Models/Meta/Llama 3.3 70B

Llama 3.3 70B

Meta 🧠 Language Model

Proven workhorse model. 70B dense parameters, strong coding and instruction following. Text-only, 128K context.

Specifications

Context Window128,000 tokens
Max Output8,192 tokens
Speed●●●●● Very Fast
ModalitiesInput: text  ·  Output: text
FeaturesTools: Yes Streaming: Yes

Pricing

Included with plan

Capabilities

chattools
Use Llama 3.3 70B on Zubnet →

More from Meta

Llama 4 Maverick
Most capable open-weight model. 400B params (17B active, 128-expert MoE). Multimodal with vision, tool use, and 524K context.
🧠 Language Model
Llama 4 Scout
Fast multimodal model. 109B params (17B active, 16-expert MoE). Vision, tool use, 327K context. Fits on a single GPU.
🧠 Language Model