Enterprise DNAEnterprise DNA
Meta logo

Models · Best coding

Llama 4 Maverick

by Meta

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion.

Visit Meta ↗

Our verdict

Not reviewed yet

We have not reviewed Llama 4 Maverick 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 Maverick

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta.

Best for

Teams that want open-weight flexibility with hosted convenience

Use cases

  • self-host experiments
  • cost-controlled apps
  • fine-tune pipelines

Enterprise DNA angle

EDNA helps teams decide when open weights belong in Omni vs when a closed frontier model is cheaper in total cost of quality.

Notes

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

Pros

  • Open-weights family economics
  • Strong community and self-host path

Cons

  • Hosted quality depends on the OpenRouter endpoint
  • May trail closed frontier models on hardest tasks

Key facts

What we have checked

Input price
$0.350 per million tokens
Checked OpenRouter models API
Output price
$1.00 per million tokens
Checked OpenRouter models API
Price on digitalocean
$0.050 per million cached input tokens
Checked OpenRouter models API
Price on digitalocean
$0.188 per million input tokens
Checked OpenRouter models API
Price on digitalocean
$0.652 per million output tokens
Checked OpenRouter models API
Price on google-vertex
$0.350 per million input tokens
Checked OpenRouter models API
Price on google-vertex
$1.15 per million output tokens
Checked OpenRouter models API
Price on parasail
$0.170 per million cached input tokens
Checked OpenRouter models API
Price on parasail
$0.350 per million input tokens
Checked OpenRouter models API
Gpqa diamond
67% (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)
Aider polyglot
15.6% (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-maverick`.

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

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

Price

What Llama 4 Maverick costs, over time

Input price

$0.200 to $0.350

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

Source: OpenRouter models API. Checked .

Output price

$0.696 to $1.00

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
digitaloceanCached input$0.050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$0.188 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanOutput$0.652 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$0.350 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$1.15 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.170 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.350 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$1.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Llama 4 Maverick is used

Tokens served a day

2.7B to 2B

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 Maverick 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 Index9.3indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index16.3indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index0.6indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Design Arena rating (Elo)894EloAs of 10 Nov 2026Design Arena via OpenRouter
Aider polyglot (best-across-versions)15.6percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Arc agi (best-across-versions)4.4percentAs 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)61.9percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Fiction livebench (best-across-versions)46.2percentAs of 6 Apr 2025Epoch AI (CC BY 4.0)
Frontiermath 2025 02 28 private (best-across-versions)0.7percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Geobench (best-across-versions)52percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)67percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Show 6 more scores
ScoreValueSourceChecked
Lech mazur writing (best-across-versions)62percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Lmca (best-across-versions)15.9percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Math level 5 (best-across-versions)73percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated20.6percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Simplebench (best-across-versions)27.7percentAs of 5 Apr 2025Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)24.5percentAs 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: 0.6525 to 1

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.1875 to 0.35

    Source: OpenRouter models API

  3. Price changed

    output per mtok: 0.696 to 0.6525

    Source: OpenRouter models API

  4. Price changed

    input per mtok: 0.2 to 0.1875

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 0.8 to 0.696

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Llama 4 Maverick is used

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

Tokens, last 7 days
14.7B ▲2.9%
Requests, last 7 days
9M
Tool calls, last 7 days
30K
Average cost per request
6.7¢
Price per million tokens
$0.35 in · $1 out
02.5B5B19 Sept: 2.7B tokens, 1.3M requests20 Sept: 2.1B tokens, 995K requests21 Sept: 2.1B tokens, 985K requests22 Sept: 3.1B tokens, 1.7M requests23 Sept: 2.3B tokens, 1.1M requests24 Sept: 2B tokens, 906K requests25 Sept: 2.2B tokens, 1.4M requests26 Sept: 2.3B tokens, 1.1M requests27 Sept: 2B tokens, 789K requests28 Sept: 1.9B tokens, 854K requests29 Sept: 2B tokens, 1.1M requests30 Sept: 2.1B tokens, 1.1M requests1 Oct: 2.2B tokens, 1.1M requests2 Oct: 2.1B tokens, 964K requests3 Oct: 1.7B tokens, 779K requests4 Oct: 2.2B tokens, 916K requests5 Oct: 1.8B tokens, 866K requests6 Oct: 1.8B tokens, 1.1M requests7 Oct: 2.6B tokens, 1.5M requests8 Oct: 2.6B tokens, 1.3M requests9 Oct: 2.9B tokens, 1.7M requests10 Oct: 2.3B tokens, 974K requests11 Oct: 1.9B tokens, 985K requests12 Oct: 2.5B tokens, 1.4M requests13 Oct: 2.5B tokens, 1.3M requests14 Oct: 2.7B tokens, 1.2M requests15 Oct: 2.6B tokens, 1.2M requests16 Oct: 2.4B tokens, 917K requests17 Oct: 2.5B tokens, 834K requests18 Oct: 2.4B tokens, 944K requests19 Oct: 2.3B tokens, 1M requests20 Oct: 2.5B tokens, 944K requests21 Oct: 3.5B tokens, 1.1M requests22 Oct: 2.1B tokens, 927K requests23 Oct: 2.2B tokens, 1M requests24 Oct: 1.8B tokens, 936K requests25 Oct: 1.9B tokens, 788K requests26 Oct: 2B tokens, 965K requests27 Oct: 1.9B tokens, 889K requests28 Oct: 1.9B tokens, 782K requests29 Oct: 2.1B tokens, 910K requests30 Oct: 1.9B tokens, 848K requests31 Oct: 2.2B tokens, 1.4M requests1 Nov: 2B tokens, 1.4M requests2 Nov: 2B tokens, 1M requests3 Nov: 2.1B tokens, 1.2M requests4 Nov: 2.4B tokens, 1.6M requests5 Nov: 2.2B tokens, 1.2M requests6 Nov: 2B tokens, 1.2M requests7 Nov: 2B tokens, 1.2M requests8 Nov: 2B tokens, 1.2M requests9 Nov: 2.2B tokens, 1.5M requests10 Nov: 2B tokens, 1.1M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Llama 4 Maverick.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-05. Hosting routes and app features can differ.

DeveloperMeta
Exact model identifiermeta-llama/llama-4-maverick
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
524K 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-maverick: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-05
openrouter.ai ↗

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

Checked 2026-11-05
Licence source ↗

Licence declared in the meta-llama/Llama-4-Maverick-17B-128E-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: 16.3 (2026-11-09) ↗Agentic Index: 0.6 (2026-11-09) ↗Design Arena: 894 (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 →