Llama 4 Maverick 17B Instruct by DevPass (LLM Gateway)

$10 off the fastest Kimi K3 and GLM 5.3$10 off the fastest Kimi K3 and GLM 5.3

Model details

Llama 4 Maverick 17B Instruct

Llama 4 Maverick Instruct is a multimodal language model designed to work with text and image inputs while producing text and code. Its mixture-of-experts design activates 17 billion parameters for each forward pass while the full model contains 400 billion parameters across 128 experts, balancing substantial capacity with selective computation.

The model was trained on 22 trillion tokens drawn from public sources, licensed material, and Meta platform data. Early-fusion multimodality enables combined processing of text and images, and its one-million-token context window makes it well suited to long documents, repository-scale analysis, and visually grounded tasks that require reasoning across large amounts of material.

DevPass (LLM Gateway)llama-4-maverick-17b-instructllama

Open provider page Provider docs

Quick Info

Provider: DevPass (LLM Gateway)
Model key: llama-4-maverick-17b-instruct
Release date: Apr 5, 2025
Last updated: Apr 5, 2025
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.27
Output token cost: $0.85

Limits

Output tokens: 2,048 tokens
Context window: 1,048,576 tokens

Transparent token rates

Compare llama pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Llama 4 Maverick 17B Instruct

DevPass (LLM Gateway)

CoverageBenchmark

OpenRouter identifies Meta’s Llama 4 Maverick 17B Instruct (128E) as a multimodal mixture-of-experts model with 128 experts, 17B active parameters, and 400B total parameters. It supports text and image input and outputs text and code in 12 languages, with early-fusion multimodality and a 1M-token context window. The same page says the model was released on April 5, 2025 under the Llama 4 Community License, has an August 2024 knowledge cutoff, and was trained on 22T tokens from public, licensed, and Meta-platform data. OpenRouter also lists provider-specific pricing, latency, throughput, and uptime, but does not mention DevPass

LLM Gateway

CoverageBenchmark

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...