Skip to content
OpenKey

Llama 4 Maverick

Meta AIReleased Apr 5, 2025

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 active parameters per forward...

Try in playground
Context window
1.0M tokens
Max output
16K tokens
Input
text, image
Output
text
Tokenizer
Llama4
Knowledge cutoff
Aug 31, 2024
Released
Apr 5, 2025

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.150$0.0045$0.154
Output$0.600$0.018$0.618

Benchmarks

Artificial Analysis

Intelligence index
14.3
Coding index
16.3
Agentic index
1.3

Design Arena

CategoryEloWin rateRank
3Dmodels97640.2%#91
Codemodels92935.8%#102
Data vizmodels92638.4%#100
Game devmodels90333.7%#103
UI componentsmodels95540.8%#94
Websitesmodels91434.4%#105

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model meta-llama/llama-4-maverick.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-maverick",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="meta-llama/llama-4-maverick",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "meta-llama/llama-4-maverick",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Llama 4 Maverick cost via API?
Through OpenKey, Llama 4 Maverick costs $0.154 per 1M input tokens and $0.618 per 1M output tokens. That is the provider price ($0.150 / $0.600) plus a flat 3% fee — nothing else.
What is Llama 4 Maverick's context window?
Llama 4 Maverick accepts up to 1.0M tokens of context and returns up to 16K tokens per request.
Is Llama 4 Maverick OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "meta-llama/llama-4-maverick" using any OpenAI SDK — only the base URL and API key change.
What inputs does Llama 4 Maverick support?
Llama 4 Maverick accepts text, image input and produces text output. Its knowledge cutoff is Aug 31, 2024.

More from Meta AI

All Meta AI models →