Microsoft: Phi 4 Mini Instruct
Released Oct 17, 2025Try it on:
Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...
Best overall rank
-
Across all subsets · overall
Total arena votes
0
Across 0 (subset, category) entries
Providers on OR
0
None yet
First seen
-
Awaiting first snapshot
Trend
No snapshot history yet - trends appear after the first daily refresh.
Pricing
Per token
- Input (per 1M)
- $0.080
- Output (per 1M)
- $0.350
- Cache Read (per 1M)
- $0.080
Capabilities
Modality
text->textContext
131K tokens
Tokenizer
Other
Max output
128K tokens
Moderation
Unmoderated
Hugging Face
Supported parameters
frequency_penalty
max_tokens
presence_penalty
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
top_k
top_p
Providers
No provider endpoint data yet.
Per-category ranks
No leaderboard entries for this model.