Model Catalog

The LLM API supports models from 4 providers, managed dynamically via the model catalog.

Providers

Provider	Models
OpenAI	GPT-4.1, GPT-4.1-mini, GPT-4.1-nano, o3, o3-mini, o4-mini
Anthropic	Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5
Google	Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite
Grok	Grok 3, Grok 3 Mini, Grok 4 Fast, Grok Code Fast

Model ID Format

Models use the provider.model format:

openai.gpt-4.1-nano
anthropic.claude-sonnet-4-6
google.gemini-2.5-flash
grok.grok-3-mini

---

Model Tiers

Models are grouped into tiers based on capability. Your plan determines which tiers you can access via the Zihin pool:

Tier	Examples	Plans (pool)
economical	GPT-4.1-nano, Haiku 4.5, Gemini Flash Lite, Grok 3 Mini	All plans
premium	GPT-4.1, Sonnet 4.6, Gemini Flash, Grok 4 Fast	Core, Pro, Business
flagship	Claude Opus 4.6, o3, Gemini 2.5 Pro	Pro, Business

BYOK unlocks all tiers

If you configure your own provider key (BYOK), all models from that provider become available regardless of your plan. See Secrets & Provider Keys for setup.

Requesting a model outside your plan's allowed tiers returns HTTP 403:

{
  "error": "MODEL_TIER_RESTRICTED",
  "details": {
    "model_tier": "flagship",
    "plan_code": "basic",
    "allowed_tiers": ["economical", "premium"]
  }
}

---

GET /api/llm/models

List all available models.

Authentication: Not required — Cache: 5 minutes

{
  "success": true,
  "count": 29,
  "models": [
    {
      "id": "openai.gpt-4.1-nano",
      "name": "GPT-4.1 Nano",
      "provider": "openai",
      "tier": "economical",
      "context": "1048576",
      "capabilities": ["chat", "code", "function_calling"],
      "performance": { "latency": 9, "quality": 6, "cost": 9 }
    }
  ]
}

Field	Description
id	Full model ID (provider.model)
provider	openai, anthropic, google, grok
tier	economical, premium, flagship
context	Context window (tokens)
capabilities	Model capabilities
performance	Scores 1-10 (latency, quality, cost)

---

GET /api/llm/provider/:provider

Get models for a specific provider.

Authentication: Not required — Cache: 15 minutes

GET /api/llm/provider/openai

{
  "success": true,
  "provider": "openai",
  "supportedModels": ["gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "o3", "o3-mini", "o4-mini"],
  "modelCount": 6
}