Phi-3.5 Mini Instruct is Microsoft's efficient 3.8B open model, available free on Hugging Face's Serverless Inference API.
https://router.huggingface.co/v1 phi-3-5-mini-instruct Phi-3.5-mini-instruct is listed for chat workloads and supports a 128K context window.
Check Hugging Face's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this Phi-3.5-mini-instruct listing on Hugging Face in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Phi-3.5-mini-instruct | Check provider | 128K | Native | Credit-metered |
| Model | Provider | Context | Access |
|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct | Hugging Face | 128K | Free tier |
| gemma-3-4b-it | Hugging Face | 131K | Free tier |
| Qwen2.5-Coder-7B-Instruct | Hugging Face | 131K | Free tier |
| Qwen2.5-7B-Instruct | Hugging Face | 131K | Free tier |
| Mistral-7B-Instruct-v0.3 | Hugging Face | 32K | Check provider |
Phi-3.5-mini-instruct is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Phi-3.5-mini-instruct appears in the free model catalog for Hugging Face, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is phi-3-5-mini-instruct.
The listed free tier limit is Credit-metered. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 4K output tokens.
Phi-3.5 Mini Instruct is Microsoft's efficient 3.8B open model, available free on Hugging Face's Serverless Inference API. Despite its small size, it delivers surprisingly strong reasoning and instruction-following for lightweight tasks, with a 128K context window that belies its compact footprint. Ideal for resource-constrained applications, simple Q&A, and as a baseline for model evaluation. Uses Hugging Face's native API format; approximately 1,000 requests per day on the free tier. Registration required.
For API keys, setup steps, and provider-level limits, see the Hugging Face provider page.