TheOldAPI provides a unified API for all your AI needs. No pay-as-you-go, just a simple $5/mo subscription.
We provide API-based inference across leading models, including text generation, image generation, and more.
Smart request router that dynamically chooses the best model for every task — zero config.
Latest iteration in the GPT series with massive coding improvements.
Anthropic's most intelligent model for building agents and coding.
There are many reasons to choose us, but here are some of the most important ones.
Drop-in replacement. Works with any OpenAI SDK, LangChain, or HTTP client. Just change your base URL.
Direct provider connections with connection pooling. Sub-100ms routing overhead.
Multi-provider failover. If one backend goes down, we route to the next automatically.
Function calling, streaming, vision, embeddings — every feature works out of the box.
GPT-5.3, Claude Opus, Gemini Pro, Grok, DeepSeek, and many more — all from one API.
Native support for both OpenAI and Anthropic message formats via /v1/messages.
Browse all available models. Filter by provider or search by name.
Loading models...
No pay-as-you-go. No hidden fees. Just a simple subscription.
Full access to every model
Retrieve your API key securely
For teams with high-volume needs
Subscribe on Ko-fi with the same email you use on this site. Your API key will appear in your Dashboard automatically.
No per-token or per-request charges. The only limit is 30 requests per minute.
Yes! Point your OpenAI SDK base URL to our API and it works instantly.
Absolutely. Cancel anytime and retain access until the end of your billing period.
Subscribe on Ko-fi with the same email you use here. Sign in, go to your Dashboard, and your key appears automatically.
Sign in to access your dashboard
Welcome back, user
Subscribe on Ko-fi using the same email as your account here. Your key will appear automatically.
Subscribe to a paid plan to get your API key.
from openai import OpenAI
client = OpenAI(
base_url="https://your-api.com/v1",
api_key="YOUR_API_KEY"
)
resp = client.chat.completions.create(
model="gpt-5.3-codex",
messages=[{"role": "user",
"content": "Hello!"}]
)
print(resp.choices[0].message.content)
/v1/chat/completions
/v1/messages
/v1/models
/v1/messages/count_tokens
Everything you need to integrate TheOldAPI into your application.
TheOldAPI is fully compatible with the OpenAI SDK. Just change your base_url and
you're ready to go.
pip install openai
from openai import OpenAI
client = OpenAI(
base_url="/v1",
api_key="your-api-key"
)
response = client.chat.completions.create(
model="gpt-5.3-codex",
messages=[
{"role": "user", "content": "Hello!"}
],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta.content, end="")
All API requests require an API key passed via the Authorization header:
Authorization: Bearer YOUR_API_KEY
Get your API key from the Dashboard after signing up.
/v1/chat/completions
Create a chat completion. Supports all OpenAI-compatible parameters including
stream, tools, temperature,
max_tokens, etc.
/v1/models
List all available models. Returns model IDs and provider information.
/v1/messages
Anthropic-compatible messages endpoint. Supports Claude-format requests natively.
/v1/messages/count_tokens
Count tokens for an Anthropic-format messages request before sending.
| Plan | Requests/min | Models |
|---|---|---|
| Unlimited ($5/mo) | 30 | All 100+ |
| Enterprise | Custom | All 100+ |
Rate limit headers are included in every response: X-RateLimit-Limit,
X-RateLimit-Remaining, X-RateLimit-Reset.
Set "stream": true in your request body to receive Server-Sent Events (SSE).
Each event contains a chunk of the response.
curl /v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5.3-codex","stream":true,
"messages":[{"role":"user","content":"Hi"}]}'
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "/v1",
apiKey: "your-api-key",
});
const completion = await client.chat.completions.create({
model: "claude-sonnet-4-20250514",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);
Last updated: February 23, 2026
By accessing or using TheOldAPI ("Service"), you agree to be bound by these Terms of Service. If you do not agree, do not use the Service.
TheOldAPI provides a unified API gateway for accessing various AI language models through an OpenAI-compatible interface. The Service aggregates multiple AI providers into a single endpoint.
You must provide a valid email address and create a password to use the Service. You are responsible for maintaining the confidentiality of your account credentials and for all activities that occur under your account.
You agree not to:
Paid plans are billed monthly. You authorize us to charge your payment method on a recurring basis. You may cancel at any time; access continues until the end of the billing period. No refunds are provided for partial months.
API keys are personal and non-transferable. You are responsible for securing your keys. If you believe your key has been compromised, rotate it immediately from your dashboard. We are not liable for unauthorized use of compromised keys.
We strive for high availability but do not guarantee 100% uptime. The Service depends on third-party AI providers whose availability is outside our control. We are not liable for downtime caused by upstream providers.
You retain ownership of all content you submit through the API. We do not store, log, or train on your prompts or completions. Requests are proxied directly to the upstream provider and responses are streamed back to you.
THE SERVICE IS PROVIDED "AS IS" WITHOUT WARRANTIES OF ANY KIND. IN NO EVENT SHALL THEOLDAPI BE LIABLE FOR ANY INDIRECT, INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OF THE SERVICE.
We reserve the right to suspend or terminate your account at any time for violation of these terms or for any other reason at our sole discretion, with or without notice.
We may update these Terms at any time. Continued use of the Service after changes constitutes acceptance of the updated Terms.
For questions about these Terms, reach out on our Discord server.
Last updated: February 23, 2026
We collect the following information when you use TheOldAPI:
We take your privacy seriously. We do not:
Your information is used solely for:
When you make an API request, your prompt is sent directly to the selected upstream AI provider (e.g., OpenAI, Anthropic, Google). We act as a proxy and do not intercept, store, or modify your content. Each provider has their own privacy policy governing how they handle your data.
We employ industry-standard security measures including:
Account data is retained for the duration of your account. Usage metadata is retained for up to 90 days for billing purposes. You may request deletion of your account and associated data at any time.
We use the following third-party services:
You have the right to:
We may update this Privacy Policy from time to time. We will notify you of material changes via email or through the Service.
For privacy-related questions, reach out on our Discord server.
Join our Discord community to connect with other developers, get help, and stay updated on the latest TheOldAPI news.
Join Discord