Llama 4 Scout 17B is Meta's efficient long-context model with 16 active experts (MoE), available free on GitHub Models.
https://models.github.ai/inference llama-4-scout-17b-16e Llama-4-Scout-17B-16E is listed for chat workloads and supports a 512K context window.
Check GitHub Models's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this llama listing on GitHub Models in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Llama-4-Scout-17B-16E | Check provider | 512K | OpenAI-style | 15 RPM, 150 RPD |
| Model | Provider | Context | Access |
|---|---|---|---|
| Phi-4 | GitHub Models | 131K | Free tier |
| 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 |
Llama-4-Scout-17B-16E is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Llama-4-Scout-17B-16E appears in the free model catalog for GitHub Models, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is llama-4-scout-17b-16e.
The listed free tier limit is 15 RPM, 150 RPD. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 512K tokens with up to 4K output tokens.
Llama 4 Scout 17B is Meta's efficient long-context model with 16 active experts (MoE), available free on GitHub Models. With a 512K context window — far beyond most free models — it can process entire novels, full code repositories, or multi-hour transcripts in a single request. The 17B total parameter footprint keeps inference fast and cost-effective, making it practical for retrieval-free document analysis and long-form summarization. Rate limits are 15 RPM and 150 requests per day with per-request output capped at 4K tokens. Fully OpenAI SDK-compatible and requires only a GitHub account.
For API keys, setup steps, and provider-level limits, see the GitHub Models provider page.