Phi-3.5-mini-instruct: API Pricing, Context Window & Benchmarks
Phi-3.5-mini-instruct is a language model from Microsoft, released in August 2024.
Phi-3.5-mini-instruct is a 3.8B-parameter model that supports up to 128K context tokens, with improved multilingual capabilities across over 20 languages. It underwent additional training and safety post-training to enhance
Phi-3.5-mini-instruct benchmarks
Rankings
Quality Tracker
Phi-3.5-mini-instruct Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Jul 20 2026Phi-3.5-mini-instruct pricing
Providers
Phi-3.5-mini-instruct starts at $0.100 per million input tokens and $0.100 per million output tokens via Azure.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Azure | $0.100 | $0.100 | 128.0K/128.0K | —/0.52 | 23/— | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
Phi-3.5-mini-instruct model size
Phi-3.5-mini-instruct has 3.8 billion parameters and was trained on 3.4 trillion tokens. See how it compares to other models in the same parameter range.
Phi-3.5-mini-instruct context window
Input and output token limits for Phi-3.5-mini-instruct, plus how it ranks on long-context understanding.
Phi-3.5-mini-instruct API
Available from the model provider
Phi-3.5-mini-instruct has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationPhi-3.5-mini-instruct latency
Phi-3.5-mini-instruct time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Phi-3.5-mini-instruct examples
Recent arena outputs from Phi-3.5-mini-instruct, picked from the highest-ranked matchups.
Phi-3.5-mini-instruct license
Phi-3.5-mini-instruct is released under the MIT license, which permits commercial use, has 3.8B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 3.8B
MIT License - allows commercial use
Phi-3.5-mini-instruct resources
Official sources for Phi-3.5-mini-instruct: api documentation, paper or system card, official launch post.
Phi-3.5-mini-instruct vs other models
The most-compared alternatives to Phi-3.5-mini-instruct are Mistral NeMo Instruct, Hermes 3 70B, Llama 4 Scout. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Phi-3.5-mini-instruct
Models ranked just above and below Phi-3.5-mini-instruct by LLM Stats score.
FAQ
Common questions about Phi-3.5-mini-instruct.