LLM Reference

Llama 4 Scout 17B-16E Instruct

Released
2025-04-05
Last refreshed
2026-07-09
Status
Researched 64d ago
Open weightsCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Llama 4 Scout 17B-16E Instruct is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 10m context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Llama 4
Released
2025-04-05
Context
10m
Parameters
109B (17B active)
Architecture
Mixture of Experts
Knowledge cutoff
2024-08
Specialization
general
Openness
Open weights
License
Llama 4 CommunityCommercial use: conditional
Weights
Unknown
Code
Unknown
Training
Pretrained
Created by

Large-scale open-source AI for social technologies.

Menlo Park, California, United States
Founded 2013
Website
Pricing
Output / 1M
$0.220
Input / 1M
$0.170

Cheapest of 12 routes · AWS Bedrock

About

Meta's Llama 4 Scout is a 17-billion parameter mixture-of-experts model with 16 expert routing. Optimized for efficient inference on edge and cloud environments with strong multi-turn conversation capabilities. Available on Cloudflare Workers AI.

Llama 4 Scout 17B-16E Instruct is an open-weight model in the Llama 4 family. The structured metadata tracks a 10m-token context window, multimodal input, and structured outputs. This page tracks provider routes through Cloudflare Workers AI, OpenRouter, Together AI, and 9 more, with the cheapest tracked route listed at $0.08 input and $0.3 output per 1M tokens. Headline tracked benchmarks include Chatbot Arena 1295.0, τ-bench 62.3, and Massive Multi-discipline Multimodal Understanding 69.4.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ B

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ A

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 12

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
AWS Bedrock$0.170$0.220
Serverless
DeepInfra$0.080$0.300
Serverless
OpenRouter$0.080$0.300
Serverless
GroqCloud$0.110$0.340
Serverless

Available via routers & gateways(16)

Capabilities

VisionMultimodalStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
Chatbot Arena1295.0Observed 2026-04-15Source
τ-bench62.3τ-benchObserved 2026-04-24Source
Massive Multi-discipline Multimodal Understanding69.4Observed 2025-04-05Source
MMLU PRO74.3Observed 2025-04-05Source
LiveCodeBench32.8Observed 2025-04-05Source

Migration checks

No linked migration route is available for this model yet.

Compare Llama 4 Scout 17B-16E Instruct with other models

Frequently asked questions

What is the context window of Llama 4 Scout 17B-16E Instruct?

Llama 4 Scout 17B-16E Instruct has a context window of 10m tokens.

How much does Llama 4 Scout 17B-16E Instruct cost?

Llama 4 Scout 17B-16E Instruct pricing ranges from $0.08/1M to $0.270/1M input tokens depending on the provider.

When was Llama 4 Scout 17B-16E Instruct released?

Llama 4 Scout 17B-16E Instruct was released on 2025-04-05.

Which providers offer Llama 4 Scout 17B-16E Instruct?

Llama 4 Scout 17B-16E Instruct is available from 12 providers: Cloudflare Workers AI, OpenRouter, Together AI, Fireworks AI, DeepInfra, GCP Vertex AI, NVIDIA NIM, GroqCloud, AWS Bedrock, Microsoft Foundry, Vercel AI Gateway, Novita AI.

What benchmarks has Llama 4 Scout 17B-16E Instruct been tested on?

Llama 4 Scout 17B-16E Instruct has been evaluated on 5 benchmarks, including Chatbot Arena, τ-bench, Massive Multi-discipline Multimodal Understanding, MMLU PRO, LiveCodeBench.