Llama-3.2-3B
Small open Llama base model for lightweight text generation and self-hosting
Context
131,072
Max output
131,072
Input / 1M
$0.10
Output / 1M
$0.10
Providers
2
01Profile
Profile
Released
2024-09-25
Last updated
2026-06-11
Knowledge cutoff
2023-12
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 2 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-09-25
2026-08-05Addedpioneeroffering→ new
2026-07-19Removedvercelofferingremoved→ new
2026-06-10ContextveniceContext window128,000→ new
2026-06-10ContextveniceContext window—→ 128,000
2026-06-10ContextveniceMax output4,096→ new
2026-06-10ContextveniceMax output—→ 4,096
2026-03-12ContextveniceMax output32,000→ 4,096
2026-01-28ContextveniceContext window131,072→ 128,000
2026-01-28ContextveniceMax output32,768→ 32,000
2026-01-10Addedverceloffering→ new
2025-12-20ContextveniceMax output32,768→ 8,192
2025-12-20ContextveniceMax output8,192→ 32,768