API documentation and quickstart

Authentication and setup

Generate your key via the dashboard or Google sign-in to access the API instantly.

Use the base URL HTTPS://api.deepseekapicosts.com/v1 with your unique key in the Authorization header.

Chat completions endpoint

Send messages to the model using the standard chat-completions POST method.

Our API accepts the same structure as OpenAI, allowing you to integrate without changing your existing client logic. The model ID is uncensored, and responses are returned in JSON format.

• Endpoint: POST /v1/chat/completions
• Model: uncensored

Copycurl https://api.deepseekapicosts.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate total monthly cost for 100 million tokens"}]
  }'

SDK integration

Integrate using your preferred language with minimal configuration changes.

Both Python and Node.js clients work out of the box by simply updating the base URL and API key. This ensures you can deploy your application quickly without vendor lock-in or complex migration steps.

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.deepseekapicosts.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 and usage

Enable real-time responses using Server-Sent Events (SSE) for better user experience.

Streaming reduces perceived latency by delivering tokens as they are generated. Usage statistics, including token counts, are provided in the final chunk of the stream, allowing you to track costs accurately without waiting for the full response.

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)

Parameters and formatting

Control generation behavior with standard parameters like temperature, top_p, and seed.

You can enforce JSON output using response_format for structured data needs. The model supports a 100,000-token context window, allowing for extensive conversation history or large document processing in a single request.

Rate limits and errors

Monitor your request volume to avoid interruptions during high-traffic periods.

Each API key is limited to 300 requests per minute and 8 concurrent requests. Common errors include 401 for invalid keys, 402 for insufficient prepaid credit, and 429 for rate limits. Errors and refusals do not consume your token balance.