Models/Meta/Llama 4 Maverick

Llama 4 Maverick

Name: Llama 4 Maverick API access
Brand: Meta

Meta · Open weights · Released Apr 5, 2025 · meta-llama/llama-4-maverick

Best $0.188 in / $0.652 out via DigitalOcean · 128K ctx at this price (headline 1.05M)

Compare Estimate cost

1.05M contextVisionToolsStructured outputPrompt cachingOpen weights

Available from 4 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 5 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	SMOKE	UPTIME
DigitalOcean	$0.188	$0.652	$0.05	128K	—	0.72s	38 tok/s	5/5	99.9%
Novita	$0.27	$0.85	—	1.05M	fp8	0.76s	41 tok/s	4/5	97.1%
Google	$0.35	$1.15	—	524K	—	✕	✕	5/5	—
Parasail	$0.35	$1.00	$0.17	524K	fp8	0.65s	52 tok/s	5/5	100.0%

TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 5 minutes ago

SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →

Input price history · best listed price, observed

↓ 6% SINCE SEP 15, 2026

$0.20 · SEP 15, 2026$0.188 · TODAY

Pricing variants · USD / MTok in / out

STANDARD

$0.188 / $0.652

per MTok in / out

CACHE READ $0.05

Recent changesRSS ↗

Oct 2, 2026endpoint removed · deepinfra5 → 4

Sep 15, 2026price decreased · input0.2 → 0.1875

Sep 15, 2026price decreased · output0.696 → 0.6525

About

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...

Specifications

Context window1,048,576

Max output16,384

Modalities intext, image

Modalities outtext

LicenseOpen weights

ReleasedApr 5, 2025

Knowledge cutoff2024-08-31

TokenizerLlama4

WeightsHugging Face ↗

Open weightsGATED

Hugging Facemeta-llama/Llama-4-Maverick-17B-128E-Instruct ↗

Downloads9.8K

Likes514

Licenseother

safetensorspytorch

Llama Guard 4 12B$0.18 / $0.18 Llama 4 Scout$0.10 / $0.30 Llama 3.3 70B Instruct$0.10 / $0.32 Llama 3.2 1B Instruct$0.027 / $0.201

Compare with

Llama 4 Maverick vs Llama 4 Scout

Embed badge

[![Llama 4 Maverick](https://modelindex.ai/badge/meta-llama/llama-4-maverick)](https://modelindex.ai/models/meta-llama/llama-4-maverick)

Sources

OpenRouter API23 minutes ago

AGGREGATOR

Hugging Face23 minutes ago

COMMUNITY

ModelIndex benchmarks17 days ago

MEASURED

Verified 23 minutes ago · list prices, not negotiated rates.