Llama 4 Maverick

llama-4-maverick by Meta Released January 27, 2026

ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off

Input from

$0.5 / 1M

Output from

$1.5 / 1M

Cached input from

$0.05 / 1M

Context window

128K

Endpoints

from 1 providers

Regions

Monde, Europe

About Llama 4 Maverick

Llama 4 Maverick est un modèle linguistique de pointe de type « mixture of experts » (MoE), entraîné et publié par Meta. Le modèle compte 17 milliards de paramètres actifs, 128 experts et un total de 400 milliards de paramètres. Il prend en charge une longueur de contexte de 128 000 tokens. Optimisé pour les cas d’utilisation de dialogues multilingues, il prend en charge 12 langues et est aligné sur les préférences humaines en matière d’utilité et de sécurité. Il n’est pas destiné à être utilisé dans d’autres langues que l’anglais. Llama 4 est distribué sous licence « Meta Llama 4 Community License », Copyright © Meta Platforms, Inc. Tous droits réservés. Il incombe aux clients de s’assurer du respect des licences applicables au modèle.

Llama 4 Maverick est un modèle conversationnel développé par Meta, disponible sur Eden AI via 2 endpoints chez 1 fournisseur, à partir de 0,5 $ par million de tokens en entrée et 1,5 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 128K tokens.

Providers and prices

2 endpoints from 1 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint

Region

Context

Input / 1M

Output / 1M

Cached / 1M

Supports

Databricks (Europe)Official−%databricks/databricks-llama-4-maverick@eu

Europe

128K

$0.5$0.5

$1.5

$0.05

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-llama-4-maverick

Monde

128K

$0.5$0.5

$1.5

$0.05

ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token

0.67 s

Databricks (Europe)

Lowest latency

0.44 s

Databricks (Europe)

Highest throughput

48.89 tok/s

Databricks

Best availability

100%

Databricks (Europe)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

Databricks (Europe)

0.67 s

0.44 s

0.73 s

3.86 tok/s

100%

Databricks

0.67 s

0.66 s

7.4 s

48.89 tok/s

100%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Llama 4 Maverick with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about Llama 4 Maverick

How much does Llama 4 Maverick cost?

On Eden AI, prices for this model start at $0.5 per million input tokens and $1.5 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

What is the context window of Llama 4 Maverick?

Up to 128K tokens, depending on the endpoint.

Which providers serve Llama 4 Maverick?

2 endpoints from 1 providers, available in: Monde, Europe. All of them are called with the same Eden AI API key.

Can I run Llama 4 Maverick in the EU?

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

How fast is Llama 4 Maverick?

Over the last 30 days, the fastest first token was 0.67 s (Databricks (Europe)) and the highest throughput was 48.89 tokens per second (Databricks).

About Llama 4 Maverick

Providers and prices

Performance

Estimate your monthly cost

Call Llama 4 Maverick with Eden AI

Questions about Llama 4 Maverick

More from Meta