06
- Open weights
- Yes
- Released
- 2025-02-26
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.