LLM Open Weight

Llama 4 Scout

by Meta

Natively multimodal MoE model with 10M context. 109B total, 17B active. Fits single H100.

Parameters
109B (17B active)
Context
10M
Providers
6
Cheapest Input
$0.080
Vision Function Calling JSON Mode Streaming Chat / InstructVision

Price Comparison

Compare pricing across 6 providers serving Llama 4 Scout

Provider Input $/1M Output $/1M Context Speed TTFT Status
OP
OpenRouter
$0.080 $0.300 Live
GR
Groq
$0.110 $0.340 Live
AM
Amazon Bedrock
$0.170 $0.450 10M Live
NO
Novita AI
$0.180 $0.590 Live
CL
Cloudflare Workers AI
$0.270 $0.850 Live
FI
Fireworks AI
$0.900 $0.900 Live
Cheapest Fastest Prices in USD per 1M tokens