Dolphin models ai API Quickstart
Dolphin models AI provides a straightforward OpenAI-compatible API for uncensored inference. This quickstart guides you through authentication, sending requests, and handling streaming data with predictable per-token billing.
1. Prerequisites: SDK and API Key
Sign up using your Google account or email to receive an API key instantly. You need the official SDK for your preferred language to communicate with the endpoint. The key authenticates every request you send.
2. Configure Your Base URL
Set the base URL to HTTPS://api.dolphinmodelsai.com/v1 in your client configuration. This URL routes your requests to our uncensored inference servers. Ensure your API key is passed in the authorization header. The endpoint follows standard OpenAI patterns for compatibility.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.dolphinmodelsai.com/v1", apiKey: process.env.API_KEY });
const resp = await client.chat.completions.create({
model: "uncensored",
messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);3. Send Your First Chat Completion Request
Send a POST request to /v1/chat/completions with the model id "uncensored". Include your message history in the messages array. The API returns a text response without content refusals for lawful adult use. You can adjust parameters like temperature to control randomness.
curl https://api.dolphinmodelsai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Calculate the time complexity of this sorting algorithm"}]
}'4. Enable Streaming and Handle Token Usage
Set streaming to true to receive tokens as they are generated. Each chunk contains partial text and usage metadata. The final chunk includes the total token count for billing accuracy. This approach reduces perceived latency for long responses.
stream = client.chat.completions.create(
model="uncensored",
messages=[{"role": "user", "content": "Tell the story in second person."}],
stream=True,
)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)5. Use JSON Mode for Structured Output
Pass response_format as {"type": "json_object"} to enforce structured output. The model guarantees valid JSON syntax in the response. This feature is ideal for parsing data into your application logic. It eliminates the need for manual regex validation.
6. Implement Function Calling (Tools)
Define tools in your request to enable function calling capabilities. The model can return tool calls instead of plain text. You execute the function and send the result back to the model. This pattern supports complex multi-step workflows.
7. Understand Rate Limits and Parameters
Each API key is limited to 300 requests per minute. You can have 8 concurrent requests at any time. The context window supports up to 100,000 tokens for input and output combined. Requests exceeding these limits receive a 429 error code. Credit errors return a 402 status.
Python
from openai import OpenAI
client = OpenAI(base_url="https://api.dolphinmodelsai.com/v1", api_key="YOUR_KEY")
resp = client.chat.completions.create(
model="uncensored",
messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)Common questions
How do I authenticate my requests?
Include your API key in the Authorization header as a Bearer token. The key is generated immediately after signup. It remains valid until you revoke or replace it.
What happens if I exceed the rate limit?
The API returns a 429 Too Many Requests error. You must wait until the rate window resets. Concurrent request limits also apply to prevent resource exhaustion.
Is the uncensored model free?
No, it uses prepaid credit charged per token. You receive trial credit for new accounts. Billing is transparent with no hidden monthly fees.
