Meta

Llama 4 Scout

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

Pricing (per 1M tokens)

Input$0.18
Output$0.66
Blended (3:1)$0.30

Source: Artificial Analysis

Performance

Output Speed135 tok/s
Time to First Token780ms

Median values from Artificial Analysis

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

ModelInputOutputSpeed
Llama 4 ScoutCurrent
$0.18$0.66135 tok/s
Qwen3 VL 32B Instruct
$0.16$0.6464 tok/s
Qwen3 32B (Reasoning)
$0.16$0.64101 tok/s
Qwen3 32B (Non-reasoning)
$0.16$0.64104 tok/s
Qwen3 VL 32B (Reasoning)
$0.16$0.6490 tok/s
Hermes 3 - Llama-3.1 70B
$0.70$0.7034 tok/s

Example Costs

Single Request
$0.0005
1.0K in / 500 out
1K Requests/day
$0.5100
1.0M in / 500.0K out
10K Requests/day
$5.10
10.0M in / 5.0M out