Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for meta-llama

Meta: Llama 4 Scout

meta-llama/llama-4-scout

Model weights
Compare

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 (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens.

Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

Modalities

In / Out Price

$0.10 / $0.30per 1M

Context

1M

Released

Apr 5, 2025

Knowledge Cutoff

Aug 2024

Compare

About Meta: Llama 4 Scout

OpenRouter makes Meta: Llama 4 Scout by Meta Llama available through a unified, OpenAI-compatible API using the model ID meta-llama/llama-4-scout. Requests can be routed across 4 providers, including DeepInfra, Groq, NovitaAI and Google Vertex, with automatic failover when an endpoint is unavailable.

Meta: Llama 4 Scout accepts text and images and returns text. It has a 1,310,720-token context window and a maximum output of 16,384 tokens.

On OpenRouter, Meta: Llama 4 Scout costs $0.10/M input tokens and $0.30/M output tokens. It was released on April 5, 2025; its knowledge cutoff is August 31, 2024.

More models from Meta Llama

  • Llama Guard 4 12B
  • Llama 4 Maverick
  • Llama 3.3 70B Instruct

Frequently asked questions

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 (text and image) and multilingual output (text and code) across 12 supported languages.

Llama 4 Scout costs $0.10/M input tokens and $0.30/M output tokens.

Llama 4 Scout has a 1,310,720 token context window. It supports up to 16,384 completion tokens.

The Llama 4 Scout endpoint shown on this page does not accept tools, so function calling is unavailable there. It also supports structured outputs via a JSON schema in response_format.

Llama 4 Scout accepts text and images as input and returns text.

Llama 4 Scout is served by 4 providers on OpenRouter: DeepInfra, Groq, NovitaAI and Google Vertex. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Llama 4 Scout was released on April 5, 2025. Its knowledge cutoff is August 31, 2024.

ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQ

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

$0.10$0.30--0.53s4 tps
99.69%
$0.11$0.34$0.0550.44s5 tps
99.77%
$0.18$0.59--0.90s2 tps
98.87%
$0.25$0.70--0.73s16 tps
99.76%

Throughput

16tok/s

P50, best across providers

Latency

0.44s

P50, best provider

Uptime (3d)

100.00%

Availability (3d)

99.91%

Availability over the last 3 days

Last 72 hours
Availability 99.91%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.87%
Without Routing
58.46%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://websim.com/
Websim Builder
new
7.53Btokens
2.
Favicon for https://esmed2021.org/
ESMED Email App V3
new
753Mtokens
3.
Favicon for https://api.forestcityrealty.com/
Advantage Archive Backend
new
547Mtokens
4.
Favicon for https://godmod3.ai/
G0DM0D3-pliny
new
425Mtokens
5.
Favicon for https://sobes.tech/
Sobes Overlay
new
313Mtokens