whichllm — Browse and compare AI model specs and pricing

Guide
Provider

Llama models

Browse Llama AI models by context window, pricing, tool calling, reasoning support, and model IDs.

Snapshot

Models 7
Providers 1
Max context 128000
Lowest input -
Lowest output -
Tool calling 7
Reasoning 0

How to use this hub

Llama appears in whichllm as a provider cluster with 7 cataloged model entries, normalized model IDs, pricing fields, and capability flags.

Use this page to scan Llama models by context window, tool calling, reasoning support, and token pricing before opening individual model specs.

Explore related hubs

Long context modelsReasoning modelsTool calling modelsVision models

Featured models

Cerebras-Llama-4-Maverick-17B-128E-Instruct Llama · 128000 context In - · Out -
Cerebras-Llama-4-Scout-17B-16E-Instruct Llama · 128000 context In - · Out -
Groq-Llama-4-Maverick-17B-128E-Instruct Llama · 128000 context In - · Out -
Llama-4-Maverick-17B-128E-Instruct-FP8 Llama · 128000 context In - · Out -
Llama-4-Scout-17B-16E-Instruct-FP8 Llama · 128000 context In - · Out -
Llama-3.3-70B-Instruct Llama · 128000 context In - · Out -
Llama-3.3-8B-Instruct Llama · 128000 context In - · Out -

Models in this hub

Cerebras-Llama-4-Maverick-17B-128E-Instruct Llama · 128000 context In - · Out -
Cerebras-Llama-4-Scout-17B-16E-Instruct Llama · 128000 context In - · Out -
Groq-Llama-4-Maverick-17B-128E-Instruct Llama · 128000 context In - · Out -
Llama-3.3-70B-Instruct Llama · 128000 context In - · Out -
Llama-3.3-8B-Instruct Llama · 128000 context In - · Out -
Llama-4-Maverick-17B-128E-Instruct-FP8 Llama · 128000 context In - · Out -
Llama-4-Scout-17B-16E-Instruct-FP8 Llama · 128000 context In - · Out -