工具市场
研究
调用测试Chat Gpt Llm Responses Live
ChatGptLlmResponsesLive
此工具已接入,但尚未开放调用。价格和启用状态由平台管理。
- 价格
- —
- 状态
- 尚未开放
- 官方参考价
- —
- 调用方式
- REST · MCP
调用测试
点击运行后才会提交调用,请先检查参数和费用上限。
运行后,在这里查看状态、费用和返回内容。
接口文档
异步创建成功仅表示取得任务回执。需将回执 ID 传给对应平台的状态或结果接口,确认上游任务是否完成。
curl https://gw.asale.ai/v1/tool-runs \
-H 'Authorization: Bearer <ASALE_API_KEY>' \
-H 'Content-Type: application/json' \
-H 'Idempotency-Key: <UNIQUE_REQUEST_ID>' \
-d '{
"tool": "ai.optimization.chat.gpt.llm.responses.live",
"input": {
"body": [
{}
]
},
"max_cost_micros": 0
}'curl https://gw.asale.ai/v1/tool-runs/<RUN_ID> -H 'Authorization: Bearer <ASALE_API_KEY>'| 参数 | 必填 | 类型 |
|---|---|---|
| body | 否 | array |
完整输入规范
{
"$defs": {
"AiOptimizationChatGptLlmResponsesLiveRequestInfo": {
"properties": {
"force_web_search": {
"anyOf": [
{
"description": "force AI agent to use web searchoptional fieldto enable this parameter, web_search must also be enabled;when enabled, the AI model is forced to access and cite current web information;default value: false;Note: even if the parameter is set to true, there is no guarantee web sources will be cited in the response Note #2: not supported in reasoning models",
"type": "boolean"
},
{
"type": "null"
}
]
},
"max_output_tokens": {
"anyOf": [
{
"description": "maximum number of tokens in the AI responseoptional fieldminimum value for reasoning models (e.g., reasoning is true in the Models endpoint): 1024;minimum value for non-reasoning models: 16;maximum value: 4096;default value: 2048Note: if web_search is set to true or the reasoning model is specified in the request, the output token count may exceed the specified max_output_tokens limit",
"type": "integer"
},
{
"type": "null"
}
]
},
"message_chain": {
"anyOf": [
{
"description": "conversation history optional field array of message objects representing previous conversation turns; each object must contain: role string with either user or ai role; message string with message content (max 500 characters); you can specify maximum of 10 message objects in the array; Note: for Perplexity models, messages must strictly alternate between user and AI roles (user → ai); example: \"message_chain\": [{\"role\":\"user\",\"message\":\"Hello, what’s up?\"},{\"role\":\"ai\",\"message\":\"Hello! I’m doi",
"items": {
"anyOf": [
{
"oneOf": [
{
"$ref": "#/$defs/LlmMessageChainItem"
}
],
"type": "object"
},
{
"type": "null"
}
]
},
"type": "array"
},
{
"type": "null"
}
]
},
"model_name": {
"description": "name of the AI modelrequired fieldmodel_nameconsists of the actual model name and version name;if the basic model name is specified, its latest version will be set by default;for example, if gpt-4.1 is specified, the gpt-4.1-2025-04-14 will be set as model_name automatically;you can receive the list of available LLM models by making a separate request to the",
"type": "string"
},
"system_message": {
"anyOf": [
{
"description": "instructions for the AI behaviouroptional fielddefines the AI's role, tone, or specific behavior you can specify up to 500 characters in the system_message field",
"type": "string"
},
{
"type": "null"
}
]
},
"tag": {
"anyOf": [
{
"description": "user-defined task identifieroptional fieldthe character limit is 255you can use this parameter to identify the task and match it with the resultyou will find the specified tag value in the data object of the response",
"type": "string"
},
{
"type": "null"
}
]
},
"temperature": {
"anyOf": [
{
"description": "randomness of the AI responseoptional fieldhigher values make output more diverse; lower values make output more focused;minimum value: 0maximum value: 2default value: 0.94Note: not supported in reasoning models",
"type": "number"
},
{
"type": "null"
}
]
},
"top_p": {
"anyOf": [
{
"description": "diversity of the AI responseoptional field controls diversity of the response by limiting token selection;minimum value: 0maximum value: 1 default value: 0.92Note: top_p cannot be used together with temperature in the same request",
"type": "number"
},
{
"type": "null"
}
]
},
"user_prompt": {
"description": "prompt for the AI modelrequired fieldthe question or task you want to send to the AI model;you can specify up to 500 characters in the user_prompt field",
"type": "string"
},
"web_search": {
"anyOf": [
{
"description": "enable web searchoptional fieldwhen enabled, the AI model can access and cite current web information;default value: false;Note: refer to the Models endpoint for a list of models that support web_search;",
"type": "boolean"
},
{
"type": "null"
}
]
},
"web_search_city": {
"anyOf": [
{
"description": "city name of the locationoptional fieldNote: not supported in o3-mini, o1-pro, o1 models",
"type": "string"
},
{
"type": "null"
}
]
},
"web_search_country_iso_code": {
"anyOf": [
{
"description": "ISO country code of the locationoptional fieldto enable this parameter, web_search must also be enabled;when enabled, the AI model will search the web from the country you specify;Note: not supported in o3-mini, o1-pro, o1 models",
"type": "string"
},
{
"type": "null"
}
]
}
},
"type": "object"
},
"LlmMessageChainItem": {
"properties": {
"message": {
"anyOf": [
{
"description": "message text",
"type": "string"
},
{
"type": "null"
}
]
},
"role": {
"anyOf": [
{
"description": "role of the user from whom the message originates",
"type": "string"
},
{
"type": "null"
}
]
}
},
"type": "object"
}
},
"additionalProperties": false,
"properties": {
"body": {
"items": {
"anyOf": [
{
"oneOf": [
{
"$ref": "#/$defs/AiOptimizationChatGptLlmResponsesLiveRequestInfo"
}
],
"type": "object"
},
{
"type": "null"
}
]
},
"type": "array"
}
},
"required": [],
"type": "object"
}价格
尚未开放
测试会使用账户余额,并受所选密钥预算限制。费用上限仅约束本次 API 调用,不包含后续调用或上游周期任务。
价格版本 3
研究
Asale 将同一能力的通道按报价撮合,优先选择可用的低价通道。参考价取各通道已核实参考价的最高值。只有明确未执行的拒绝才可换通道;结果不确定时进入对账,避免重复收费。
供给通道: 1