Enterprise DNAEnterprise DNA
Meta logo

Models · Best cheap

Llama 4 Scout

by Meta

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.

Visit Meta ↗

Our verdict

Not reviewed yet

We have not reviewed Llama 4 Scout yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About 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.

Best for

Open-weight long-context coding on a budget

Use cases

  • repo Q&A
  • self-host experiments
  • batch coding

Enterprise DNA angle

Omni helps teams prove Scout quality on real jobs before committing infra.

Notes

Llama 4 Scout is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Open-weights economics with long context
  • Good fit for cost-controlled coding agents

Cons

  • Hosted quality varies by endpoint
  • May need eval gates vs closed frontier models

Key facts

What we have checked

Input price
$0.100 per million tokens
Checked OpenRouter models API
Output price
$0.300 per million tokens
Checked OpenRouter models API
Price on deepinfra
$0.080 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$0.240 per million output tokens
Checked OpenRouter models API
Price on google-vertex
$0.250 per million input tokens
Checked OpenRouter models API
Price on google-vertex
$0.700 per million output tokens
Checked OpenRouter models API
Latest version
meta-llama/llama-4-scout-17b-16e-instruct
Checked OpenRouter models API
Time to first token (ms)
740
Checked Artificial Analysis
Output speed (tokens a second)
134.4
Checked Artificial Analysis
Gpqa diamond
51.8% (for 5 Apr 2025)
Checked Epoch AI (CC BY 4.0)
Arc agi 2
0% (for 5 Apr 2025)
Checked Epoch AI (CC BY 4.0)
Arc agi
0.5% (for 5 Apr 2025)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `meta-llama/llama-4-scout`.

  • openrouter · meta-llama/llama-4-scout · Docs

OpenRouter id: meta-llama/llama-4-scout

Price

What Llama 4 Scout costs, over time

Input price

$0.100 to $0.100

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.300 to $0.300

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
deepinfraInput$0.080 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.240 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$0.250 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$0.700 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Llama 4 Scout is used

Tokens served a day

1.8B to 1.3B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Llama 4 Scout scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index6.5indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index8.2indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index0.5indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Design Arena rating (Elo)896EloAs of 10 Nov 2026Design Arena via OpenRouter
Arc agi (best-across-versions)0.5percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)0percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)57.9percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Fiction livebench (best-across-versions)36percentAs of 6 Apr 2025Epoch AI (CC BY 4.0)
Frontiermath 2025 02 28 private (best-across-versions)0percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)51.8percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Lmca (best-across-versions)12percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Math level 5 (best-across-versions)62.3percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Show 1 more score
ScoreValueSourceChecked
Otis mock aime 2024 2025 (best-across-versions)Saturated7.8percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    output per mtok: 0.59 to 0.3

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.18 to 0.1

    Source: OpenRouter models API

  3. Price changed

    output per mtok: 0.3 to 0.59

    Source: OpenRouter models API

  4. Price changed

    input per mtok: 0.1 to 0.18

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Llama 4 Scout is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
11.4B ▼24.9%
Requests, last 7 days
6.8M
Tool calls, last 7 days
29.4K
Average cost per request
2.3¢
Price per million tokens
$0.1 in · $0.3 out
02.5B5B19 Sept: 1.8B tokens, 808K requests20 Sept: 1B tokens, 556K requests21 Sept: 1.2B tokens, 649K requests22 Sept: 1.2B tokens, 702K requests23 Sept: 1.2B tokens, 649K requests24 Sept: 1.5B tokens, 811K requests25 Sept: 1.5B tokens, 782K requests26 Sept: 1.1B tokens, 604K requests27 Sept: 893M tokens, 571K requests28 Sept: 1.5B tokens, 756K requests29 Sept: 2.6B tokens, 942K requests30 Sept: 2.8B tokens, 1.1M requests1 Oct: 2.2B tokens, 972K requests2 Oct: 1.3B tokens, 715K requests3 Oct: 1.7B tokens, 721K requests4 Oct: 1.5B tokens, 762K requests5 Oct: 1.5B tokens, 797K requests6 Oct: 1.7B tokens, 867K requests7 Oct: 1.6B tokens, 812K requests8 Oct: 1.3B tokens, 689K requests9 Oct: 1.3B tokens, 705K requests10 Oct: 2B tokens, 731K requests11 Oct: 2.3B tokens, 800K requests12 Oct: 2.1B tokens, 701K requests13 Oct: 2.2B tokens, 754K requests14 Oct: 3.2B tokens, 992K requests15 Oct: 4.2B tokens, 1.1M requests16 Oct: 4.1B tokens, 1.5M requests17 Oct: 2.9B tokens, 831K requests18 Oct: 2.6B tokens, 809K requests19 Oct: 2.3B tokens, 698K requests20 Oct: 2.4B tokens, 813K requests21 Oct: 2.6B tokens, 846K requests22 Oct: 2.5B tokens, 903K requests23 Oct: 1.3B tokens, 605K requests24 Oct: 3.9B tokens, 1.3M requests25 Oct: 1.2B tokens, 607K requests26 Oct: 933M tokens, 543K requests27 Oct: 1.1B tokens, 654K requests28 Oct: 1.9B tokens, 1.1M requests29 Oct: 1.9B tokens, 1.2M requests30 Oct: 1.9B tokens, 1.1M requests31 Oct: 2.5B tokens, 1.6M requests1 Nov: 2.5B tokens, 1.6M requests2 Nov: 2.2B tokens, 1.3M requests3 Nov: 2.1B tokens, 1.2M requests4 Nov: 2.5B tokens, 1.4M requests5 Nov: 2.4B tokens, 1.4M requests6 Nov: 2.3B tokens, 1.2M requests7 Nov: 943M tokens, 742K requests8 Nov: 793M tokens, 513K requests9 Nov: 1.1B tokens, 725K requests10 Nov: 1.3B tokens, 771K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Llama 4 Scout.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-11. Hosting routes and app features can differ.

DeveloperMeta
Exact model identifiermeta-llama/llama-4-scout
Inputtext, image
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
llama4, open weights (access request)
Context length
1.3M tokens
Knowledge cutoff
31 Aug 2024
Developer release date
Not established
First seen in the catalogue
5 Apr 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

meta-llama/llama-4-scout: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-11
openrouter.ai ↗

Source for first seen, tool calling, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-11
Licence source ↗

Licence declared in the meta-llama/Llama-4-Scout-17B-16E-Instruct model repository on Hugging Face, which holds the weights files behind an access request. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Coding Index: 8.2 (2026-11-09) ↗Agentic Index: 0.5 (2026-11-09) ↗Design Arena: 896 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →