Meta: Llama 4 Maverick

MetaOpen weights

Meta: Llama 4 Maverick by Meta costs $0.19 per 1M input tokens and $0.65 per 1M output tokens, with a 1M-token context window.

Pricing

Input (per 1M tokens)

$0.19

Output (per 1M tokens)

$0.65

Cached input (per 1M)

$0.05

Specifications

Provider: Meta
Context window: 1M tokens
Parameters: 400B
Released: Apr 2025
Open weights: Yes
Frontier model: No
Hugging Face: meta-llama/Llama-4-Maverick-17B-128E-Instruct

Speed & latency

Time to first token

0.22s

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

Compare Meta: Llama 4 Maverick with…

Meta: Llama 4 Maverick vs Gemma 2 27B$0.65/1M Meta: Llama 4 Maverick vs Step-3$0.65/1M Meta: Llama 4 Maverick vs WizardLM-2 8x22B$0.62/1M Meta: Llama 4 Maverick vs Meta-Llama-3-8B-Instruct$0.61/1M Meta: Llama 4 Maverick vs Qwen2.5 7B Instruct$0.70/1M Meta: Llama 4 Maverick vs Qwen3 8B$0.70/1M

FAQ

How much does Meta: Llama 4 Maverick cost?

Meta: Llama 4 Maverick is priced at $0.19 per 1M input tokens and $0.65 per 1M output tokens. Output tokens cost more than input.

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

Meta: Llama 4 Maverick supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.

Is Meta: Llama 4 Maverick open weight?

Yes — Meta: Llama 4 Maverick 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.