Models
Explore models and compare pricing across providers. Select a creator to browse their models.
Llama 3.1 8B Instruct
MetaMeta Llama 3.1 8B Instruct — a widely deployed small open-weight model.
Llama 3.2 1B Instruct
MetaMeta's Llama 3.2 1B Instruct — smallest open-weight Llama 3.2 text model.
Llama 3.2 3B Instruct
MetaMeta's Llama 3.2 3B Instruct — small open-weight text model for lightweight and on-device use.
Llama 3.3 70B
MetaWidely deployed open-weight model with strong general capabilities.
Llama 4 Maverick
MetaLargest open Llama 4 with 128 experts. 400B total, 17B active. Beats GPT-4o on benchmarks.
Llama 4 Scout
MetaNatively multimodal MoE model with 10M context. 109B total, 17B active. Fits single H100.
Muse Glimmer 30B
MetaMeta's Muse Glimmer 30B — compact Muse model with image input.
Muse Spark Open
MetaMeta's open-weight Muse Spark — 816B MoE (42B active) for agentic coding and long-horizon tasks, with text, image, video and audio input and a 1M-token context window.