Quickstart - Sail Research

Sail supports the OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses), and Anthropic Messages (/v1/messages) APIs. See the API support matrix for the full picture. If you are already using these APIs, switching to Sail is just a base URL and API key change.

1. Get your API key

Sign up at the Sail dashboard and create an API key.

2. Make a request

Point the SDK you already use at Sail. The OpenAI SDK works with the Chat Completions and Responses APIs, and the Anthropic SDK works with the Messages API.

Chat Completions (OpenAI)
Responses (OpenAI)
Messages (Anthropic)

from openai import OpenAI


client = OpenAI(
    base_url="https://api.sailresearch.com/v1",
    api_key="YOUR_SAIL_API_KEY",
)

completion = client.chat.completions.create(
    model="zai-org/GLM-5.3",
    messages=[{"role": "user", "content": "Explain the key ideas behind transformers."}],
)

print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.sailresearch.com/v1",
  apiKey: process.env.SAIL_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "zai-org/GLM-5.3",
  messages: [
    {
      role: "user",
      content: "Explain the key ideas behind transformers.",
    },
  ],
});

console.log(completion.choices[0].message.content);

URL=https://api.sailresearch.com/v1/chat/completions
AUTH="Authorization: Bearer YOUR_SAIL_API_KEY"

curl -s $URL \
  -H "$AUTH" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "messages": [
      {
        "role": "user",
        "content": "Explain the key ideas behind transformers."
      }
    ]
  }' | jq

from openai import OpenAI


client = OpenAI(
    base_url="https://api.sailresearch.com/v1",
    api_key="YOUR_SAIL_API_KEY",
)

response = client.responses.create(
    model="zai-org/GLM-5.3",
    input="Explain the key ideas behind transformers.",
    max_output_tokens=1000,
)

# Incomplete responses still expose their partial output.
print(response.output_text)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.sailresearch.com/v1",
  apiKey: process.env.SAIL_API_KEY,
});

const response = await client.responses.create({
  model: "zai-org/GLM-5.3",
  input: "Explain the key ideas behind transformers.",
  max_output_tokens: 1000,
});

// Incomplete responses still expose their partial output.
console.log(response.output_text);

URL=https://api.sailresearch.com/v1/responses
AUTH="Authorization: Bearer YOUR_SAIL_API_KEY"

curl -s $URL \
  -H "$AUTH" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "input": "Explain the key ideas behind transformers.",
    "max_output_tokens": 1000
  }' | jq

from anthropic import Anthropic


client = Anthropic(
    base_url="https://api.sailresearch.com",
    api_key="YOUR_SAIL_API_KEY",
)

message = client.messages.create(
    model="zai-org/GLM-5.3",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Explain the key ideas behind transformers."}],
)

# Reasoning models can return a thinking block first, so select text by type.
for block in message.content:
    if block.type == "text":
        print(block.text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://api.sailresearch.com",
  apiKey: process.env.SAIL_API_KEY,
});

const message = await client.messages.create({
  model: "zai-org/GLM-5.3",
  max_tokens: 1000,
  messages: [
    {
      role: "user",
      content: "Explain the key ideas behind transformers.",
    },
  ],
});

// Reasoning models can return a thinking block first, so select text by type.
for (const block of message.content) {
  if (block.type === "text") console.log(block.text);
}

URL=https://api.sailresearch.com/v1/messages
AUTH="x-api-key: YOUR_SAIL_API_KEY"

curl -s $URL \
  -H "$AUTH" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "max_tokens": 1000,
    "messages": [
      {
        "role": "user",
        "content": "Explain the key ideas behind transformers."
      }
    ]
  }' | jq

Next steps

Look at our full list of supported models and pricing.
Check the API support matrix for what each API supports today, and browse the full API reference for endpoints and request fields.
Using a coding agent? Connect it to the Sail docs MCP server to give it a live connection to these docs.
Email us if you have questions.