## Specs & substance

### Spec sheet

| Field                | Info                                                   |
|----------------------|--------------------------------------------------------|
| Developed by         | Skyfall                                                |
| Model family         | Skyfall                                                |
| Category             | compact                                                |
| Modality             | Text                                                  |
| Context window       | 128K tokens                                           |
| Architecture         | Dense FP8                                            |
| Version              | v2                                                    |
| License              | Apache 2.0                                            |
| Pricing              | $0.55 in / $0.80 out · $0.25 cache                  |
| Released             | Feb 2025                                             |
| Endpoint             | parasail-skyfall-36b-v2-fp8                          |

Fine-tuned model with enhanced instruction-following and creative output.

Skyfall 36B v2 is part of the Skyfall family by Skyfall, categorized as a **compact** model. It supports a 128K tokens context window and is built on a Dense FP8 architecture.

Key strengths: creative, instruction-tuned. Parasail serves Skyfall 36B v2 on a global fleet of current-gen GPUs behind a single OpenAI-compatible endpoint — with per-token pricing, no minimums, and dedicated capacity options when you need guaranteed throughput.

## Integrate

### Drop-in via the OpenAI SDK

Point any OpenAI-compatible chat client at Parasail and change the model name. That's it.

#### Python

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.parasail.io/v1"
)

response = client.chat.completions.create(
    model="parasail-skyfall-36b-v2-fp8",
    messages=[
        {"role": "user", "content": "Hello, what can you do?"}
    ],
    stream=True,
    stream_options={"include_usage": True},
    top_p=1,
    max_tokens=1000,
    temperature=1
)

for chunk in response:
    if chunk.choices and chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)
```

#### bash

```bash
curl https://api.parasail.io/v1/chat/completions \
  -H "Authorization: Bearer $PARASAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "parasail-skyfall-36b-v2-fp8",
    "messages": [{"role": "user", "content": "Hello, what can you do?"}],
    "stream": true,
    "max_tokens": 1000
  }'
```