Dolphin modelos API Quickstart

Base URL and Authentication

The Dolphin modelos API is an OpenAI-compatible service. Set your base URL to https://api.dolphinmodelos.com/v1 and pass your API key in the Authorization header. Use the model ID uncensored for inference. This ensures compatibility with standard SDKs without custom routing logic.

Copycurl https://api.dolphinmodelos.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List endpoints for wallet connection via crypto gateway"}]
  }'

Sending a Completion Request

Send a simple text prompt to generate responses. The API accepts standard parameters like temperature and top_p. You receive pure text output without unnecessary wrappers. This direct approach eliminates the need for model-specific parsing logic.

Copyfrom openai import OpenAI

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

Streaming Responses with SSE

Enable real-time token generation using Server-Sent Events. The final chunk includes the full token usage statistics for billing accuracy. Streaming reduces perceived latency for long outputs. This method is ideal for interactive applications requiring immediate feedback.

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)

Function Calling and Tools

Define tools to let the model execute specific actions. Use tool_choice to enforce function usage. The API supports standard tool definitions and returns structured arguments. This enables complex workflows without external parsing scripts. Configure tools via the standard OpenAI format for seamless integration.

JSON Mode for Structured Output

Force the model to return valid JSON using response_format: {"type": "json_object"}. This ensures consistent data structures for downstream processing. Ideal for API responses or database inserts. The model adheres to the schema without adding conversational filler text.

Error Handling and Limits

The context window is 100,000 tokens total. Handle errors like 401 for invalid keys or 429 for rate limits. The API enforces 300 requests per minute. Use these codes to manage retries efficiently. Errors and refusals do not consume credit, protecting your balance during testing phases.

Node.js

Copyimport OpenAI from "openai";

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