desirecore/config-center
2
0
Fork 0
mirror of https://git.openapi.site/https://github.com/desirecore/config-center.git synced 2026-09-05 17:53:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: consolidate smart routing into model specs (#75)

Browse Source
This commit is contained in:
yi-ge
2026-08-10 19:13:08 +08:00
committed by GitHub
parent ed0aeccf29
commit ad8c515938
32 changed files with 3907 additions and 2021 deletions
Download Patch File Download Diff File Expand all files Collapse all files

173
compute/model-specs/moonshot.json
View File

@@ -5,29 +5,90 @@
"id": "kimi-k3",
"displayName": "Kimi K3",
"family": "kimi-k3",
"match": { "exact": ["kimi-k3"], "patterns": ["kimi-k3*"] },
"match": {
"exact": [
"kimi-k3"
],
"patterns": [
"kimi-k3*"
]
},
"spec": {
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"capabilities": ["chat", "reasoning", "code", "tool_use", "agent", "long_context", "vision"],
"serviceType": ["reasoning"],
"capabilities": [
"chat",
"reasoning",
"code",
"tool_use",
"agent",
"long_context",
"vision"
],
"serviceType": [
"reasoning"
],
"supportsReasoning": true,
"description": "Moonshot Kimi K3 — 2.8T 参数多模态推理模型，默认 reasoning_effort=max，始终启用思考"
},
"routing": {
"tier": "flagship",
"routingPriority": 35,
"eligibleForAgent": true,
"defaultReference": false,
"reasoning": {
"supportedModes": [
"auto",
"off",
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"defaultMode": "high"
}
}
},
{
"id": "kimi-k2.7-code",
"displayName": "Kimi K2.7 Code",
"family": "kimi-k2.7",
"match": { "exact": ["kimi-k2.7-code"], "patterns": ["kimi-k2.7-code*"] },
"match": {
"exact": [
"kimi-k2.7-code"
],
"patterns": [
"kimi-k2.7-code*"
]
},
"spec": {
"contextWindow": 262144,
"maxOutputTokens": 16384,
"capabilities": ["chat", "code", "vision", "tool_use"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"code",
"vision",
"tool_use"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true,
"description": "Moonshot Kimi K2.7 Code 编程专用模型"
},
"routing": {
"tier": "balanced",
"routingPriority": 50,
"eligibleForAgent": true,
"defaultReference": false,
"reasoning": {
"supportedModes": [
"auto"
],
"defaultMode": "auto"
}
}
},
{
@@ -37,10 +98,38 @@
"spec": {
"contextWindow": 262144,
"maxOutputTokens": 16384,
"capabilities": ["chat", "reasoning", "code", "tool_use", "agent", "long_context", "vision"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"tool_use",
"agent",
"long_context",
"vision"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true
},
"routing": {
"tier": "balanced",
"routingPriority": 45,
"eligibleForAgent": true,
"defaultReference": false,
"reasoning": {
"supportedModes": [
"auto",
"off",
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"defaultMode": "medium"
}
}
},
{
@@ -50,8 +139,18 @@
"spec": {
"contextWindow": 256000,
"maxOutputTokens": 32768,
"capabilities": ["chat", "reasoning", "code", "tool_use", "agent", "long_context", "vision"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"tool_use",
"agent",
"long_context",
"vision"
],
"serviceType": [
"chat"
],
"defaultTemperature": 1,
"supportsReasoning": true
}
@@ -63,8 +162,16 @@
"spec": {
"contextWindow": 256000,
"maxOutputTokens": 16384,
"capabilities": ["reasoning", "math", "code", "deep_thinking", "long_context"],
"serviceType": ["reasoning"],
"capabilities": [
"reasoning",
"math",
"code",
"deep_thinking",
"long_context"
],
"serviceType": [
"reasoning"
],
"defaultTemperature": 1,
"supportsReasoning": true
}
@@ -76,8 +183,17 @@
"spec": {
"contextWindow": 256000,
"maxOutputTokens": 8192,
"capabilities": ["chat", "reasoning", "code", "tool_use", "agent", "long_context"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"reasoning",
"code",
"tool_use",
"agent",
"long_context"
],
"serviceType": [
"chat"
],
"defaultTemperature": 0.6,
"supportsReasoning": true
}
@@ -89,8 +205,13 @@
"spec": {
"contextWindow": 8192,
"maxOutputTokens": 4096,
"capabilities": ["chat", "code"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"code"
],
"serviceType": [
"chat"
],
"defaultTemperature": 0
}
},
@@ -101,8 +222,14 @@
"spec": {
"contextWindow": 32768,
"maxOutputTokens": 4096,
"capabilities": ["chat", "code", "long_context"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"code",
"long_context"
],
"serviceType": [
"chat"
],
"defaultTemperature": 0
}
},
@@ -113,8 +240,14 @@
"spec": {
"contextWindow": 131072,
"maxOutputTokens": 4096,
"capabilities": ["chat", "code", "long_context"],
"serviceType": ["chat"],
"capabilities": [
"chat",
"code",
"long_context"
],
"serviceType": [
"chat"
],
"defaultTemperature": 0
}
}