curl -X POST https://api-llm.sunra.ai/v1/responses \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-2.5-flash",
"input": [
{
"type": "message",
"role": "user",
"content": "Hello, how are you?"
}
]
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/responses",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "google/gemini-2.5-flash",
"input": [
{
"type": "message",
"role": "user",
"content": "Hello, how are you?"
}
]
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/responses", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "google/gemini-2.5-flash",
input: [
{
type: "message",
role: "user",
content: "Hello, how are you?"
}
]
})
});
const data = await response.json();
console.log(data);
{
"id": "resp-abc123",
"object": "response",
"created_at": 1704067200,
"status": "completed",
"model": "google/gemini-2.5-flash",
"output": [
{
"type": "message",
"id": "msg_abc123",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Hello! I'm doing well, thank you for asking. How can I help you today?",
"annotations": []
}
]
}
],
"temperature": 1.0,
"top_p": 1.0,
"max_output_tokens": null,
"usage": {
"input_tokens": 15,
"output_tokens": 18,
"total_tokens": 33,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens_details": {
"reasoning_tokens": 0
}
},
"error": null
}
LLM
Create a response
POST
/
v1
/
responses
curl -X POST https://api-llm.sunra.ai/v1/responses \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-2.5-flash",
"input": [
{
"type": "message",
"role": "user",
"content": "Hello, how are you?"
}
]
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/responses",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "google/gemini-2.5-flash",
"input": [
{
"type": "message",
"role": "user",
"content": "Hello, how are you?"
}
]
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/responses", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "google/gemini-2.5-flash",
input: [
{
type: "message",
role: "user",
content: "Hello, how are you?"
}
]
})
});
const data = await response.json();
console.log(data);
{
"id": "resp-abc123",
"object": "response",
"created_at": 1704067200,
"status": "completed",
"model": "google/gemini-2.5-flash",
"output": [
{
"type": "message",
"id": "msg_abc123",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Hello! I'm doing well, thank you for asking. How can I help you today?",
"annotations": []
}
]
}
],
"temperature": 1.0,
"top_p": 1.0,
"max_output_tokens": null,
"usage": {
"input_tokens": 15,
"output_tokens": 18,
"total_tokens": 33,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens_details": {
"reasoning_tokens": 0
}
},
"error": null
}
使用 OpenAI Responses API 格式创建流式或非流式响应。
认证
string
必填
Bearer 令牌。在 Authorization 请求头中使用您的 API 密钥作为 Bearer 令牌。格式：
Bearer <SUNRA_KEY>请求
此端点接受一个 JSON 对象。string
必填
用于生成响应的模型 ID。在 sunra.ai/models 浏览可用模型。
object
可选的 Provider 路由偏好。省略时使用自动路由。支持的字段和 Provider 查询方式见 Provider 路由。
string | object[]
string | null
在模型上下文的第一个项目中插入系统（或开发者）消息。与
input 一起使用时，指令会插入到输入的开头。boolean
默认值:false
如果设置为
true，将使用服务器发送事件（SSE）流式传输响应。流式请求受空闲超时与生命周期上限约束，见输出上限与流生命周期。number
默认值:1
采样温度，介于 0 到 2 之间。较高的值增加随机性。
number
默认值:1
核采样参数。温度采样的替代方案。
number
默认值:0
介于 -2.0 和 2.0 之间的数字。正值会根据新令牌在文本中的现有频率进行惩罚。
number
默认值:0
介于 -2.0 和 2.0 之间的数字。正值会根据新令牌是否已出现在文本中进行惩罚。
object[]
string | object
控制工具选择行为。支持的字符串值：
none、auto、required。也可以指定特定函数。boolean
默认值:true
是否允许模型并行运行工具调用。
object
boolean
默认值:true
是否存储生成的响应以供后续检索。
object
可附加到响应的 16 个键值对集合。键为最长 64 个字符的字符串。值为最长 512 个字符的字符串。
string
代表您的最终用户的唯一标识符。最长 128 个字符。
响应
成功的响应对象。string
唯一响应标识符。
string
对象类型。始终为
response。number
响应创建时的 Unix 时间戳（秒）。
string
响应的状态。可能的值：
completed、failed、in_progress、cancelled。string
用于生成响应的模型。
object[]
object
number
使用的采样温度。
number
使用的核采样值。
integer | null
使用的最大输出令牌数设置。
object | null
如果生成失败，则为错误对象。
curl -X POST https://api-llm.sunra.ai/v1/responses \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-2.5-flash",
"input": [
{
"type": "message",
"role": "user",
"content": "Hello, how are you?"
}
]
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/responses",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "google/gemini-2.5-flash",
"input": [
{
"type": "message",
"role": "user",
"content": "Hello, how are you?"
}
]
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/responses", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "google/gemini-2.5-flash",
input: [
{
type: "message",
role: "user",
content: "Hello, how are you?"
}
]
})
});
const data = await response.json();
console.log(data);
{
"id": "resp-abc123",
"object": "response",
"created_at": 1704067200,
"status": "completed",
"model": "google/gemini-2.5-flash",
"output": [
{
"type": "message",
"id": "msg_abc123",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "Hello! I'm doing well, thank you for asking. How can I help you today?",
"annotations": []
}
]
}
],
"temperature": 1.0,
"top_p": 1.0,
"max_output_tokens": null,
"usage": {
"input_tokens": 15,
"output_tokens": 18,
"total_tokens": 33,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens_details": {
"reasoning_tokens": 0
}
},
"error": null
}
⌘I