TokenRate

Llama 3.2 3B Pricing

Fast

Meta · 131K tokens context

Llama 3.2 3B from Meta costs $0.051 per 1 million input tokens and $0.335 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 131,072-token context window (approximately 98,304 words) with a 4K-token maximum output. A typical 1,000-token request costs $0.0001 in input charges; a 10,000-token request costs $0.0005.

Llama 3.2 3B pricing and capability summary
Input price$0.051 / 1M tokens
Output price$0.335 / 1M tokens
Output / input ratio6.6×
Context window131,072 tokens (~98,304 words)
Maximum output4,096 tokens
Cost per 1K tokens (input)$0.0001
TierFast
Last verified

Llama 3.2 3B is a tiny but surprisingly capable open-weight model — one of the cheapest LLMs available from any provider. Fits on edge hardware and consumer GPUs with room to spare.

Live pricing from OpenRouter

Input Price

$0.051

per 1 million tokens

Output Price

$0.335

per 1 million tokens

Context Window

131K tokens

max 4K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.0000678$0.000134
10-page document (2,500 words)3,333$0.00017$0.000335
1,000 lines of code5,000$0.000255$0.000503
100K token document100,000$0.00509$0.0101

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Extremely cheap to host and call
  • Fits on consumer hardware (single GPU)
  • 128K context for the size

Limitations

  • Limited reasoning and generation quality
  • Not suitable for complex tasks

Best Use Cases

On-device inference
Simple extraction
Prototype chatbots

Calculate Llama 3.2 3B Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact Llama 3.2 3B costs — and compare across all models.

Open Calculator →

Llama 3.2 3B — FAQ

Related Models

Related Guides