Llama 4 Scout
AI model by Meta. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Llama 4 Scout is a budget-tier option from Meta at $0.66/M output tokens. Despite the low price, it scores competitively on Intelligence Index (10.3) and Coding Index (8.2) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Llama 4 Scout reports 135 tok/s output speed and 780ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Llama 4 Scout costs $0.25 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 ScoutCurrent | $0.18 | $0.66 | 135 tok/s |
| Qwen3 VL 32B Instruct | $0.16 | $0.64 | 64 tok/s |
| Qwen3 32B (Reasoning) | $0.16 | $0.64 | 101 tok/s |
| Qwen3 32B (Non-reasoning) | $0.16 | $0.64 | 104 tok/s |
| Qwen3 VL 32B (Reasoning) | $0.16 | $0.64 | 90 tok/s |
| Hermes 3 - Llama-3.1 70B | $0.70 | $0.70 | 34 tok/s |