Build once.
Use the best of AI.
Reach the leading models for chat, code, reasoning, and vision through one familiar API. Choose a model yourself, or let Auto choose for every request.
“Review this authentication code for security issues.”
Unlimited chat, UI tools, and provider APIs.
One subscription unlocks unlimited use across Text Generator: chat in the UI, create with the playground and built-in tools, or call the full provider network through our OpenAI-compatible API.
You describe the work.
Auto picks the model.
Use one model ID for everyday requests. Auto matches each job with a model suited to its speed, quality, and cost needs.
Your model layer, under control.
Use an exact model when consistency matters. Choose Auto when you want quality, speed, and price balanced for you.
Read the API docs arrow_forwardBuilt-in fallbacks
Keep requests moving when a provider is rate-limited or unavailable.
One credit balance
Fund once, use every routed model, and keep usage in one account.
Your keys or ours
Use the managed gateway now and retain a clean path to provider keys.
Private by design
Model selection happens without sending your prompt through another AI call.
from openai import OpenAI
client = OpenAI(
base_url="https://api.text-generator.io/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="text-generator/auto",
messages=[{"role": "user",
"content": "Ship something great"}],
)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.text-generator.io/v1",
apiKey: "YOUR_API_KEY",
});
const response = await client.chat.completions.create({
model: "text-generator/auto",
messages: [{ role: "user", content: "Ship something great" }],
});curl https://api.text-generator.io/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "text-generator/auto",
"messages": [
{"role": "user", "content": "Ship something great"}
]
}'Keep the SDK.
Change the destination.
Point the OpenAI client at Text Generator and unlock the provider network without rewriting your application.
- checkChat completions and streaming-compatible responses
- checkAliases, Auto profiles, and exact model IDs
- checkRouting metadata and provider response headers
}Open source, from API to router.
Inspect the code, run it yourself, or help shape what comes next. The complete platform is available on GitHub.
Use every surface your way.
Subscribe for unlimited chat, UI tools, and provider APIs, or start free and add API credits when you need them.