Nvidia
Phi-4-Mini
Canonical ID:
nvidia/microsoft/phi-4-mini-instruct
Efficient model for low-latency assistance, extraction, and routine automation
Overview
- Provider
-
Nvidia
- Family
- phi-4-mini-instruct
- Release date
- 2024-12-01
- Last updated
- 2025-09-05
- Input modalities
- text, image, audio
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $0/1M
- Output
- $0/1M
- Cached input
- N/A
Context and output
- Context window
- 131,072
- Max output tokens
- 8,192
- Qualified ID
- nvidia/microsoft/phi-4-mini-instruct
Model Summary
Phi-4-Mini is a model listing in the Nvidia provider catalog. It is categorized under the phi-4-mini-instruct family.
The model supports text, image, audio modalities across input/output paths. Reported context capacity is 131,072. Pricing is listed at $0/1M input and $0/1M output.
More From Nvidia
Related models from the same provider catalog.
Nvidia
Active Speaker Detection
nvidia/nvidia/active-speaker-detection
Nvidia
bevformer
nvidia/nvidia/bevformer
Nvidia
BGE M3
nvidia/baai/bge-m3
Nvidia
ByteDance-Seed/Seed-OSS-36B-Instruct
nvidia/bytedance/seed-oss-36b-instruct
Nvidia
Codegemma 1.1 7b
nvidia/google/codegemma-1.1-7b
Nvidia
Codegemma 7b
nvidia/google/codegemma-7b
Nvidia
Codellama 70b
nvidia/meta/codellama-70b
Nvidia
Codestral 22b Instruct V0.1
nvidia/mistralai/codestral-22b-instruct-v0.1
Same Family: phi-4-mini-instruct
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
Phi-4-mini-instruct
github_models/microsoft/phi-4-mini-instruct
|
GitHub Models
|
128,000 | $0/1M | $0/1M |
Reasoning
Tools
|
|
Phi-4-mini-instruct
wandb/microsoft/Phi-4-mini-instruct
|
Weights & Biases
|
128,000 | $0.08/1M | $0.35/1M |
Reasoning
Tools
|