# Granite Vision 3.3 2B API Pricing

As of November 21, 2026, Granite Vision 3.3 2B costs $0 per 1M input tokens and $0.25 per 1M output tokens on Replicate.

- Page: https://models.litellm.ai/models/granite-vision-3.3-2b
- LiteLLM model name: `replicate/ibm-granite/granite-vision-3.3-2b`
- Added to LiteLLM: November 11, 2026
- Prices updated: November 11, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Replicate | `replicate/ibm-granite/granite-vision-3.3-2b` | $0 | $0.25 | – | – | – | – |

## Cost examples

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

- Replicate: $0.125

## Features

Supported: Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="replicate/ibm-granite/granite-vision-3.3-2b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## Cost calculator

10,000 requests a day with 1,000 input and 500 output tokens each, at Replicate's price: $0.000125 per request, $1.25 per day, $37.50 per month (30 days).

## FAQ

### How much does Granite Vision 3.3 2B cost?

Granite Vision 3.3 2B costs $0 per 1M input tokens and $0.25 per 1M output tokens on Replicate.

### Which providers offer Granite Vision 3.3 2B?

Granite Vision 3.3 2B is available from Replicate through LiteLLM, using the model name replicate/ibm-granite/granite-vision-3.3-2b.

### How do I call Granite Vision 3.3 2B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="replicate/ibm-granite/granite-vision-3.3-2b", 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 Granite Vision 3.3 2B support?

Granite Vision 3.3 2B supports image input.

### When did LiteLLM add Granite Vision 3.3 2B?

Granite Vision 3.3 2B was added to LiteLLM's model price file on November 11, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change.
