SpiderGate

A task alias is the value you put in the model field to ask SpiderGate for a job instead of a specific model. SpiderGate resolves the alias to a ranked chain of models and serves the first one that's healthy and available, falling back automatically down the chain.

{ "model": "spideriq/coding", "messages": [...] }

There are 26 aliases in two families. The live, authoritative list — including each alias's full fallback chain and recent usage — is always available at GET /api/gate/v1/aliases (no auth required):

curl "https://spideriq.ai/api/gate/v1/aliases"

Two families

**spideriq/* (18 aliases) — tuned for workers**: scrapers, batch enrichers, single-shot LLM calls. Biased toward fast, free-tier providers (Groq, Mistral, OpenRouter free) because cost dominates at batch scale.
**agent/* (8 aliases) — tuned for live conversational agents**: chat interfaces, assistants, multi-turn sessions. Biased toward subscription primaries where multi-turn coherence and uptime beat per-token cost.

Pick the family by what's calling: a background job → spideriq/*; a user-facing agent → agent/*.

`spideriq/*` — worker aliases

::table
Alias | Use it for | Leads with
`spideriq/coding` | Code generation, debugging, refactors | Codex `gpt-5.3-codex`
`spideriq/extraction` | Structured data extraction, JSON output | Groq Llama 3.1 8B (fastest)
`spideriq/creative` | SEO copy and creative writing | Mistral Codestral
`spideriq/lead-analysis` | B2B lead analysis and scoring | Mistral Codestral
`spideriq/research` | Long-context analysis and research | Groq Llama 3.3 70B
`spideriq/research-person` | Person research reports | Groq Llama 4 Scout 17B
`spideriq/planning` | Strategic planning | Groq Llama 3.3 70B
`spideriq/tool-use` | Function calling | Groq Llama 3.3 70B
`spideriq/chat` | General conversation | Groq Llama 3.3 70B
`spideriq/classification` | Categorization tasks | Groq Llama 3.1 8B
`spideriq/summarization` | Text summarization | Groq Llama 4 Scout 17B
`spideriq/translation` | Language translation | Mistral Small
`spideriq/fast` | Lowest-latency simple tasks | Groq Llama 3.1 8B
`spideriq/vision` | Image understanding, OCR | Mistral Pixtral
`spideriq/free` | Zero-cost requests only | Groq Llama 3.1 8B
`spideriq/opvs` | OPVS symbol-notation formatting | Mistral Codestral
`spideriq/design` | Design reasoning (site cloning) | MiniMax M2.5
`spideriq/design-vision` | Multimodal design reasoning (screenshots) | Mistral Pixtral

Note: spideriq/opvs is the one alias where SpiderGate injects a system prompt — it prepends OPVS notation rules so the model emits valid symbol output. Your own messages are appended after it.

`agent/*` — live-agent aliases

::table
Alias | Use it for | Leads with
`agent/chat` | General customer-facing conversation | Codex `gpt-5.3-codex`
`agent/tool-use` | Heavy tool calling, multi-step, JSON | MiniMax M2.5
`agent/coding` | Code generation, refactors, debugging | Codex `gpt-5.3-codex`
`agent/planning` | Long-horizon planning, system design | Codex `gpt-5.3-codex`
`agent/creative` | Copywriting, brand voice, narrative | Mistral Codestral
`agent/vision` | Image understanding for agents | Mistral Pixtral
`agent/research` | Long-context, multi-document synthesis | Codex `gpt-5.3-codex`
`agent/fast` | Quick utility, classification, short replies | Groq Llama 3.1 8B

How resolution works

Resolve the alias to its configured fallback chain.
Reorder by health — models on healthy providers move to the front; models on unhealthy providers move to the back. No model is removed, so the chain always has candidates.
Try in order — call the first model; on failure (rate limit, error, timeout), move to the next.
Cross-alias fallback — if the alias's whole chain is exhausted, the request falls through to the family's general alias (spideriq/* → spideriq/chat, agent/* → agent/chat) so a request rarely fails outright.

When the model that finally served differs from the alias's first choice, the non-streaming response carries an X-SpiderGate-Fallback-From header naming that first choice. Add ?include_route_trace=true to see every attempt — see Chat Completions.

Aliases vs. direct models

You don't have to use an alias. You can pass a concrete model id (e.g. gpt-4o) to pin a single model with no fallback chain — useful when you need exactly one model. The trade-off is that you lose automatic failover. See Models & Direct Routing.

Multi-modal endpoints (images, audio, embeddings) do not use aliases — you pass the real OpenAI model name. See Images, Audio & Embeddings.

Next steps

Send a request with your chosen alias — Chat Completions.
Inspect the full live chains at GET /aliases — API Reference.
Restrict which models or aliases a token may use — Agent Keys.

Task Aliases