meta-llama/llama-4-maverick-17b-128e-instruct

meta-llama/Llama-4-Maverick-17B-128E-Instruct

Context

128K

Input

text

Output

text

Tool calling

Supported

About this model

Llama 4 Maverick 17B-128E Instruct is Meta's 17B-parameter MoE instruction model featuring 128 experts with 4 active per token. Optimized for complex task decomposition and tool-integrated reasoning with constitutional AI safety, delivering expert-level performance at accessible computational requirements.

Compare Text Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Groq

Available

Input tokens

$0.200 / 1M tokens

Output tokens

$0.600 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.200 / 1M tokens
Output tokens	$0.600 / 1M tokens

Performance

Published evaluation results associated with this model.

Instruction Following

AlpacaEval92.8

InstructBench87.4

Complex Task Accuracy89.6

Multi-Step Completion93.1

Tool & Reasoning

Tool Calling Accuracy96.3

API Composition90.7

GSM8K92.4

TheoremQA58.3

Safety & Alignment

Constitutional Adherence98.4

Harmlessness99

Bias Detection94.7

TruthfulQA88.6

Efficiency Metrics

Tokens/sec520

Expert Activation Latency0.8

VRAM Utilization42.3

Tokens/$64.8

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'