Microsoft · General language
Phi-3-mini-128k-instruct
The model that launched the SLM category; still one of the most downloaded Phi checkpoints for offline/edge use, but on Azure Phi-4-mini-instruct is cheaper and stronger.
Open weights · Permissive (Apache, MIT, OpenMDW) · Data checked September 6, 2026 · Not a hands-on evaluation
Model ID Phi-3-mini-128k-instruct
- Parameters
- 3.8B
- Architecture
- Not recorded
- Context window
- 131,072 tokensMaximum input
- Max output
- 4,096 tokensPer response
- Input price
- $0.13 per 1M tokens
- Output price
- $0.52 per 1M tokens
- Cached input
- Not published
- Blended price
- $0.2275 per 1M tokens3:1 input to output
- Knowledge cutoff
- 2023-10
- Released
- 2024-04-22
- Status
- deprecated
- Size band
- Up to 4B
License and openness
Phi-3-mini-128k-instruct is released under the MIT. This is a permissive license. It generally allows use, modification and redistribution, including commercial use, subject to attribution and notice requirements. License terms can change between versions; confirm the text published with the weights you download.
Capabilities
| Input modalities | text |
|---|---|
| Output modalities | text |
What it is for
At a three-to-one input-to-output ratio, Phi-3-mini-128k-instruct costs $0.23 per million tokens blended. A workload of one million input and 330,000 output tokens per day would run about $9.05 per month at list price, before caching or batch discounts.
Cost at list price
| Input | $0.13 per 1M tokens |
|---|---|
| Output | $0.52 per 1M tokens |
| Cached input | Not published |
| Blended, 3:1 | $0.2275 per 1M tokens |
Sources
- Source: prices.azure.com ↗
- Microsoft pricing ↗
- API docs ↗
- Full reference record for Phi-3-mini-128k-instruct ↗
- Microsoft in the reference ↗
Sources checked September 6, 2026. Specifications and prices change without notice; confirm against the provider before you commit.
Other open-weight models from Microsoft
- MAI-DS-R1 · 671B total · 37B active
- Phi-4 · 14.7B
- Phi-4-mini-instruct · 3.8B
- Phi-4-multimodal-instruct · 5.6B
- Phi-4-reasoning · 14.7B
- Phi-4-reasoning-plus · 14.7B
- Phi-4-mini-reasoning · 3.8B
- Phi-4-mini-flash-reasoning · 3.8B
- Phi-4-Reasoning-Vision-15B · 15B
- Phi-mini-MoE-instruct · 7.6B total · 2.4B active
- Phi-tiny-MoE-instruct · 3.8B total · 1.1B active
- Phi-Ground-Any · Not recorded