# Llama3.2 3B Instruct API Pricing

As of October 10, 2026, Llama3.2 3B Instruct costs $0.015 per 1M input tokens and $0.025 per 1M output tokens from Lambda, the lowest of 8 providers. It has a 131,072-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/llama-3.2-3b-instruct
- Lab: Meta
- LiteLLM model name: `lambda_ai/llama3.2-3b-instruct`
- Context window: 131,072 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: October 2024
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Lambda | `lambda_ai/llama3.2-3b-instruct` | $0.015 | $0.025 | – | – | – | 128K |
| Amazon Bedrock | `meta.llama3-2-3b-instruct-v1:0` | $0.15 | $0.15 | – | – | – | 128K |
| Cloudflare Workers AI | `cloudflare/@cf/meta/llama-3.2-3b-instruct` | $0.0509 | $0.335 | – | – | – | 80K |
| DeepInfra | `deepinfra/meta-llama/Llama-3.2-3B-Instruct` | $0.02 | $0.02 | – | – | – | 128K |
| Hyperbolic | `hyperbolic/meta-llama/Llama-3.2-3B-Instruct` | $0.12 | $0.30 | – | – | – | 32K |
| IBM watsonx.ai | `watsonx/meta-llama/llama-3-2-3b-instruct` | $0.15 | $0.15 | – | – | – | 128K |
| Novita AI | `novita/meta-llama/llama-3.2-3b-instruct` | $0.03 | $0.05 | – | – | – | 32K |
| Together AI | `together_ai/meta-llama/Llama-3.2-3B-Instruct` | $0.06 | $0.06 | – | – | – | 128K |
| Amazon Bedrock (EU cross-region) | `eu.meta.llama3-2-3b-instruct-v1:0` | $0.19 | $0.19 | – | – | – | 128K |
| Amazon Bedrock (US cross-region) | `us.meta.llama3-2-3b-instruct-v1:0` | $0.15 | $0.15 | – | – | – | 128K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Lambda: $0.0425
- DeepInfra: $0.05
- Novita AI: $0.085
- Cloudflare Workers AI: $0.2693

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Lambda: $0.155
- DeepInfra: $0.204
- Novita AI: $0.31
- Cloudflare Workers AI: $0.576

## Features

Supported: Function calling, Parallel tool calls.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="lambda_ai/llama3.2-3b-instruct",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Llama3.2 3B Instruct cost?

Llama3.2 3B Instruct costs $0.015 per 1M input tokens and $0.025 per 1M output tokens from Lambda, the lowest of 8 providers.

### What is the context window of Llama3.2 3B Instruct?

Llama3.2 3B Instruct has a 131,072-token context window and returns up to 131,072 tokens per response.

### Which providers offer Llama3.2 3B Instruct?

Llama3.2 3B Instruct is available from 8 providers through LiteLLM: Lambda, Amazon Bedrock, Cloudflare Workers AI, DeepInfra, Hyperbolic, IBM watsonx.ai, Novita AI and Together AI. The lowest price is on Lambda.

### How do I call Llama3.2 3B Instruct with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="lambda_ai/llama3.2-3b-instruct", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Llama3.2 3B Instruct support?

Llama3.2 3B Instruct supports function calling and parallel tool calls.

### When did LiteLLM add Llama3.2 3B Instruct?

Llama3.2 3B Instruct was added to LiteLLM's model price file in October 2024.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json