Weights & Biases
Phi-4-mini-instruct
Canonical ID:
wandb/microsoft/Phi-4-mini-instruct
Phi-4-mini-instruct is listed under Weights & Biases in LLM Directory with pricing, context limits, modalities, and capability metadata for quick comparison.
Overview
- Provider
-
Weights & Biases
- Family
- phi-4-mini-instruct
- Release date
- 2024-12-11
- Last updated
- 2024-12-11
- Input modalities
- text
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $0.08/1M
- Output
- $0.35/1M
- Cached input
- N/A
Context and output
- Context window
- 128,000
- Max output tokens
- 4,096
- Qualified ID
- wandb/microsoft/Phi-4-mini-instruct
Model Summary
Phi-4-mini-instruct is a model listing in the Weights & Biases provider catalog. It is categorized under the phi-4-mini-instruct family.
The model supports text modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0.08/1M input and $0.35/1M output.
More From Weights & Biases
Related models from the same provider catalog.
Weights & Biases
Beam 1.0 501B A23B
wandb/reflection/Beam-1.0-501B-A23B
Weights & Biases
DeepSeek-R1-0528
wandb/deepseek-ai/DeepSeek-R1-0528
Weights & Biases
DeepSeek-V3-0324
wandb/deepseek-ai/DeepSeek-V3-0324
Weights & Biases
DeepSeek V3.1
wandb/deepseek-ai/DeepSeek-V3.1
Weights & Biases
DeepSeek V4.1 Flash
wandb/deepseek-ai/DeepSeek-V4.1-Flash
Weights & Biases
DeepSeek V4 Flash 0731
wandb/deepseek-ai/DeepSeek-V4-Flash-0731
Weights & Biases
DeepSeek V4 Pro 0813
wandb/deepseek-ai/DeepSeek-V4-Pro-0813
Weights & Biases
Gemma 4 26B A4B
wandb/google/gemma-4-26B-A4B-it
Same Family: phi-4-mini-instruct
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
Phi-4-Mini
nvidia/microsoft/phi-4-mini-instruct
|
Nvidia
|
131,072 | $0/1M | $0/1M |
Reasoning
Tools
|
|
Phi-4-mini-instruct
github_models/microsoft/phi-4-mini-instruct
|
GitHub Models
|
128,000 | $0/1M | $0/1M |
Reasoning
Tools
|