{
  "schema_version": 1,
  "object": "catalog",
  "name": "Dagon Inference model catalog",
  "snapshot": true,
  "snapshot_note": "Build snapshot at price version 2026-11-02.2, as of 2026-11-02. Prices follow the providers and may have changed since; the live prices and current price version are at https://inference.dagon.so/v1/models (no key needed).",
  "live": "https://inference.dagon.so/v1/models",
  "openapi": "https://inference.dagon.so/openapi.json",
  "docs": "https://inference.dagon.so/llms.txt",
  "price_version": "2026-11-02.2",
  "updated": "2026-11-02",
  "currency": "USD",
  "price_unit": "per 1M tokens",
  "markup_bps": 1000,
  "markup_note": "Prices are USD per 1M tokens at the cheapest provider serving each model plus the 10% markup (15% in total on private zkAPI leases). A request that falls back to another provider is billed at that provider's rate plus the markup; its signed receipt names the provider. Billing is per request in whole micro-USD, rounded up once.",
  "base_urls": {
    "openai": "https://inference.dagon.so/v1",
    "anthropic": "https://inference.dagon.so"
  },
  "auth": "Authorization: Bearer <gk_ prepaid key or lk_ lease key>; Anthropic SDKs may send x-api-key instead. Create a key with POST /v1/keys.",
  "models": [
    {
      "id": "abliterated-model-large-v2",
      "name": "Abliterated Large v2",
      "description": "Flagship large model, text only, 1M context.",
      "deprecated": false,
      "url": "https://inference.dagon.so/models/abliterated-model-large-v2",
      "providers": 3,
      "provider_ids": [
        "abliteration",
        "refuseless",
        "experiential-labs"
      ],
      "provider_names": [
        "abliteration.ai",
        "Refuseless",
        "Experiential Labs"
      ],
      "cheapest_provider": "refuseless",
      "pricing": {
        "input": "1.10",
        "cached_input": "0.165",
        "output": "2.20"
      },
      "pricing_per_mtok_micros": {
        "inputPerMtok": 1100000,
        "cachedInputPerMtok": 165000,
        "outputPerMtok": 2200000
      },
      "context_length": 1048576,
      "max_output_tokens": 65536,
      "input_modalities": [
        "text"
      ],
      "endpoints": [
        "/v1/chat/completions",
        "/v1/responses",
        "/v1/messages"
      ]
    },
    {
      "id": "deepseek-v4.1-flash-abliterated",
      "name": "DeepSeek V4.1 Flash Abliterated",
      "description": "DeepSeek V4.1 Flash with refusal behavior removed, served by Refuseless. Text only, 1M context.",
      "deprecated": false,
      "url": "https://inference.dagon.so/models/deepseek-v4.1-flash-abliterated",
      "providers": 2,
      "provider_ids": [
        "refuseless",
        "experiential-labs"
      ],
      "provider_names": [
        "Refuseless",
        "Experiential Labs"
      ],
      "cheapest_provider": "refuseless",
      "pricing": {
        "input": "0.132",
        "cached_input": "0.0275",
        "output": "0.495"
      },
      "pricing_per_mtok_micros": {
        "inputPerMtok": 132000,
        "cachedInputPerMtok": 27500,
        "outputPerMtok": 495000
      },
      "context_length": 1048576,
      "max_output_tokens": 65536,
      "input_modalities": [
        "text"
      ],
      "endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
      ]
    },
    {
      "id": "glm-5.3-flash-abliterated",
      "name": "GLM-5.3 Flash Abliterated",
      "description": "GLM-5.3 Flash with refusal behavior removed, served by Refuseless. Text only, 1M context.",
      "deprecated": false,
      "url": "https://inference.dagon.so/models/glm-5.3-flash-abliterated",
      "providers": 2,
      "provider_ids": [
        "refuseless",
        "experiential-labs"
      ],
      "provider_names": [
        "Refuseless",
        "Experiential Labs"
      ],
      "cheapest_provider": "refuseless",
      "pricing": {
        "input": "0.132",
        "cached_input": "0.044",
        "output": "0.55"
      },
      "pricing_per_mtok_micros": {
        "inputPerMtok": 132000,
        "cachedInputPerMtok": 44000,
        "outputPerMtok": 550000
      },
      "context_length": 1048576,
      "max_output_tokens": 65536,
      "input_modalities": [
        "text"
      ],
      "endpoints": [
        "/v1/chat/completions",
        "/v1/responses"
      ]
    },
    {
      "id": "abliterated-model-large-flash",
      "name": "Abliterated Large Flash",
      "description": "Fast large model with a 1M context window and image input.",
      "deprecated": false,
      "url": "https://inference.dagon.so/models/abliterated-model-large-flash",
      "providers": 1,
      "provider_ids": [
        "abliteration"
      ],
      "provider_names": [
        "abliteration.ai"
      ],
      "cheapest_provider": "abliteration",
      "pricing": {
        "input": "1.10",
        "cached_input": "0.11",
        "output": "2.20"
      },
      "pricing_per_mtok_micros": {
        "inputPerMtok": 1100000,
        "cachedInputPerMtok": 110000,
        "outputPerMtok": 2200000
      },
      "context_length": 1048576,
      "max_output_tokens": 65536,
      "input_modalities": [
        "text",
        "image"
      ],
      "endpoints": [
        "/v1/chat/completions",
        "/v1/responses",
        "/v1/messages"
      ]
    },
    {
      "id": "abliterated-model",
      "name": "Abliterated Model",
      "description": "General model with text and image input.",
      "deprecated": false,
      "url": "https://inference.dagon.so/models/abliterated-model",
      "providers": 1,
      "provider_ids": [
        "abliteration"
      ],
      "provider_names": [
        "abliteration.ai"
      ],
      "cheapest_provider": "abliteration",
      "pricing": {
        "input": "1.10",
        "cached_input": "0.11",
        "output": "3.30"
      },
      "pricing_per_mtok_micros": {
        "inputPerMtok": 1100000,
        "cachedInputPerMtok": 110000,
        "outputPerMtok": 3300000
      },
      "context_length": 262144,
      "max_output_tokens": 65536,
      "input_modalities": [
        "text",
        "image"
      ],
      "endpoints": [
        "/v1/chat/completions",
        "/v1/responses",
        "/v1/messages"
      ]
    },
    {
      "id": "abliterated-model-large",
      "name": "Abliterated Large",
      "description": "Previous large model. Deprecated upstream; kept for existing integrations.",
      "deprecated": true,
      "url": null,
      "providers": 1,
      "provider_ids": [
        "abliteration"
      ],
      "provider_names": [
        "abliteration.ai"
      ],
      "cheapest_provider": "abliteration",
      "pricing": {
        "input": "3.30",
        "cached_input": "0.33",
        "output": "5.50"
      },
      "pricing_per_mtok_micros": {
        "inputPerMtok": 3300000,
        "cachedInputPerMtok": 330000,
        "outputPerMtok": 5500000
      },
      "context_length": 1000000,
      "max_output_tokens": 65536,
      "input_modalities": [
        "text"
      ],
      "endpoints": [
        "/v1/chat/completions",
        "/v1/responses",
        "/v1/messages"
      ]
    }
  ]
}