BLTYAPI

1 Overview

BLTYAPI provides an interface that is fully compatible with the OpenAI API. You can use any OpenAI-compatible SDK or HTTP client to connect directly, with no code changes required.

2 Authentication

All API requests must include an Authorization Bearer Token in the HTTP header. You can obtain your API Key from the BLTYAPI dashboard.

Authorization: Bearer <YOUR_BLTYAPI_KEY>

3 Chat Completions

Send a POST request to /v1/chat/completions to get a model-generated response. This endpoint is fully compatible with OpenAI's Chat Completions format.

cURL Example

curl https://api.jdlbags.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_BLTYAPI_KEY" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Write a poem about the ocean."}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }' | jq .

Python Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Write a poem about the ocean."}
    ],
    temperature=0.7,
    max_tokens=1024
)

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

Response Example

{
  "id": "chatcmpl-9a8b7c6d5e4f3a2b1c0d",
  "object": "chat.completion",
  "created": 1734567890,
  "model": "deepseek-chat",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "碧波万顷接天流，\n浪涌千层送远舟。\n日月沉浮皆过客，\n一怀浩气写春秋。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 30,
    "completion_tokens": 32,
    "total_tokens": 62
  }
}

Streaming

Set stream: true to enable Server-Sent Events (SSE) streaming output, receiving content token by token.

from openai import OpenAI

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

stream = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Introduce Shanghai in 50 words."}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

4 Models

Query the list of available models. This endpoint is compatible with the OpenAI Models API format.

GET https://api.jdlbags.com/v1/models

Available Models

cURL Query Example

curl https://api.jdlbags.com/v1/models \\\
      -H "Authorization: Bearer YOUR_BLTYAPI_KEY" | jq .

Python: List Models

from openai import OpenAI

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

models = client.models.list()
for model in models:
    print(f"{model.id} - {model.owned_by}")

5 Error Codes

BLTYAPI follows the OpenAI error format for returning error information. Below are common error codes and how to handle them:

{
  "error": {
    "message": "Incorrect API key provided: sk-***. You can find your API key at ...",
    "type": "authentication_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

6 Rate Limits

To ensure service stability, BLTYAPI enforces rate limits on API requests. Requests exceeding the limit will return 429 Too Many Requests.

Response Headers