Overview

SpiderGate is SpiderIQ's OpenAI-compatible LLM gateway — one endpoint in front of 100+ models across 18 providers. Send a request to a task alias like spideriq/fast and SpiderGate routes it to the best available model, falls back automatically on failure, caps your spend, and hands back the real per-call cost.

• Base URL — https://spideriq.ai/api/gate/v1

• Protocol — OpenAI Chat Completions, drop-in. Point any OpenAI SDK at the base URL.

• Auth — a Bearer API key.

• Version — 2.70.0

Your first request

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": "user", "content": "In one sentence, what is an LLM gateway?" }], "max_tokens": 60 }'

You never name a provider — the spideriq/fast alias picks the model, and the response tells you which one served it. Head to Chat in the API Reference to send a request from the page with Try it.

Task aliases

Route by task, not model. A few of the live aliases: spideriq/fast (low latency), spideriq/extraction (structured data/JSON), spideriq/lead-analysis (B2B scoring), spideriq/creative (SEO/multilingual copy), spideriq/coding (code gen). List them all at GET /aliases.

⚠️ Never send client PII on a free-tier alias (spideriq/fast, spideriq/free, spideriq/extraction) — route sensitive data through spideriq/lead-analysis.