Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • Enterprise
  • Labs

Company

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

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

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
1.3M
Released
Apr 5, 2025
Knowledge Cutoff
Aug 2024
Compare
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

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 Floor (cheapest).

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.

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.

API

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.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Latency / throughput
$0.10$0.300.49s57 tps
99.76%
$0.25$0.70----
--
Priority
$0.15$0.450.43s58 tps
89.79%
Not used in Standard routing:Why these endpoints are not used
Flex
$0.08$0.241.56s21 tps
67.53%
Throughput
58tok/s

P50, best across providers

Latency
0.43s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
97.46%

Availability over the last 3 days

Last 72 hours
Availability 97.46%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
96.10%
Without Routing
79.84%

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 provider routing options.

1.
Favicon for https://websim.com/
Websim Builder
new
6.64Btokens
2.
Favicon for https://github.com/verifier-meta-agents/verifier-meta-agents
VerifierContractBench
new
495Mtokens
3.
Favicon for https://github.com/saurabh-tripathi/verifier-meta-agents
VerifierContractBench
new
464Mtokens
4.
Favicon for https://mud-server.local/
MUD Adventure Generator
new
409Mtokens
5.
Favicon for https://fakecorp.internal/research
failure-classifier
new
275Mtokens

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.

Yes. Llama 4 Scout accepts tools and tool_choice for function calling. 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 2 providers on OpenRouter: DeepInfra 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.