Seedream 5.0 Pro está no ar | Experimente no Gerador de Imagens →
Entrar

Meta LLM Models

4 Meta models on WaveSpeedAI — transparent per-token pricing, OpenAI-compatible endpoint, no cold starts.

Llama 3.1 8b Instruct API
meta-llama/llama-3.1-8b-instruct
$0.02/M in· $0.05/M out· 16K ctx
Llama 3.2 3b Instruct API
meta-llama/llama-3.2-3b-instruct
$0.051/M in· $0.34/M out· 80K ctx
Llama 3.3 70b Instruct API
meta-llama/llama-3.3-70b-instruct
$0.1/M in· $0.32/M out· 131K ctx
Llama Guard 4 12b API
meta-llama/llama-guard-4-12b
$0.18/M in· $0.18/M out· 164K ctx

Browse all LLMs

Compare every Claude, GPT, Gemini, Qwen, DeepSeek, Llama, Grok and more.

wavespeed.ai/llm →

Open the Playground

Run any model live, see latency and cost in real time.

wavespeed.ai/llm/playground →
Meta LLM Models — API Pricing & Playground | WaveSpeedAI