curl -X POST https://api-llm.sunra.ai/v1/embeddings \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-embedding-2",
"input": [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
"dimensions": 768
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/embeddings",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "google/gemini-embedding-2",
"input": [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
"dimensions": 768
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/embeddings", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "google/gemini-embedding-2",
input: [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
dimensions: 768
})
});
const data = await response.json();
console.log(data);
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.011253, -0.020551, 0.049236, "..."]
},
{
"object": "embedding",
"index": 1,
"embedding": [0.031744, 0.008122, -0.014307, "..."]
}
],
"model": "google/gemini-embedding-2",
"usage": {
"prompt_tokens": 18,
"total_tokens": 18
}
}
LLM
Create embeddings
POST
/
v1
/
embeddings
curl -X POST https://api-llm.sunra.ai/v1/embeddings \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-embedding-2",
"input": [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
"dimensions": 768
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/embeddings",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "google/gemini-embedding-2",
"input": [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
"dimensions": 768
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/embeddings", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "google/gemini-embedding-2",
input: [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
dimensions: 768
})
});
const data = await response.json();
console.log(data);
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.011253, -0.020551, 0.049236, "..."]
},
{
"object": "embedding",
"index": 1,
"embedding": [0.031744, 0.008122, -0.014307, "..."]
}
],
"model": "google/gemini-embedding-2",
"usage": {
"prompt_tokens": 18,
"total_tokens": 18
}
}
从文本或媒体输入创建 embedding 向量。纯文本请求每条输入返回一个向量，适用于检索、语义搜索、聚类、分类和 RAG。包含媒体（以 base64 data URI 形式传入的图片、音频或视频）的请求会将所有输入融合为单个跨模态向量——如需每个资产各得一个向量，请将每个资产放在单独的请求中进行 embedding。兼容 OpenAI Embeddings API 格式。此端点不支持流式传输。
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。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 | string[]
必填
要进行 embedding 的输入，可以是单个字符串或字符串数组。纯文本输入独立进行 embedding，按输入顺序每条返回一个向量。媒体输入以 base64 data URI 形式传入（
data:image/png;base64,…、data:audio/mpeg;base64,…、data:video/mp4;base64,…），可与文本混合——但任何包含媒体的请求都会为全部输入返回一个融合后的单一向量。限制（来自上游）：每个请求最多 6 张图片，视频最长 120 秒，所有模态合计不超过 8,192 个 token（按文本 token 计；图片每张 258 个 token，音频每秒 25 个 token，视频每秒 66 个 token）。integer
输出 embedding 的维度数。仅支持具有灵活输出维度（Matryoshka Representation Learning）的模型。
google/gemini-embedding-2 默认为 3072，支持 128 到 3072 之间的值。较小的值会截断向量，同时保留大部分语义质量。string
返回 embedding 的格式。
float（默认）或 base64。响应
string
始终为
list。object[]
string
用于创建 embedding 的模型。
object
curl -X POST https://api-llm.sunra.ai/v1/embeddings \
-H "Authorization: Bearer <SUNRA_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-embedding-2",
"input": [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
"dimensions": 768
}'
import requests
response = requests.post(
"https://api-llm.sunra.ai/v1/embeddings",
headers={
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
json={
"model": "google/gemini-embedding-2",
"input": [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
"dimensions": 768
}
)
print(response.json())
const response = await fetch("https://api-llm.sunra.ai/v1/embeddings", {
method: "POST",
headers: {
"Authorization": "Bearer <SUNRA_KEY>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "google/gemini-embedding-2",
input: [
"The quick brown fox jumps over the lazy dog.",
"Sunra is a platform for AI models."
],
dimensions: 768
})
});
const data = await response.json();
console.log(data);
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.011253, -0.020551, 0.049236, "..."]
},
{
"object": "embedding",
"index": 1,
"embedding": [0.031744, 0.008122, -0.014307, "..."]
}
],
"model": "google/gemini-embedding-2",
"usage": {
"prompt_tokens": 18,
"total_tokens": 18
}
}
⌘I