ModelPickr

Models / Meta / Llama-3.2-3B

Meta · llama

Llama-3.2-3B

Small open Llama base model for lightweight text generation and self-hosting

$0.10 in · $0.10 out

per 1M tokens · provider rate closest to the median. No first-party Meta price was listed. The reference price is Pioneer's rate, the provider closest to the median.

Provider input prices run from $0.051 to $0.15 per 1M tokens. Output prices run from $0.10 to $0.60.

Context
131,072
Max output
8,192
Cache read
$0.10
Cache write
$0.10
Reasoning
No
Tool calls
No
Structured output
Unknown
Vision
No
Open weights
Yes
License
Llama 3.2 Community License
Released
Sep 25, 2024
Updated in source
Sep 25, 2024
Knowledge
2023-12
Providers
3

Hugging Face weights

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Cloudflare Workers AI$0.051$0.34———
Pioneerreference$0.10$0.10$0.10$0.10—
Venice AI$0.15$0.60———