# Babbage 002 API Pricing

As of October 10, 2026, Babbage 002 costs $0.40 per 1M input tokens and $0.40 per 1M output tokens on OpenAI. It has a 16,384-token context window and returns up to 4,096 tokens per response.

- Page: https://models.litellm.ai/models/babbage-002
- Lab: OpenAI
- LiteLLM model name: `babbage-002`
- Context window: 16,384 tokens
- Max output: 4,096 tokens
- Deprecation date: September 28, 2026
- 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 |
|---|---|---|---|---|---|---|---|
| OpenAI | `babbage-002` | $0.40 | $0.40 | – | – | – | 16K |
| OpenAI (fine-tuned) | `ft:babbage-002` | $1.60 | $1.60 | – | – | – | 16K |

## Cost examples

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

- OpenAI: $1.00
- OpenAI batch: $0.50

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="babbage-002",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Babbage 002 cost?

Babbage 002 costs $0.40 per 1M input tokens and $0.40 per 1M output tokens on OpenAI. Batch requests cost $0.20 per 1M input tokens and $0.20 per 1M output tokens.

### What is the context window of Babbage 002?

Babbage 002 has a 16,384-token context window and returns up to 4,096 tokens per response.

### Which providers offer Babbage 002?

Babbage 002 is available from OpenAI through LiteLLM, using the model name babbage-002.

### How do I call Babbage 002 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="babbage-002", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### Is Babbage 002 being deprecated?

OpenAI deprecated babbage-002 on September 28, 2026.

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