Integration docs

# chat completion (streaming)
curl https://nieotoken.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-****" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

# list models
curl https://nieotoken.com/v1/models \
  -H "Authorization: Bearer sk-****"

from openai import OpenAI

client = OpenAI(
    api_key="sk-****",                     # your key
    base_url="https://nieotoken.com/v1",   # NieoToken
)

resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user",
               "content": "Hello"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-****",
  baseURL: "https://nieotoken.com/v1",
});

const res = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(res.choices[0].message.content);

import OpenAI from "openai";

const stream = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: messages,
  stream: true,                  // SSE stream
});

for await (const chunk of stream) {
  process.stdout.write(
    chunk.choices[0]?.delta?.content ?? ""
  );
}

const res = await client.chat.completions.create({
  model: "deepseek-v4-flash-vision-exp",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "What is in this screenshot?" },
      { type: "image_url",
        image_url: { url: "data:image/png;base64,..." } }
    ]
  }]
});

# NieoToken spreads requests across multiple
# upstream accounts and retries once on failure,
# so a sustained batch does not need you to
# rotate keys or run your own pooling layer.

# Keep concurrency sane and let the gateway
# handle upstream hiccups:
for prompt in prompts:
    try:
        out.append(call(prompt))
    except RateLimitError:
        backoff(); retry(prompt)