# Stable Conservative Upscale API Pricing

As of October 10, 2026, Stable Conservative Upscale costs $0.40 per image on Amazon Bedrock. It has a 77-token context window.

- Page: https://models.litellm.ai/models/stable-conservative-upscale
- Lab: Stability AI
- LiteLLM model name: `stability.stable-conservative-upscale-v1:0`
- Context window: 77 tokens
- Added to LiteLLM: December 2025
- 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 |
|---|---|---|---|---|---|---|---|
| Amazon Bedrock | `stability.stable-conservative-upscale-v1:0` | – | – | – | $0.40 | – | 77 |

## Cost examples

Generating 1,000 images:

- Amazon Bedrock: $400.00

## Use it with LiteLLM

```python
from litellm import image_edit

response = image_edit(
    model="stability.stable-conservative-upscale-v1:0",
    image=open("image.png", "rb"),
    prompt="Describe your edit",
)
```

## FAQ

### How much does Stable Conservative Upscale cost?

Stable Conservative Upscale costs $0.40 per image on Amazon Bedrock.

### What is the context window of Stable Conservative Upscale?

Stable Conservative Upscale has a 77-token context window.

### Which providers offer Stable Conservative Upscale?

Stable Conservative Upscale is available from Amazon Bedrock through LiteLLM, using the model name stability.stable-conservative-upscale-v1:0.

### How do I call Stable Conservative Upscale with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="stability.stable-conservative-upscale-v1:0", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/images/edits from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### When did LiteLLM add Stable Conservative Upscale?

Stable Conservative Upscale was added to LiteLLM's model price file in December 2025.

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