🚀 3-Minute Quick Start
GPU Compute & AI Models
Quick Deployment Guide
From registration to production in as fast as 3 minutes. Works with Python, curl, or OpenAI SDK — zero learning curve.
Three Ways to Integrate
Choose your preferred dev method — configure in under 3 minutes
📝
OpenAI SDK
Use the official OpenAI Python SDK — just change the base URL and API key to switch to FlowerWolf.
Python
💻
curl CLI
No SDK needed. One curl command to call any model. Great for quick tests, scripts, and shell automation.
Shell / CLI
🛠
REST API
Standard HTTPS REST API — works with Go, Java, Node.js, PHP and more.
Multi-language
Code Examples
Copy-paste to run, no business logic changes needed
Python / OpenAI SDK
from openai import OpenAI
client = OpenAI(
api_key="fw_xxxxxxxxxxxxxxxx",
base_url="https://api.flowerwolf.net/v1"
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Random text? Answer in two sentences"}]
)
print(response.choices[0].message.content)
curl / Shell
curl https://api.flowerwolf.net/v1/chat/completions \\
-H "Authorization: Bearer fw_xxxxxxxxxxxxxxxx" \\
-H "Content-Type: application/json" \\
-d '{"model":"gpt-4o","messages":[{"role":"user","content":"What day of the week is it?"}]}'
JavaScript / Node.js
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: "fw_xxxxxxxxxxxxxxxx",
baseURL: "https://api.flowerwolf.net/v1",
});
const chat = await client.chat.completions.create({
model: "gpt-4o",
messages: [{role: "user", content: "用两句话回答，What day of the week is it?"}],
});
console.log(chat.choices[0].message.content);
Supported Models
One Key for all models — no switching required
GPT-4o
GPT-4o Mini
Claude 3.5 Sonnet
Claude 3 Haiku
Gemini 1.5 Pro
Gemini 1.5 Flash
DeepSeek V3
DeepSeek Chat
Qwen 2.5 72B
Qwen 2.5 7B
LLaMA 3.1 405B
Mistral Large 2
Stable Diffusion XL
Whisper Large V3
Use Cases
Recommended models and GPU config by use case
💻
AI App Development
Integrate fast with OpenAI SDK — just replace base URL in your existing code. Works with LangChain, LlamaIndex and all major frameworks.
📈
Data Processing Pipeline
Gemini 1.5 Flash is extremely low cost — perfect for batch document analysis, content moderation, data cleaning. GPU compute for parallel high-throughput processing.
🎨
AI Image / Video Generation
Stable Diffusion XL image generation accelerated by H100 / A100 80GB GPU clusters. FLUX.1 coming soon with fine-grained control.
💬
Customer Service / Chat
Claude 3.5 Sonnet 200K context for long memory, GPT-4o multimodal with image input. DeepSeek low price for high-concurrency.
FAQ FAQ
Which models are API-compatible?▼
FlowerWolf API follows OpenAI Chat Completions format — supports GPT-4o, Claude 3.5, Gemini 1.5, DeepSeek V3, Qwen, LLaMA, Mistral and all 14+ major models. Replace base URL, set model name.
Are there rate limits?▼
Different tiers have RPM and TPM limits. Startup: 60 RPM / 100K TPM. Enterprise can get higher limits. Contact us for unlimited.
Is data retained or used for training?▼
Absolutely not. FlowerWolf never retains, inspects, or uses your data for training. Deleted immediately after computation. DPAs available on request.
Can GPU compute and API models be used together?▼
Yes — FlowerWolf core advantage. Deploy your own models on our GPUs (vLLM / TensorRT-LLM) while calling FlowerWolf API models, all under one unified billing account.
Is streaming / WebSocket output supported?▼
Yes. OpenAI SDK stream=True works directly. FlowerWolf returns Server-Sent Events (SSE). For curl: add -N flag to disable buffering for real-time output.
Ready to Start?
Get your API key in 1 minute after signup and start calling immediately