# Groq-Llama-4-Maverick-17B-128E-Instruct

> Groq-Llama-4-Maverick-17B-128E-Instruct is an open-weight language model from Meta, released on 5 Apr 2025. It accepts text and generates text, with a 128K-token context window and up to 4K output tokens per response.

Source page: https://www.aimodel.directory/models/groq-llama-4-maverick-17b-128e-instruct
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Meta
- **Release date:** 5 Apr 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Max output:** 4K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llama/models/groq-llama-4-maverick-17b-128e-instruct.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Llama API | Free | Free | – | 128K |

## FAQ

### What is the context window of Groq-Llama-4-Maverick-17B-128E-Instruct?

Groq-Llama-4-Maverick-17B-128E-Instruct has a context window of 128,000 tokens (128K) and can generate up to 4,096 tokens in a single response, according to models.dev.

### Is Groq-Llama-4-Maverick-17B-128E-Instruct open source?

Groq-Llama-4-Maverick-17B-128E-Instruct is an open-weight model. Check the license terms before commercial use.

### When was Groq-Llama-4-Maverick-17B-128E-Instruct released?

Meta released Groq-Llama-4-Maverick-17B-128E-Instruct on 5 Apr 2025, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Groq-Llama-4-Maverick-17B-128E-Instruct", https://www.aimodel.directory/models/groq-llama-4-maverick-17b-128e-instruct