Should you use Phi-4?
Phi-4 is listed for reasoning workloads and supports a 131K context window.
Use it when GitHub Models's free tier is enough for evaluation, demos, or light production traffic.
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
https://models.github.ai/inference Phi-4 Phi-4 is listed for reasoning workloads and supports a 131K context window.
Use it when GitHub Models's free tier is enough for evaluation, demos, or light production traffic.
We only found this phi-4 listing on GitHub Models in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Phi-4 | Free tier | 131K | OpenAI-style | See provider page |
| Model | Provider | Context | Access |
|---|---|---|---|
| Mistral Large (24.11) | GitHub Models | 131K | Free tier |
| AI21 Jamba 1.5 Large | GitHub Models | 256K | Free tier |
| gpt-5 | GitHub Models | 200K | Free tier |
| gpt-4.1 | GitHub Models | 1.0M | Free tier |
| gpt-4.1-mini | GitHub Models | 1.0M | Free tier |
Phi-4 is tagged for reasoning in this catalog and works with OpenAI-compatible client libraries.
Phi-4 is listed with free API access on GitHub Models, subject to the provider's quota and account policy.
The model ID shown in this catalog is Phi-4.
The listed context window is 131K tokens with up to 4K output tokens.
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
For API keys, setup steps, and provider-level limits, see the GitHub Models provider page.