# Swe 1.7 API Pricing

As of October 10, 2026, Swe 1.7 costs $0.50 per 1M input tokens and $2.50 per 1M output tokens on Cognition, with cache reads at $0.20 per 1M tokens.

- Page: https://models.litellm.ai/models/swe-1.7
- LiteLLM model name: `cognition/swe-1.7`
- Added to LiteLLM: August 21, 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 |
|---|---|---|---|---|---|---|---|
| Cognition | `cognition/swe-1.7` | $0.50 | $2.50 | $0.20 | – | – | – |

## Cost examples

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

- Cognition: $2.25

## Features

Supported: Function calling, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="cognition/swe-1.7",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Swe 1.7 cost?

Swe 1.7 costs $0.50 per 1M input tokens and $2.50 per 1M output tokens on Cognition, with cache reads at $0.20 per 1M tokens.

### Which providers offer Swe 1.7?

Swe 1.7 is available from Cognition through LiteLLM, using the model name cognition/swe-1.7.

### How do I call Swe 1.7 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="cognition/swe-1.7", 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 Swe 1.7 support?

Swe 1.7 supports function calling and prompt caching.

### When did LiteLLM add Swe 1.7?

Swe 1.7 was added to LiteLLM's model price file on August 21, 2026.

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