{
  "providers": {
    "wmcpp": {
      "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": "Qwen3.5-9B-Q4_K_M",
          "name": "Qwen3.5 9B · 16k · vision — daily driver (33 t/s)",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 16384,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.5-9B-Thinking",
          "name": "Qwen3.5 9B Thinking · 16k · vision — hard problems (38 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 16384,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.5-9B-MTP",
          "name": "Qwen3.5 9B MTP · 8k · vision — quiet desktop only (57 t/s)",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 8192,
          "maxTokens": 2048,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gemma-4-E4B-it-UD-Q4_K_XL",
          "name": "Gemma 4 E4B · 32k · vision — fastest, long docs (85 t/s)",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 32768,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Mellum2.1-12B-A2.5B-Thinking-IQ4_XS",
          "name": "Mellum 2.1 12B A2.5B · 16k — fast reasoning coder (63–87 t/s)",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 16384,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Ornith-1.5-35B-A3B-instant",
          "name": "Ornith 35B A3B instant · 16k — agentic coder (14–21 t/s busy, 31 quiet)",
          "reasoning": false,
          "input": ["text"],
          "contextWindow": 16384,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Ornith-1.5-35B-A3B-IQ4_XS",
          "name": "Ornith 35B A3B thinking · 16k — coder with reasoning (10 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 16384,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b",
          "name": "gpt-oss 20B · 32k — reasoning + tools (17 t/s)",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 32768,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b-low",
          "name": "gpt-oss 20B low · 32k — snappy answers (17 t/s)",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 32768,
          "maxTokens": 8192,
          "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 (~57 t/s)",
          "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 (~34 t/s)",
          "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 (~30 t/s)",
          "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 (~16 t/s)",
          "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 (~36 t/s)",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.6-35B-A3B-Thinking",
          "name": "Qwen3.6 35B Thinking · 24k · vision — hard problems (~39 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "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 (~32 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 32768,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.8-27B-UD-IQ3_XXS",
          "name": "Qwen3.8 27B · 24k · vision — hybrid reasoner, quiet desktop only (~15 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "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 (~21 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "GLM-4.7-Flash-UD-Q3_K_XL",
          "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Ornith-1.5-35B-A3B-IQ3_XXS",
          "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b",
          "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)",
          "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 (~37 t/s)",
          "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 (~57 t/s)",
          "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 (~34 t/s)",
          "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 (~30 t/s)",
          "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 (~16 t/s)",
          "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 (~36 t/s)",
          "reasoning": false,
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.6-35B-A3B-Thinking",
          "name": "Qwen3.6 35B Thinking · 24k · vision — hard problems (~39 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "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 (~32 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 32768,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Qwen3.8-27B-UD-IQ3_XXS",
          "name": "Qwen3.8 27B · 24k · vision — hybrid reasoner, quiet desktop only (~15 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "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 (~21 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "GLM-4.7-Flash-UD-Q3_K_XL",
          "name": "GLM-4.7 Flash Q3 · 24k — fast coder (~28 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "Ornith-1.5-35B-A3B-IQ3_XXS",
          "name": "Ornith 1.5 35B · 24k · vision — agentic coder, thinking (~32 t/s)",
          "reasoning": true,
          "compat": { "thinkingFormat": "qwen-chat-template" },
          "input": ["text", "image"],
          "contextWindow": 24576,
          "maxTokens": 4096,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        },
        {
          "id": "gpt-oss-20b",
          "name": "gpt-oss 20B · 64k — fast reasoning + tools (~38 t/s)",
          "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 (~37 t/s)",
          "reasoning": true,
          "input": ["text"],
          "contextWindow": 65536,
          "maxTokens": 8192,
          "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
        }
      ]
    }
  }
}