OpenAI Chat Completions
For the OpenAI SDKs and the frameworks built on them.
client = OpenAI(
base_url="https://api.zeroretentionapi.ai/v1",
api_key=os.environ["ZERO_RETENTION_API_KEY"],
)
A curated, zero-retention LLM API
Nothing you send is retained. Ever. Not by us, and not by any model provider on our list. We list a model only when its provider is bound by a written zero-retention contract. No contract, no listing.
OpenAI- and Anthropic-compatible: change the base URL, keep your code.
Early access. Public sign-up is not open yet. To get in early, email hello@zeroretentionapi.ai.
curl https://api.zeroretentionapi.ai/v1/chat/completions \
-H "Authorization: Bearer $ZERO_RETENTION_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "MODEL_ID",
"messages": [{ "role": "user", "content": "Hello" }]
}'
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.zeroretentionapi.ai/v1",
api_key=os.environ["ZERO_RETENTION_API_KEY"],
)
# MODEL_ID: any id from your model list.
reply = client.chat.completions.create(
model="MODEL_ID",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.zeroretentionapi.ai/v1",
apiKey: process.env.ZERO_RETENTION_API_KEY,
});
// MODEL_ID: any id from your model list.
const reply = await client.chat.completions.create({
model: "MODEL_ID",
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);
# Point Claude Code at the Anthropic-format endpoint.
export ANTHROPIC_BASE_URL=https://api.zeroretentionapi.ai
export ANTHROPIC_AUTH_TOKEN=$ZERO_RETENTION_API_KEY
claude
More updates soon. New models appear here when their zero-retention contract is signed.
How it works
Your app sends one request to our router. The router sends it to a model provider on our list and streams the answer back. No one on that path keeps what you sent.
Use your usual SDK. Set our base URL, your key, and a model id from your model list.
kept: nothingWe check your key and your balance, pick the provider for that model, and convert the format if needed. All in memory.
kept: nothingThe model runs at a provider on our list, under a written zero-retention contract.
kept: nothingWe stream the answer back, count the tokens, and bill the cost. The prompt and the answer are gone.
kept: billing numbers onlyZero data retention
Nothing is retained. Ever. Not by us, and not by any model provider on our list. Here is how we keep that promise.
There is no logging switch to forget. The text is never written to our storage.
The list grows as agreements are signed.
To bill you and show your usage, we record per call: which key called which model and when, the token counts and cost, timing and status, request details such as origin and user agent, and optional labels you send (for example an end-user id). Never the prompt. Never the answer.
Model list
Every listed model runs under a signed zero-retention agreement. The list grows as agreements are signed.
The model provider signs a written zero-retention contract with us.
We test it through our router on each API format before any customer call.
Your key reads the current list, with model ids, from GET /v1/models.
Need a model we do not list yet? Tell us which one. We will ask its provider for a zero-retention contract.
Quickstart
Three request formats, one key. Change the base URL, keep your code.
For the OpenAI SDKs and the frameworks built on them.
client = OpenAI(
base_url="https://api.zeroretentionapi.ai/v1",
api_key=os.environ["ZERO_RETENTION_API_KEY"],
)
For code that uses the newer OpenAI Responses API.
reply = client.responses.create(
model="MODEL_ID",
input="Hello",
)
For the Anthropic SDKs and Claude Code.
export ANTHROPIC_BASE_URL=https://api.zeroretentionapi.ai
export ANTHROPIC_AUTH_TOKEN=$ZERO_RETENTION_API_KEY
claude # Claude Code, through our endpoint
Pricing
Prepaid credits, no subscription. Each call costs what the provider charges for its tokens. We earn from the deposit fee, not from your calls.
No markup on calls. Your balance drops by the real token cost of each call, at the provider's list price for that model.
One fee when you add credits. This is how we earn: never from your calls.
| Credit you add | Fee | You pay |
|---|---|---|
| $10.00 | $0.80 | $10.80 |
| $50.00 | $2.75 | $52.75 |
| $100.00 | $5.50 | $105.50 |
For teams
Tell us your monthly volume, the models you need, and what your security team must see. A person reads every email.
Zero Retention API is a curated LLM API: one API key for many large language models, through endpoints that speak the OpenAI and Anthropic formats. Nothing you send is retained, not by us and not by any model provider on our list. We list a model only when its provider is bound by a written zero-retention contract.
Nothing you send is retained. Ever. Not by us, and not by any model provider on our list. Your request passes through our router in memory, goes to the provider, and the answer comes back the same way. We record only billing numbers: which key, which model, token counts, cost, and timing. Never the prompt, never the answer.
A written contract. We list a model only when its provider is bound by a written zero-retention contract with us. No contract, no listing. A settings toggle or a public policy page is not enough to get on the list.
The models on our curated list. Your key reads the current list, with model ids, from
GET /v1/models. The list grows as zero-retention agreements are signed.
Need a model we do not list yet? Email us and we will ask its provider.
No. A log of prompts is a copy, and a copy is retention. Our usage records hold numbers and labels, not content. Provider error messages can quote your input, so we do not store those either.
Anything that speaks the OpenAI Chat Completions, OpenAI Responses, or Anthropic Messages format. In most cases you change the base URL and the key. Claude Code works through the Anthropic format. Streaming works on all three.
Each call costs the model provider's token price, with no markup. When you add prepaid credits, we charge a deposit fee of 5.5%, minimum $0.80. There is no subscription. When the balance reaches zero, calls stop with HTTP 402 until you add credits.
No. We do not keep the content, so there is nothing to train on or to sell.
We are in early access. Public sign-up is not open yet. Email hello@zeroretentionapi.ai and we will tell you when your account can go live.
Every listed model runs under a written zero-retention contract. Get a key, add credits, and change one base URL.