Dolphin API Quickstart Guide

Authentication: Bearer Tokens

Authentication requires a Bearer token sent in the Authorization header.

Get your key from the dashboard or use the trial credit. Every request must include this header to prove identity.

Keep the key secure. Share it only with trusted services.

The /v1/chat/completions Endpoint

This endpoint processes text input and returns text output.

Send requests to https://api.whatisdolphin.com/v1 with your model ID and messages.

Use this structure for basic interactions.

Streaming Responses with SSE

Streaming allows real-time token delivery via Server-Sent Events.

Set stream to true in your request payload.

Parse the chunks as they arrive to build a continuous output.

Function Calling and JSON Mode

Function calling lets models execute tools based on your instructions.

Use JSON mode to enforce strict schema compliance for structured data.

Define tools in the request to guide the model's behavior.

Context Window and Token Limits

The context window supports 100,000 tokens total.

Output limits vary: set max_tokens for control, otherwise default to 2,048 tokens.

Manage input length to stay within bounds for optimal performance.

Rate Limits and Error Handling

Rate limits allow 300 requests per minute per key.

Handle 401 errors for invalid keys and 429 for rate limits.

Monitor usage to avoid service interruptions during high volume.

cURL

Copycurl https://api.whatisdolphin.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Define what a dolphin is in two lines."}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.whatisdolphin.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)

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.whatisdolphin.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);

Streaming

Copystream = 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)