113 lines
3.2 KiB
JSON
113 lines
3.2 KiB
JSON
{
|
|
"providers": {
|
|
"llama-serve-remote": {
|
|
"baseUrl": "http://192.168.1.214:8080/v1",
|
|
"api": "openai-completions",
|
|
"apiKey": "dummy",
|
|
"compat": {
|
|
"supportsDeveloperRole": false,
|
|
"supportsReasoningEffort": false
|
|
},
|
|
"models": [
|
|
{
|
|
"id": "unsloth/gemma-4-12b-it-GGUF:UD-Q4_K_XL",
|
|
"name": "Gemma 4 12B IT",
|
|
"reasoning": false,
|
|
"input": ["text"],
|
|
"contextWindow": 32768,
|
|
"maxTokens": 32768,
|
|
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
|
|
}
|
|
]
|
|
},
|
|
"llama-serve": {
|
|
"baseUrl": "http://localhost:8080/v1",
|
|
"api": "openai-completions",
|
|
"apiKey": "dummy",
|
|
"compat": {
|
|
"supportsDeveloperRole": false,
|
|
"supportsReasoningEffort": false
|
|
},
|
|
"models": [
|
|
{
|
|
"id": "Qwen/Qwen3-9B",
|
|
"name": "Qwen3.5-9B (Unsloth)",
|
|
"reasoning": true,
|
|
"input": ["text"],
|
|
"contextWindow": 131072,
|
|
"maxTokens": 8192,
|
|
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
|
|
}
|
|
]
|
|
},
|
|
"opencode-go": {
|
|
"baseUrl": "https://opencode.ai/zen/go/v1",
|
|
"api": "openai-completions",
|
|
"apiKey": "OPENCODE_API_KEY",
|
|
"models": [
|
|
{
|
|
"id": "mimo-v2-pro",
|
|
"name": "MiMo-V2-Pro",
|
|
"reasoning": true,
|
|
"input": ["text"],
|
|
"contextWindow": 1048576,
|
|
"maxTokens": 131072,
|
|
"cost": { "input": 0.5, "output": 2.0, "cacheRead": 0.1, "cacheWrite": 0 }
|
|
},
|
|
{
|
|
"id": "glm-5",
|
|
"name": "GLM-5",
|
|
"reasoning": true,
|
|
"input": ["text"],
|
|
"contextWindow": 202752,
|
|
"maxTokens": 131072,
|
|
"cost": { "input": 1.0, "output": 3.2, "cacheRead": 0.2, "cacheWrite": 0 }
|
|
},
|
|
{
|
|
"id": "glm-5.1",
|
|
"name": "GLM-5.1",
|
|
"reasoning": true,
|
|
"input": ["text"],
|
|
"contextWindow": 204800,
|
|
"maxTokens": 131072,
|
|
"cost": { "input": 1.0, "output": 3.2, "cacheRead": 0.2, "cacheWrite": 0 }
|
|
},
|
|
{
|
|
"id": "kimi-k2.5",
|
|
"name": "Kimi K2.5",
|
|
"reasoning": true,
|
|
"input": ["text", "image"],
|
|
"contextWindow": 262144,
|
|
"maxTokens": 131072,
|
|
"cost": { "input": 0.6, "output": 3.0, "cacheRead": 0.1, "cacheWrite": 0 }
|
|
}
|
|
]
|
|
},
|
|
"opencode": {
|
|
"baseUrl": "https://opencode.ai/zen/v1",
|
|
"api": "openai-completions",
|
|
"apiKey": "OPENCODE_API_KEY",
|
|
"models": [
|
|
{
|
|
"id": "big-pickle",
|
|
"name": "Big Pickle",
|
|
"reasoning": true,
|
|
"input": ["text"],
|
|
"contextWindow": 200000,
|
|
"maxTokens": 128000,
|
|
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
|
|
},
|
|
{
|
|
"id": "qwen3.6-plus-free",
|
|
"name": "Qwen 3.6 Plus",
|
|
"reasoning": true,
|
|
"input": ["text"],
|
|
"contextWindow": 1048576,
|
|
"maxTokens": 131072,
|
|
"cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|