Meta: Llama 4 Scout
Analysis Summary
Meta Llama 4 Scout is a multimodal model from Meta with an exceptional 10M token context window, supporting text and image inputs alongside tool use and function calling. Its MMLU-Pro score of 0.752 and GPQA of 0.587 reflect solid general reasoning, and its IFBench score of 0.395 suggests reasonable instruction-following for structured tasks.
For businesses, the standout feature is the context window: it can hold entire codebases, lengthy contracts, or large document sets in a single call. This makes it particularly useful for long-document analysis, retrieval-augmented generation, and content workflows where context depth matters. Its coding index of 6.7 is modest, so it is not the primary choice for software engineering tasks.
At $0.10 input and $0.30 output per million tokens, it offers strong value for its context capacity. Teams that regularly work with very long documents or need to consolidate large information sets will find it a practical and cost-effective option.
Assessed June 17, 2026
Editorial notes
Meta Llama 4 Scout offers a 10M token context window with vision, tool use, and function calling at $0.10 input per million tokens, making it a strong choice for long-document business workflows.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Meta: Llama 4 Scout compares
Meta: Llama 4 Scout ranks #223 of 382 AI models we track for overall intelligence, #105 of 111 for coding, #269 of 293 for agentic tasks. Its 10M-token context window is larger than 100% of the models we list. At $0.10 per million input tokens it is cheaper than 67% of comparable models.
About Meta: Llama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Meta: Llama 4 Scout stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
meta-llama/llama-4-scout
|
| Provider | meta-llama |
| Model Family | Llama 4 |
| Release Date | April 5, 2025 |
| Context Length | 10,000,000 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000100 |
| Output | $0.30 | $0.000300 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Meta: Llama 4 Scout
How much does Meta: Llama 4 Scout cost?
Meta: Llama 4 Scout costs $0.10 per million input tokens and $0.30 per million output tokens.
What is the context window of Meta: Llama 4 Scout?
Meta: Llama 4 Scout has a context window of 10,000,000 tokens (10M).
Is Meta: Llama 4 Scout good for coding?
On our coding benchmark index, Meta: Llama 4 Scout ranks #105 of 111 models, placing it in the broader range of the field for code generation and debugging.
What can Meta: Llama 4 Scout do?
Meta: Llama 4 Scout supports image/vision input, tool use, and function calling.
Who created Meta: Llama 4 Scout?
Meta: Llama 4 Scout is developed by Meta and was released on April 5, 2025.
