AI TOOLS RADAR
Explore
All models / META-LLAMA
meta-llama logo
meta-llama

Meta: Llama 4 Maverick

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 pass (400B total). $0.20 per million input tokens, $0.696 per million output tokens. 1,048,576 token context window. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
115,200 tokens
Architecture
text+image->text
Tokenizer
Llama4
Knowledge cutoff
2024-08-31
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.2
/M tokens
Output
$0.696
/M tokens
API

Quick start

Call this exact model ID through OpenRouter’s OpenAI-compatible API.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta-llama/llama-4-maverick","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
API

Supported API parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

5 providers

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DigitalOcean

unknown
Context
128K
Maximum output
115K
Input
$0.200
Output
$0.696
Cache read
Not provided
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
16K
Input
$0.200
Output
$0.800
Cache read
Not provided
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
8K
Input
$0.270
Output
$0.850
Cache read
Not provided
Cache write
Not provided

Parasail

fp8
Context
524K
Maximum output
33K
Input
$0.350
Output
$1.00
Cache read
$0.170
Cache write
Not provided

Google

unknown
Context
524K
Maximum output
8K
Input
$0.350
Output
$1.15
Cache read
Not provided
Cache write
Not provided
meta-llama

models

All models
meta-llama logometa-llama

Meta: Llama Guard 4 12B

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...

Context
164K
Input
image · text
Output
text
Input: $0.180Output: $0.180per 1M tokens
View model details →
meta-llama logometa-llama

Meta: 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. It supports native multimodal input...

Context
1.3M
Input
text · image
Output
text
Input: $0.110Output: $0.340per 1M tokens
View model details →
meta-llama logometa-llama

Meta: Llama 3.3 70B Instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Context
131K
Input
text
Output
text
Input: $0.710Output: $0.710per 1M tokens
View model details →
meta-llama logometa-llama

Meta: Llama 3.2 1B Instruct

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

Context
60K
Input
text
Output
text
Input: $0.027Output: $0.201per 1M tokens
View model details →