# Llama 4 Maverick 17B Instruct Usage, Cost & Rank | OpenCode Data

> Llama 4 Maverick 17B Instruct costs $0.27 per 1M input tokens and $0.85 per 1M output tokens.

Open multimodal Llama for strong reasoning with efficient everyday serving

- Page: https://opencode.ai/data/meta/llama-4-maverick-17b-instruct
- JSON: https://opencode.ai/data/meta/llama-4-maverick-17b-instruct.json
- Model ID: meta/llama-4-maverick-17b-instruct
- Lab: Meta

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 1M |
| Max output | 16K |
| Knowledge cutoff | 2024-08 |
| Release date | 2025-04-05 |
| Input modalities | text, image |
| Output modalities | text |
| Reasoning | No |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct) |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.27 | $0.85 | - | - |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| Aider Polyglot | 15.6 | percent correct | https://aider.chat/docs/leaderboards/ |
| SWE-Bench Pro | 5.24 | resolve rate | https://labs.scale.com/leaderboard/swe_bench_pro_public |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.