anoman
Sign InGet API Key
Documentation home

List models.

GET · /v1/models — every model available through the Anoman gateway. Updated daily from upstream catalogs.

OpenAI-compatible

GET /v1/models

Standard OpenAI shape — useful when bringing your own SDK / agent framework that expects this endpoint. Returns the slug + creation date for every model your tier has access to.

from openai import OpenAI
 
client = OpenAI(base_url="https://api.anoman.io/v1", api_key="anm-sk-...")
 
models = client.models.list()
for m in models.data:
    print(m.id)
curl https://api.anoman.io/v1/models \
  -H "Authorization: Bearer anm-sk-..."

200 — model list

{
  "object": "list",
  "data": [
    {
      "id": "deepseek-v3",
      "object": "model",
      "created": 1730000000,
      "owned_by": "anoman"
    },
    {
      "id": "claude-sonnet-4-6",
      "object": "model",
      "created": 1730000000,
      "owned_by": "anoman"
    }
  ]
}

Public catalog

GET /public/v1/pricing

For most integration use cases, the richer /public/v1/pricing endpoint is more useful. It returns pricing, modality, capabilities, and data-processing region for every public model — without authentication. Cached at our edge for 60 seconds, IP-rate-limited at 60 req/min.

# /public/v1/pricing returns richer model metadata (price + modality +
# residency). Used by our marketing /models page. No auth required;
# IP-rate-limited at 60 req/min.
curl https://api.anoman.io/public/v1/pricing
[
  {
    "modelId": "deepseek-v3",
    "provider": "siliconflow",
    "region": "id",
    "displayName": "DeepSeek V3 (SiliconFlow)",
    "tier": 2,
    "category": "chat",
    "modality": "text",
    "dataProcessingRegions": ["cn"],
    "supportsStreaming": true,
    "supportsBatch": true,
    "maxContextTokens": 128000,
    "maxOutputTokens": 4096,
    "providerInputCostPerMtok":   "0.1400",
    "providerOutputCostPerMtok":  "0.2800",
    "effectiveInputPricePerMtok": "0.1400",
    "effectiveOutputPricePerMtok":"0.2800",
    "pricingTier": "mid"
  }
]

See /docs/regional-routing for how to filter by dataProcessingRegions.

Catalog freshness

Updated daily

A nightly job at 03:00 UTC pulls the model lists from every upstream we route to, reconciles pricing, and updates the catalog. New model launches typically surface within 24 hours.

Need a model that is not in the catalog yet? Email [email protected] with the upstream model ID and we will fast-track it.

Browse the catalog.

Hundreds of LLMs; each detail page lists the model's price, context window and processing region.

On this page