Llama 3.2 3B API

Llama 3.2 3B is a large language model by Meta, available on the Venice API as llama-3.2-3b. It runs privately, with zero data retention.

Llama 3.2 3B API pricing

Model ID	Variant	Privacy	Price
`llama-3.2-3b`	Standard	Private	$0.15 input /$ 0.60 output per 1M tokens

Llama 3.2 3B specifications

Spec	Value
Provider	Meta
Released	Oct 3, 2024
Privacy	Private
Open weights	Yes
Context window	125K tokens
Max output	4K tokens
Served precision	FP16

How to use the Llama 3.2 3B API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "llama-3.2-3b" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.2-3b",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'

Llama 3.2 3B API FAQ

How much does the Llama 3.2 3B API cost?

0.15 per 1M input tokens and

0.60 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity.

What is the Llama 3.2 3B model ID?

Use llama-3.2-3b as the model parameter.

Is the Llama 3.2 3B API private?

Llama 3.2 3B is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of Llama 3.2 3B?

125K tokens of context, with up to 4K output tokens per response.

What does Llama 3.2 3B support?

Llama 3.2 3B supports function calling and web search.

Which endpoint does the Llama 3.2 3B API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

Llama 3.3 70B API: $0.70 input /$ 2.80 output per 1M tokens
Qwen 3 235B A22B Instruct 2507 API: $0.15 input /$ 0.75 output per 1M tokens
Gemma 4 Uncensored API: $0.16 input /$ 0.50 output per 1M tokens
DeepSeek V3.2 API: $0.33 input /$ 0.48 output per 1M tokens
GPT-4o Mini API: $0.19 input /$ 0.75 output per 1M tokens

Explore

By modality