# Dolphin API Pricing

As of October 10, 2026, Dolphin costs $0.50 per 1M input tokens and $0.50 per 1M output tokens on NLP Cloud. It has a 16,384-token context window and returns up to 16,384 tokens per response.

- Page: https://models.litellm.ai/models/dolphin
- LiteLLM model name: `dolphin`
- Context window: 16,384 tokens
- Max output: 16,384 tokens
- 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 |
|---|---|---|---|---|---|---|---|
| NLP Cloud | `dolphin` | $0.50 | $0.50 | – | – | – | 16K |

## Cost examples

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

- NLP Cloud: $1.25

## Use it with LiteLLM

```python
from litellm import completion

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

## FAQ

### How much does Dolphin cost?

Dolphin costs $0.50 per 1M input tokens and $0.50 per 1M output tokens on NLP Cloud.

### What is the context window of Dolphin?

Dolphin has a 16,384-token context window and returns up to 16,384 tokens per response.

### Which providers offer Dolphin?

Dolphin is available from NLP Cloud through LiteLLM, using the model name dolphin.

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

Use the LiteLLM Python SDK with model="dolphin", 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.

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