PlanPulse
English

Llama 4 Scout API Pricing

Short answer

Llama 4 Scout costs $0.15 per 1M input tokens and $0.60 per 1M output tokens (cached input $0.075/1M). Context window: 131K. Last verified 2026-06-17 from fireworks.ai. Confidence: Auto.

Llama 4 Scout is Meta's open-weight MoE with a standout 10M-token context window, hosted on several providers.

Input
$0.15 /1M
Output
$0.60 /1M
Cached input
$0.075 /1M
Input pricing$0.15
Cached input$0.075
Output pricing$0.60

Limits & capabilities

Context window131K
Max output—
Modalitytext + image input, text output
ChannelFireworks
ProviderMeta

Best for

Open weightUltra-long contextMultimodal
Open-weight (17B active / 16 experts). Native 10M context; some hosts cap it (Groq 128K).
Open provider → Pricing source: fireworks.ai →
Last checked Auto

More from Meta

Llama 3.3 70B

$0.10 /1M in
$0.32 /1M out

Open weight, General, Cheap

Llama 4 Maverick

$0.15 /1M in
$0.60 /1M out

Open weight, Reasoning, Multimodal

Related comparisons

OpenAI vs Anthropic API

Compare pricing, channels, and trade-offs →