Llama 4 Maverick
by DeepInfra · 17B (128 experts) parameters
Today's price · per 1M tokens
Input
$0.200
per 1M tokens
Output
$0.800
per 1M tokens
Blended
$0.350
blended $/1M — 3:1 weighted input:output
Price receipt
We read DeepInfra's own pricing page on Aug 24, 2026 and found Llama-4-Maverick-17B-128E listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is c3a82092cd.
Overview
Meta Llama 4 Maverick served on DeepInfra at $0.20/$0.80 per 1M tokens. Natively multimodal MoE (17B active, 128 experts, 400B total) with a 1M-token context.
Deploy this open model on rented GPUs
Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.
Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is better- AA Intelligence Index: 14.5 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 1.2 (Tool use, planning, autonomy)
- AA-Omniscience Index: -41.9 (−100–100)
- Ranks #43 of 73 benchmarked models by average score
- Ranks #127 of 170 comparably-measured models by percentile score, across 6 independent measurements
- Ranks #39 of 170 comparably-tested models by normalized performance per dollar
- Strongest at MMMLU — 84.6%, #11 of 34
126 tokens/sec output 0.45s latency to first token (TTFT)
Source: Vellum LLM Leaderboard · updated Aug 28, 2026 · See full rankings →
Specifications
- Provider
- DeepInfra
- Context window
- 1M tokens
- Modality
- text, image
- Parameters
- 17B (128 experts)
- Open source
- Yes — open weights available
- Released
- Apr 6, 2025
- Status
- Current
- Last updated
- Jul 28, 2026
- Tags
Availability verified: Aug 24, 2026 — listed on DeepInfra's own page