Venice AI
Llama 3.2 3B
Canonical ID:
venice/llama-3.2-3b
Open Llama instruction model for multilingual chat, reasoning, and coding
Overview
- Provider
-
Venice AI
- Family
- llama-3.2-3b
- Release date
- 2024-10-03
- Last updated
- 2026-01-28
- Input modalities
- text
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $0.15/1M
- Output
- $0.6/1M
- Cached input
- N/A
Context and output
- Context window
- 128,000
- Max output tokens
- 32,000
- Qualified ID
- venice/llama-3.2-3b
Model Summary
Llama 3.2 3B is a model listing in the Venice AI provider catalog. It is categorized under the llama-3.2-3b family.
The model supports text modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0.15/1M input and $0.6/1M output.
More From Venice AI
Related models from the same provider catalog.
Venice AI
Abliterated Large V2
venice/abliteration-abliterated-model-large-v2
Venice AI
Aion 3.0
venice/aion-labs-aion-3-0
Venice AI
Aion 3.0 Mini
venice/aion-labs-aion-3-0-mini
Venice AI
Aion 3.5
venice/aion-labs-aion-3-5
Venice AI
Aion 3.5 Mini
venice/aion-labs-aion-3-5-mini
Venice AI
Claude Fable 5
venice/claude-fable-5
Venice AI
Claude Fable 5.1
venice/claude-fable-5-1
Venice AI
Claude Haiku 5.5
venice/claude-haiku-5-5
Same Family: llama-3.2-3b
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
Llama 3.2 3B Instruct
vercel/meta/llama-3.2-3b
|
Vercel AI Gateway
|
128,000 | $0.15/1M | $0.15/1M |
|