# Llama 4 Maverick 17B Instruct

> Llama 4 Maverick 17B Instruct is an open-weight language model from Meta, released on 5 Apr 2025. It accepts text and images and generates text, with a 1M-token context window and up to 8K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.24 per million input tokens and $0.97 per million output tokens (Amazon Bedrock), across 1 provider we track.

Source page: https://www.aimodel.directory/models/llama-4-maverick-17b-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/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Context window:** 1M (1,000,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Max output:** 8K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Knowledge cutoff:** Aug 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Input:** Text and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/us.meta.llama4-maverick-17b-instruct-v1:0.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Amazon Bedrock | $0.24 | $0.97 | – | 1M |
| Amazon Bedrock | $0.24 | $0.97 | – | 1M |

## FAQ

### What is the context window of Llama 4 Maverick 17B Instruct?

Llama 4 Maverick 17B Instruct has a context window of 1,000,000 tokens (1M) and can generate up to 8,192 tokens in a single response, according to models.dev.

### How much does the Llama 4 Maverick 17B Instruct API cost?

Llama 4 Maverick 17B Instruct is listed from $0.24 per million input tokens and $0.97 per million output tokens (Amazon Bedrock). Prices last verified 4 Oct 2026.

### Is Llama 4 Maverick 17B Instruct open source?

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

### When was Llama 4 Maverick 17B Instruct released?

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

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