Meta: Llama 4 Scout

MetaOpen weights

Meta: Llama 4 Scout by Meta costs $0.18 per 1M input tokens and $0.59 per 1M output tokens, with a 1.3M-token context window.

Pricing

Input (per 1M tokens)

$0.18

Output (per 1M tokens)

$0.59

Cached input (per 1M)

—

Specifications

Provider: Meta
Context window: 1.3M tokens
Parameters: 109B
Released: Apr 2025
Open weights: Yes
Frontier model: No
Hugging Face: meta-llama/Llama-4-Scout-17B-16E-Instruct

Speed & latency

Time to first token

0.23s

Output speed

220 tok/s

Fastest host: bedrock (via vercel-ai-gateway).

Compare Meta: Llama 4 Scout with…

Meta: Llama 4 Scout vs GPT OSS 120B$0.60/1M Meta: Llama 4 Scout vs GPT-4o-mini$0.60/1M Meta: Llama 4 Scout vs Command R (08-2024)$0.60/1M Meta: Llama 4 Scout vs Gemma 4 26B A4B IT$0.60/1M Meta: Llama 4 Scout vs Mistral Small (latest)$0.60/1M Meta: Llama 4 Scout vs Gemini 2.5 Flash Preview$0.60/1M

FAQ

How much does Meta: Llama 4 Scout cost?

Meta: Llama 4 Scout is priced at $0.18 per 1M input tokens and $0.59 per 1M output tokens. Output tokens cost more than input.

What is Meta: Llama 4 Scout's context window?

Meta: Llama 4 Scout supports a context window of 1.3M tokens — the maximum prompt plus response length it can handle in a single request.

Is Meta: Llama 4 Scout open weight?

Yes — Meta: Llama 4 Scout has openly available weights.

Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.