HTTP API
ModelBinding
Determines the provider and the model an agent runs with. It carries no credentials; the API key is resolved from configuration.
Shape: object
| Property | Required | Type | Description | Rules |
|---|---|---|---|---|
provider |
yes | string |
Gets the provider name, for example openai. |
— |
model |
yes | string |
Gets the model name, for example gpt-5.4-mini. |
— |
temperature |
no | number (float) |
Gets the sampling temperature. The provider default is used when it is null. |
pattern `^-?(?:0\ |
maxOutputTokens |
no | integer (int32) |
Gets the upper output token limit. The provider default is used when it is null. |
pattern `^-?(?:0\ |
topP |
no | number (float) |
Gets the nucleus sampling threshold. The provider default is used when it is null. |
pattern `^-?(?:0\ |
reasoningEffort |
no | string |
Gets the reasoning effort level. Models that support it use the value; the other providers ignore it. | — |
providerSettings |
no | object |
Gets the provider-specific extra settings. A key has the form {provider}.{setting}. |
— |
responseFormat |
no | null oneOf AgentResponseFormat |
— | — |
fallbacks |
no | array of ModelFallback |
Gets the ordered fallback chain tried when the primary provider is unavailable. Empty by default. | — |
responseCache |
no | null oneOf ResponseCacheSettings |
— | — |
allowConcurrentToolCalls |
no | boolean |
Gets whether independent tool calls within one turn may run at the same time. | — |