Llama 4 Maverick
AI model by Meta. Real-time pricing and benchmark data.
Benchmarks
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
| Model | Input | Output | Speed |
|---|---|---|---|
Llama 4 MaverickCurrent | $0.26 | $0.91 | 96 tok/s |
| Qwen3 235B A22B 2507 Instruct | $0.23 | $0.92 | 56 tok/s |
| GLM-4.6V (Non-reasoning) | $0.30 | $0.90 | 73 tok/s |
| Agnes 2.5 Pro Alpha | $0.45 | $0.90 | 130 tok/s |
| GLM-4.6V (Reasoning) | $0.30 | $0.90 | 70 tok/s |
| DeepSeek V3 (Dec '24) | $0.36 | $0.89 | — |