Meta model product
Llama 4 Scout
Llama 4 Scout is a natively multimodal model capable of processing both text and images.
Updated Aug 12, 2026. Default version: Llama 4 Scout
LLMBoard score14.1Llama 4 Scout
Coverage80%11 benchmark families
Context window10MTokens
Official input priceN/AOfficial price unavailable
Llama 4 Scout Specifications
Technical details for the model's default version.
- Version
- Llama 4 Scout
- Released
- Apr 5, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 109B
- Context window
- 10M
- Max output
- 10M
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Llama 4 Community License Agreement
Llama 4 Scout Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Llama 4 Scout Benchmark Results
Benchmark scores for Llama 4 Scout.
Llama 4 Scout Arena Results
Preference and agent-evaluation results for the default version.
| vision style control | overall | 106 | 1127.9 | 6,485 | N/A | |
| vision | overall | 107 | 1118.3 | 6,485 | N/A | |
| text style control | overall | 229 | 1322.4 | 30,400 | N/A | |
| text | overall | 243 | 1280.3 | 30,400 | N/A |
Llama 4 Scout Runtime Performance
Provider-specific output speed and catalog latency for Llama 4 Scout. Runtime does not affect the capability score.
| Groq | 776.1 tok/s | 1.08 s | 10M | 10M | |
| Lambda | 139.7 tok/s | 0.43 s | 10M | 10M | |
| Fireworks | 116.1 tok/s | 0.53 s | 10M | 10M | |
| Together | 106.9 tok/s | 0.54 s | 10M | 10M | |
| DeepInfra | 76.1 tok/s | 0.31 s | 10M | 10M | |
| Novita | 69.82 tok/s | 0.85 s | 10M | 10M |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Llama 4 Scout Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.08 input, $0.30 output per 1M via Helicone
- Tracked offerings
- 3
| Helicone | llama-4-scout | global | $0.08 | $0.30 | 131.1K | |
| NanoGPT | meta-llama/llama-4-scout | global | $0.085 | $0.46 | 328K | |
| OpenRouter | meta-llama/llama-4-scout | global | $0.10 | $0.30 | 1.3M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Llama 4 Scout Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Llama 4 Scout | 14.1 | 109B | 10M | 10M | No | Llama 4 Community License Agreement |
What is Llama 4 Scout?
Key information about Llama 4 Scout and its available data.
Llama 4 Scout is a natively multimodal model capable of processing both text and images. It features a 17 billion activated parameter (109B total) mixture-of-experts (MoE) architecture with 16 experts, supporting a wide range of multimodal tasks such as conversational interaction, image analysis, and code generation.
The model includes a 10 million token context window.
Data as of 2026-08-11.
Llama 4 Scout vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Llama 4 Scout
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
ME
Llama 3.1 70B
Meta
ME
Llama 3.2 90B
Meta
ME
Llama 3.3 70B
Meta
ME
Llama 3.1 405B
Meta
ME
Llama 4 Maverick
Meta
ME
Llama 3.2 3B
Meta
FAQ
Common questions about Llama 4 Scout.
When was Llama 4 Scout released?
Llama 4 Scout's default version was released on Apr 5, 2025.
How much does Llama 4 Scout cost?
No official standard PAYG price is currently available for Llama 4 Scout. The lowest tracked third-party offer starts at $0.08 input and $0.30 output via Helicone.
Who created Llama 4 Scout?
Llama 4 Scout was created by Meta.
What is the context window for Llama 4 Scout?
The default version has a 10M token context window.
Is Llama 4 Scout open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Llama 4 Scout?
3 provider offerings are linked to the default version.
What models should I compare Llama 4 Scout with?
Nearby ranked alternatives include QvQ 72B, Qwen2.5 32B, GPT-4-Turbo.