Reference
Hober-Specific Features
Model Fallbacks
Pass an array of models in the models field. Hober tries each in order until one succeeds. If the primary model is down or rate-limited, the next model is used automatically.
{
"models": [
"deepseek/deepseek-chat-v3.2",
"qwen/qwen3-235b",
"glm/glm-4-plus"
],
"messages": [{"role": "user", "content": "Hello"}]
}Provider Preferences
Control which providers are used for routing with the provider field.
| Parameter | Type | Required | Description |
|---|---|---|---|
| provider.sort | string | optional | "price" (cheapest first) or "latency" (fastest first) |
| provider.only | array | optional | Only use these providers: ["deepseek", "qwen"] |
| provider.ignore | array | optional | Never use these providers: ["glm"] |
provider.sortstringoptional
"price" (cheapest first) or "latency" (fastest first)
provider.onlyarrayoptional
Only use these providers: ["deepseek", "qwen"]
provider.ignorearrayoptional
Never use these providers: ["glm"]
{
"model": "deepseek/deepseek-chat-v3.2",
"messages": [{"role": "user", "content": "Hello"}],
"provider": {
"sort": "latency",
"ignore": ["glm"]
}
}Model Suffixes
Append routing hints to any model slug:
| Suffix | Behavior | Example |
|---|---|---|
| :nitro | Prefer lowest-latency provider endpoint | deepseek/deepseek-chat-v3.2:nitro |
| :floor | Prefer cheapest provider endpoint | qwen/qwen3-235b:floor |