{
  "providers": {
    "lwcpp": {
      "baseUrl": "http://127.0.0.1:11343/v1",
      "api": "openai-completions",
      "apiKey": "no-key-required",
      "compat": {
        "supportsDeveloperRole": false,
        "supportsReasoningEffort": false,
        "maxTokensField": "max_tokens"
      },
      "models": [
        {
          "id": "gemma-4-E2B-it-UD-Q4_K_XL",
          "name": "Gemma 4 E2B · 4k — fastest on lw (~6 t/s)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 4096,
          "maxTokens": 1024,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Granite-4.0-H-Tiny",
          "name": "Granite 4.0 H Tiny · 8k — speed AND brains (~4.8 t/s)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 8192,
          "maxTokens": 2048,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3-1.7B",
          "name": "Qwen3 1.7B · 8k — thinking, snappy (~4.8 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 8192,
          "maxTokens": 2048,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3-4B-Instruct-2507",
          "name": "Qwen3 4B 2507 · 4k — daily driver (~3.9 t/s)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 4096,
          "maxTokens": 1024,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen2.5-Coder-3B-Instruct",
          "name": "Qwen2.5 Coder 3B · 8k — small coder (~3.3 t/s)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 8192,
          "maxTokens": 2048,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3-30B-A3B-Instruct-2507-UD-IQ3_XXS",
          "name": "Qwen3 30B A3B · 4k — quality when you can wait (~2.7 t/s)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 4096,
          "maxTokens": 1024,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Jan-v3-4b",
          "name": "Jan v3 4B · 4k — agentic tune (~2.6 t/s)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 4096,
          "maxTokens": 1024,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gemma-4-E4B-it-UD-Q4_K_XL",
          "name": "Gemma 4 E4B · 4k — quality; vision once mmproj added (~2.5 t/s)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 4096,
          "maxTokens": 1024,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    },
    "duskadiy": {
      "baseUrl": "https://llm.duskadiy.com/api/v1",
      "api": "openai-completions",
      "apiKey": "$DUSKADIY_API_KEY",
      "compat": {
        "supportsDeveloperRole": false,
        "supportsReasoningEffort": false,
        "maxTokensField": "max_tokens"
      },
      "models": [
        {
          "id": "gemma-4-E4B-it-UD-Q8_K_XL",
          "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 65536,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gemma-4-26B-A4B-it-UD-IQ4_XS",
          "name": "Gemma 4 26B · 24k · vision — quality generalist",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3-Coder-30B-Instruct-UD-Q3_K_XL",
          "name": "Qwen3 Coder 30B · 32k — main agent coder",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 32768,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3-Coder-Next-UD-IQ3_XXS",
          "name": "Qwen3 Coder Next 80B · 128k — long sessions",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 131072,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.6-35B-A3B-MTP-UD-IQ3_XXS",
          "name": "Qwen3.6 35B · 24k · vision — daily driver",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.6-35B-A3B-Thinking",
          "name": "Qwen3.6 35B Thinking · 24k · vision — hard problems",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.5-9B-UD-Q6_K_XL",
          "name": "Qwen3.5 9B · 32k · vision — quick tasks",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 32768,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "GLM-4.7-Flash-UD-Q4_K_XL",
          "name": "GLM-4.7 Flash · 24k — quality coder",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 24576,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b",
          "name": "gpt-oss 20B · 64k — fast reasoning + tools",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 65536,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b-low",
          "name": "gpt-oss 20B low · 64k — snappy answers",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 65536,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    },
    "localcpp": {
      "baseUrl": "http://192.168.0.204:11343/v1",
      "api": "openai-completions",
      "apiKey": "no-key-required",
      "compat": {
        "supportsDeveloperRole": false,
        "supportsReasoningEffort": false,
        "maxTokensField": "max_tokens"
      },
      "models": [
        {
          "id": "gemma-4-E4B-it-UD-Q8_K_XL",
          "name": "Gemma 4 E4B · 64k · vision — fast generalist, long docs",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 65536,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gemma-4-26B-A4B-it-UD-IQ4_XS",
          "name": "Gemma 4 26B · 24k · vision — quality generalist",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3-Coder-30B-Instruct-UD-Q3_K_XL",
          "name": "Qwen3 Coder 30B · 32k — main agent coder",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 32768,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3-Coder-Next-UD-IQ3_XXS",
          "name": "Qwen3 Coder Next 80B · 128k — long sessions",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 131072,
          "maxTokens": 16384,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.6-35B-A3B-MTP-UD-IQ3_XXS",
          "name": "Qwen3.6 35B · 24k · vision — daily driver",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.6-35B-A3B-Thinking",
          "name": "Qwen3.6 35B Thinking · 24k · vision — hard problems",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.5-9B-UD-Q6_K_XL",
          "name": "Qwen3.5 9B · 32k · vision — quick tasks",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 32768,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "GLM-4.7-Flash-UD-Q4_K_XL",
          "name": "GLM-4.7 Flash · 24k — quality coder",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 24576,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b",
          "name": "gpt-oss 20B · 64k — fast reasoning + tools",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 65536,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b-low",
          "name": "gpt-oss 20B low · 64k — snappy answers",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 65536,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    }
  }
}