Llama 4 Maverick 17B is Meta's high-expert-count MoE model with 128 active experts, available for free on GitHub Models.
https://models.github.ai/inference llama-4-maverick-17b-128e Llama-4-Maverick-17B-128E is listed for chat workloads and supports a 256K 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-Maverick-17B-128E | Check provider | 256K | OpenAI-style | 10 RPM, 50 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-Maverick-17B-128E is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Llama-4-Maverick-17B-128E 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-maverick-17b-128e.
The listed free tier limit is 10 RPM, 50 RPD. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 256K tokens with up to 4K output tokens.
Llama 4 Maverick 17B is Meta's high-expert-count MoE model with 128 active experts, available for free on GitHub Models. Despite its compact 17B active parameter footprint, the large expert pool gives it broad knowledge coverage — making it a strong general-purpose chat and instruction-following model that rivals much larger dense architectures. The free tier limits output to 4K tokens per request with 10 RPM and 50 requests per day, so it is best suited for interactive chat and short-form generation rather than long-form writing. Fully OpenAI SDK-compatible; requires only a GitHub account to start using.
For API keys, setup steps, and provider-level limits, see the GitHub Models provider page.