💡Introduction

SogniLLM

SogniLLM is an OpenAI-compatible LLM inference service powered by the Sogni Supernet — a decentralized network of GPU workers. It currently runs Qwen 3.5 models and supports streaming, tool calling, and multi-turn conversations.

Because SogniLLM follows the OpenAI Chat Completions API format, any application or tool that supports a custom OpenAI-compatible endpoint can use Sogni as a backend. Just change the base URL and API key — everything else stays the same.

---

OpenAI API Compatibility

SogniLLM implements the following OpenAI-compatible endpoints:

Endpoint	Method	Description
/v1/chat/completions	POST	Create a chat completion (streaming and non-streaming)
/v1/models	GET	List available models
/v1/models/:model_id	GET	Get details for a specific model

You can use these endpoints with the OpenAI Python SDK, the OpenAI Node.js SDK, curl, or any OpenAI-compatible client.

---

Base URL

Base URL: https://api.sogni.ai

All API requests go to https://api.sogni.ai/v1/...

---

Available Models

Model ID	Display Name	Context Window	Notes
qwen3.5-35b-a3b-gguf-q4km	Qwen 3.5 35B-A3B	32K tokens	Default model. Standard Qwen 3.5 with reasoning and tool calling.
qwen3.5-35b-a3b-abliterated-gguf-q4km	Qwen 3.5 35B-A3B Abliterated	32K tokens	Uncensored variant.

Use GET /v1/models to see the current list of available models at any time.

---

Pricing

SogniLLM usage is billed in Spark or SOGNI tokens — not USD.

	Rate
Input tokens	~$0.30 per 1M tokens
Output tokens	~$0.90 per 1M tokens

You receive free starter tokens when you create an account, and you can claim a daily bonus in the app. See Supernet & Rewards for more details on acquiring tokens.

---

Getting Your API Key

1. Create a free account at app.sogni.ai

2. Go to your Account Settings

3. Copy your API Key

Your API key is used as a Bearer token in all requests:

Authorization: Bearer YOUR_API_KEY

---

Quick Test

Verify your API key works with a simple curl request:

curl https://api.sogni.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen3.5-35b-a3b-gguf-q4km",
    "messages": [
      {"role": "user", "content": "Hello! What model are you?"}
    ]
  }'

You should receive a JSON response with the model's reply in choices[0].message.content.

---

What's Next

• Open WebUI Integration — Connect SogniLLM to Open WebUI

• OpenClaw Integration — Use SogniLLM as a provider in OpenClaw