Meta

Llama 4 Maverick

AI model by Meta. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$0.26
Output$0.91
Blended (3:1)$0.42

Source: Artificial Analysis

Performance

Output Speed96 tok/s
Time to First Token930ms

Median values from Artificial Analysis

Editorial Analysis

Profile. Llama 4 Maverick is a budget-tier option from Meta at $0.91/M output tokens. Despite the low price, it scores competitively on Coding Index (16.3) and Intelligence Index (14.5) — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, Llama 4 Maverick reports 96 tok/s output speed and 930ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.

Cost model. For a workload of 1M input tokens + 100K output tokens, Llama 4 Maverick costs $0.35 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
Llama 4 MaverickCurrent
$0.26$0.9196 tok/s
Qwen3 235B A22B 2507 Instruct
$0.23$0.9256 tok/s
GLM-4.6V (Non-reasoning)
$0.30$0.9073 tok/s
Agnes 2.5 Pro Alpha
$0.45$0.90130 tok/s
GLM-4.6V (Reasoning)
$0.30$0.9070 tok/s
DeepSeek V3 (Dec '24)
$0.36$0.89

Example Costs

Single Request
$0.0007
1.0K in / 500 out
1K Requests/day
$0.7150
1.0M in / 500.0K out
10K Requests/day
$7.15
10.0M in / 5.0M out