Meta: Llama 3.2 3B
Llama 3.2 3B is a language model from Meta released on Sep 25, 2024. It reads text and writes text, with a 128K token context window and up to 4K tokens per reply.
Show moreShow less
It costs $0.15 per million input tokens and $0.60 per million output tokens.
It supports tool calling, and its weights are open, so you can host it yourself.
- Modalities
- In / out price
- $0.15 / $0.60 per 1M
- Context
- 128K
- Max output
- 4K
- Released
- Sep 25, 2024
- Knowledge cutoff
- Dec 2023
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Llama 3.2 3B pricing
USD, as listed on Nov 22, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.15 / 1M tokens | |
|---|---|---|
| Output | $0.60 / 1M tokens |
What Llama 3.2 3B costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Llama 3.2 3B through an OpenAI compatible API.
- Tools
tools - Temperature
temperature
Alternatives to Llama 3.2 3B
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 11.3
Reads text, images and files. Tool calling, structured output, reasoning. Served by 14 providers.
by mistralaiMar 16, 2026262K context$0.15/M input tokens$0.60/M output tokens14 providers
- Index 11.6
Reads text. Tool calling, structured output, reasoning. Served by 76 providers.
by openaiAug 5, 2025131K context$0.15/M input tokens$0.60/M output tokens76 providers
- 128K context
Reads text. Tool calling, structured output. Served by 5 providers.
by cohereAug 30, 2024$0.15/M input tokens$0.60/M output tokens5 providers
- Index 25.3
Reads text. Tool calling, structured output, reasoning. Served by 17 providers.
by tencentJul 6, 2026262K context$0.14/M input tokens$0.58/M output tokens17 providers
- Index 39.8
Reads text, images and video. Tool calling, structured output, reasoning. Served by 31 providers.
by qwenAug 26, 20261M context$0.15/M input tokens$0.47/M output tokens31 providers
- Index 14.7
Reads text and images. Tool calling, structured output, reasoning. Served by 43 providers.
by googleApr 2, 2026262K context$0.14/M input tokens$0.40/M output tokens43 providers
More from Meta
- 164K context
Reads text and images. Served by 5 providers.
by meta-llamaApr 29, 2025$0.18/M input tokens$0.18/M output tokens5 providers
- 512 context
Reads text. Served by 3 providers.
by meta-llamaApr 29, 2025$0.03/M input tokens$0.03/M output tokens3 providers
- 512 context
Reads text. Served by 3 providers.
by meta-llamaApr 29, 2025$0.04/M input tokens$0.04/M output tokens3 providers
- Index 10
Reads text and images. Tool calling, structured output. Served by 6 providers.
by meta-llamaApr 5, 2025128K context$0.35/M input tokens$1/M output tokens6 providers
- 430K context
Reads text and images. Tool calling, structured output. Served by 5 providers.
by meta-llamaApr 5, 2025$0.25/M input tokens$1/M output tokens5 providers
- Index 8.1
Reads text and images. Tool calling, structured output. Served by 4 providers.
by meta-llamaApr 5, 2025128K context$0.17/M input tokens$0.66/M output tokens4 providers
Llama 3.2 3B questions
How much does the Llama 3.2 3B API cost?
$0.15 per million input tokens and $0.60 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Llama 3.2 3B?
128,000 tokens of input, and it can write up to 4,096 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Does Llama 3.2 3B support tool calling?
Yes. It accepts tool definitions, which is what an agent needs to call your APIs.
Is Llama 3.2 3B open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Llama 3.2 3B released?
Sep 25, 2024, with training data up to Dec 2023.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 22, 2026. The summary is written from these facts.