Flywheel Platform
Open-weight models, fine-tuned per vertical. Self-host them on your own box for free, or call the OpenAI-compatible hosted API — change one line and the rest of your stack never notices.
curl https://gyld.dev/api/v1/chat/completions \
-H "Authorization: Bearer $FLYWHEEL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fitness",
"messages": [
{ "role": "user", "content": "Beginner full-body workout?" }
]
}'from openai import OpenAI
client = OpenAI(base_url="https://gyld.dev/api/v1", api_key="fw_live_…")
resp = client.chat.completions.create(
model="fitness",
messages=[{"role": "user", "content": "Beginner full-body workout?"}],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gyld.dev/api/v1",
apiKey: process.env.FLYWHEEL_API_KEY,
});
const resp = await client.chat.completions.create({
model: "fitness",
messages: [{ role: "user", content: "Beginner full-body workout?" }],
});
console.log(resp.choices[0].message.content);cfg := openai.DefaultConfig("fw_live_…")
cfg.BaseURL = "https://gyld.dev/api/v1"
client := openai.NewClientWithConfig(cfg)
resp, _ := client.CreateChatCompletion(ctx, openai.ChatCompletionRequest{
Model: "fitness",
Messages: []openai.ChatCompletionMessage{{Role: "user", Content: "Beginner full-body workout?"}},
})
fmt.Println(resp.Choices[0].Message.Content)Same OpenAI Chat Completions shape — point any OpenAI SDK at https://gyld.dev/api/v1.
Get started
Pick the surface that fits your stack. They both speak the OpenAI API, so you can move between them without touching your code.
Apache-2.0 open weights on your own hardware. Run them with llama.cpp or vLLM in one command — free forever, and your data never leaves the machine.
Managed inference — no hardware to run. OpenAI-compatible, with keys minted in seconds. Plans scale with the number of AI employees you run.
Guide
Follow the path that matches how you run it. Every step is a link.
Models
Every model is a fine-tune of the same base (Qwen3.6-35B-A3B, Apache-2.0) with a point-of-use guardrail baked into the weights. Each sharpens from real, consented usage.
Live
Qualifies leads, books consults, and routes new-matter intake for law firms.
Live
Handles patient scheduling, intake, and front-desk questions for clinics.
Live
Books service, quotes repairs, and answers shop questions for auto businesses.
Live
Triages service calls, schedules techs, and quotes jobs for the trades.
Live
Books appointments, manages intake, and answers client questions for salons & spas.
Live
Takes reservations, answers menu and hours questions, and handles guest requests.
Live
Programs workouts, handles memberships, and answers client questions for gyms & coaches.
Live
Prices change orders, schedules crews, and handles bid and project questions.
Live
Runs discovery, scopes builds, and handles client ops for automation agencies.
Live
Qualifies buyers, books showings, and manages listing and client follow-up.
Resources
Your first request in under a minute — hosted or self-hosted.
Every request and response field for chat completions.
Every niche model, with sizes, evals, and install commands.
Self-host free, hosted API by AI-employee count, or a private model.
The open weights — download and run them anywhere.
Create an account and put your first AI employee to work.