Chat Completions

Create a model response for a conversation. SpiderGate is OpenAI-compatible, so this is the same shape as OpenAI's Chat Completions — plus SpiderGate routing (model accepts a task alias) and spidergate_options.

POST /chat/completions

Authentication — Authorization: Bearer <API key> (details).

Request body

spidergate_options

Example request

cURL

curl https://spideriq.ai/api/gate/v1/chat/completions \
  -H "Authorization: Bearer $SPIDERGATE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "spideriq/fast",
    "messages": [
      { "role": "system", "content": "You are a concise assistant." },
      { "role": "user", "content": "In one sentence, what is an LLM gateway?" }
    ],
    "max_tokens": 60,
    "spidergate_options": { "max_cost_usd": 0.01 }
  }'

Python (drop-in OpenAI SDK — just change base_url)

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SPIDERGATE_API_KEY"],
    base_url="https://spideriq.ai/api/gate/v1",
)

resp = client.chat.completions.create(
    model="spideriq/fast",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "In one sentence, what is an LLM gateway?"},
    ],
    max_tokens=60,
)
print(resp.choices[0].message.content)

JavaScript (fetch)

const res = await fetch("https://spideriq.ai/api/gate/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.SPIDERGATE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "spideriq/fast",
    messages: [{ role: "user", content: "In one sentence, what is an LLM gateway?" }],
    max_tokens: 60,
  }),
});
const data = await res.json();
console.log(data.choices[0].message.content);

Response

A chat.completion object (real response from the call above):

{
  "id": "chatcmpl-721027d3a2444b09a1769d21",
  "object": "chat.completion",
  "created": 1784494387,
  "model": "nvidia_nim/meta/llama-3.1-8b-instruct",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "An LLM (Large Language Model) gateway is a software interface that enables other applications or services to access and utilize the capabilities of a large language model, such as natural language processing and generation, in a secure and scalable manner."
      }
    }
  ],
  "usage": { "prompt_tokens": 52, "completion_tokens": 47, "total_tokens": 99 }
}

Response fields

Streaming

Set "stream": true to receive chat.completion.chunk events as server-sent events, each carrying a choices[].delta fragment. The stream ends with data: [DONE].

JSON mode & tool calling

• JSON mode — "response_format": { "type": "json_object" } forces valid JSON; pass a json_schema to constrain the shape.

• Tool calling — supply tools (OpenAI function definitions); when the model calls one, finish_reason is tool_calls and message.tool_calls[] carries the calls.

Errors

Full list + handling → Errors.