> ## Documentation Index > Fetch the complete documentation index at: https://docs.siliconflow.cn/llms.txt > Use this file to discover all available pages before exploring further. # 创建嵌入请求 > Converts input content into embedding vectors. Supports text, image URL/base64, and mixed lists. ## OpenAPI ````yaml post /embeddings openapi: 3.0.0 info: title: SiliconFlow API description: The SiliconFlow REST API version: 1.0.0 contact: name: SiliconFlow Support url: https://www.siliconflow.cn/ license: name: MIT url: https://github.com/siliconflow/siliconcloud/blob/main/LICENSE servers: - url: https://api.siliconflow.cn/v1 security: - bearerAuth: [] paths: /embeddings: post: tags: - Embeddings summary: Create Embeddings description: >- Converts input content into embedding vectors. Supports text, image URL/base64, and mixed lists. operationId: createEmbedding requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/EmbeddingsRequest' responses: '200': description: >- The response from the model. The response header contains the x-siliconcloud-trace-id field, which serves as a unique identifier for tracing requests, facilitating log queries and issue troubleshooting. content: application/json: schema: $ref: '#/components/schemas/EmbeddingsResponse' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' '429': $ref: '#/components/responses/RateLimit' '503': $ref: '#/components/responses/Overloaded' '504': $ref: '#/components/responses/Timeout' deprecated: false x-codeSamples: - lang: curl label: Single text string source: | curl -X POST https://api.siliconflow.cn/v1/embeddings \ -H "Authorization: Bearer $SILICONFLOW_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": "Hello, world!", "model": "Qwen/Qwen3-VL-Embedding-8B" }' - lang: curl label: Text content object source: | curl -X POST https://api.siliconflow.cn/v1/embeddings \ -H "Authorization: Bearer $SILICONFLOW_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "text": "The quick brown fox" }, "model": "Qwen/Qwen3-VL-Embedding-8B", "encoding_format": "float" }' - lang: curl label: Image content source: | curl -X POST https://api.siliconflow.cn/v1/embeddings \ -H "Authorization: Bearer $SILICONFLOW_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "image": "https://example.com/image.jpg" }, "model": "Qwen/Qwen3-VL-Embedding-8B" }' - lang: curl label: Mixed content list source: | curl -X POST https://api.siliconflow.cn/v1/embeddings \ -H "Authorization: Bearer $SILICONFLOW_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": [ "First text", { "text": "Second text" }, { "image": "https://example.com/image.jpg" } ], "model": "Qwen/Qwen3-VL-Embedding-8B", "dimensions": 768 }' - lang: curl label: Long text handling source: | curl -X POST https://api.siliconflow.cn/v1/embeddings \ -H "Authorization: Bearer $SILICONFLOW_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": "Very long text content...", "model": "Qwen/Qwen3-VL-Embedding-8B", "truncate": "right", "user": "user_123" }' components: schemas: EmbeddingsRequest: description: > Compatible with two request formats: - Classic Embedding: keeps the historical parameter definition - VL Embedding: supports mixed text/image input, plus `user` and `truncate` Note: OpenAPI cannot automatically route schemas based on `model`. Choose parameters according to model capabilities. anyOf: - $ref: '#/components/schemas/EmbeddingsClassicRequest' - $ref: '#/components/schemas/EmbeddingsVLRequest' EmbeddingsResponse: type: object required: - object - model - data - usage properties: object: type: string description: The object type, which is always "list". enum: - - list model: description: The name of the model used to generate the embedding. type: string data: type: array description: The list of embeddings generated by the model. items: type: object required: - index - object - embedding properties: object: type: string enum: - embedding embedding: type: array items: type: number index: type: integer usage: type: object description: The usage information for the request. properties: prompt_tokens: type: integer description: The number of tokens used by the prompt. completion_tokens: type: integer description: The number of tokens used by the completion. total_tokens: type: integer description: The total number of tokens used by the request. required: - prompt_tokens - total_tokens - completion_tokens EmbeddingsClassicRequest: title: EmbeddingsClassicRequest type: object required: - model - input properties: model: type: string description: >- Corresponding Model Name. To better enhance service quality, we will make periodic changes to the models provided by this service, including but not limited to model on/offlining and adjustments to model service capabilities. We will notify you of such changes through appropriate means such as announcements or message pushes where feasible. **For a complete list of available models, please check the [Models](https://cloud.siliconflow.cn/sft-d29cs9gh3vvc73c59kb0/models?types=embedding)**. example: BAAI/bge-large-zh-v1.5 input: description: > Input text to embed must be provided as a string or an array of tokens. To process multiple inputs in a single request, pass an array of strings or an array of token arrays. The input length must not exceed the model's maximum token limit and should not be an empty string. The maximum input tokens for each model are as follows: BAAI/bge-large-zh-v1.5, BAAI/bge-large-en-v1.5, netease-youdao/bce-embedding-base_v1: 512 BAAI/bge-m3, Pro/BAAI/bge-m3: 8192 Qwen/Qwen3-Embedding-8B, Qwen/Qwen3-Embedding-4B, Qwen/Qwen3-Embedding-0.6B: 32768 oneOf: - type: string title: string description: >- The string that will be turned into an embedding. the item must not exceed the max models tokens limitation. example: >- Silicon flow embedding online: fast, affordable, and high-quality embedding services. come try it out! - type: array title: array description: > The array of strings that will be turned into an embedding. The array length must not exceed the max size, and the item must not exceed the max models tokens limitation. Current, the maximum array size is 32 , At the same time every item must not exceed 512 tokens for current models. minItems: 1 maxItems: 32 items: type: string default: '[''LLM'', ''Embedding'', ''RAG'']' example: '[''LLM'', ''Embedding'', ''RAG'']' encoding_format: description: > "The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/). " example: float default: float type: string enum: - float - base64 dimensions: description: > The number of dimensions the resulting output embeddings should have. Only supported in `Qwen/Qwen3` series. - Qwen/Qwen3-Embedding-8B: [64,128,256,512,768,1024,1536,2048,2560,4096] - Qwen/Qwen3-Embedding-4B:[64,128,256,512,768,1024,1536,2048,2560] - Qwen/Qwen3-Embedding-0.6B: [64,128,256,512,768,1024] type: integer example: 1024 EmbeddingsVLRequest: title: EmbeddingsVLRequest type: object required: - model - input properties: model: type: string description: >- The model name for VL Embedding. support models:Qwen/Qwen3-VL-Embedding-8B. example: Qwen/Qwen3-VL-Embedding-8B input: description: > Input content to be converted. Supported forms: - A single string - A content object (text or image) - A mixed list (strings/content objects) Notes: - Text content object format: `{"text":"text to embed"}` - Image content object format: `{"image":"https://example.com/image.jpg"}` or base64 - Video content is not supported yet - Input length must not exceed the model context limit and cannot be empty oneOf: - type: string title: string description: 作为 embedding 输入的单条文本。 example: >- Silicon flow embedding online: fast, affordable, and high-quality embedding services. come try it out! - $ref: '#/components/schemas/EmbeddingTextContent' - $ref: '#/components/schemas/EmbeddingImageContent' - type: array title: array description: >- A content list where each item can be a string, text object, or image object. minItems: 1 maxItems: 32 items: $ref: '#/components/schemas/EmbeddingInputItem' example: - First text - text: Second text - image: https://example.com/image.jpg encoding_format: description: | Output encoding format. Available values: `float` or `base64`. example: float default: float type: string enum: - float - base64 dimensions: description: > The number of dimensions the resulting output embeddings should have. Only supported in `Qwen/Qwen3` series. - Qwen/Qwen3-Embedding-8B: [64,128,256,512,768,1024,1536,2048,2560,4096] - Qwen/Qwen3-Embedding-4B:[64,128,256,512,768,1024,1536,2048,2560] - Qwen/Qwen3-Embedding-0.6B: [64,128,256,512,768,1024] type: integer example: 1024 user: type: string description: User identifier for request tracing and rate limiting. example: user_123 truncate: type: string description: >- Truncation direction for overlong text. Available values: `left` or `right`. enum: - left - right example: right BadRquestData: type: object required: - message - data - code properties: code: type: integer nullable: true default: false example: 20012 message: type: string nullable: false data: type: string nullable: false UnauthorizedData: type: string default: false example: Invalid token ForbiddenData: type: string default: false example: Forbidden NotFoundData: type: string default: false example: 404 page not found RateLimitData: type: object required: - message - data properties: message: type: string example: >- Request was rejected due to rate limiting. If you want more, please contact contact@siliconflow.cn. Details:TPM limit reached. data: type: string OverloadedtData: type: object required: - code - message - data properties: code: type: integer example: 50505 message: type: string example: Model service overloaded. Please try again later. data: type: string nullable: false TimeoutData: type: string EmbeddingTextContent: type: object description: Text content object. properties: text: type: string description: Text content to be converted. example: The quick brown fox required: - text EmbeddingImageContent: type: object description: Image content object. properties: image: type: string description: Image URL or base64-encoded image content. example: https://example.com/image.jpg required: - image EmbeddingInputItem: description: A single item in the embedding input list. oneOf: - type: string description: Text string. example: First text - $ref: '#/components/schemas/EmbeddingTextContent' - $ref: '#/components/schemas/EmbeddingImageContent' responses: BadRequest: description: BadRequest content: application/json: schema: $ref: '#/components/schemas/BadRquestData' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/UnauthorizedData' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ForbiddenData' NotFound: description: NotFound content: application/json: schema: $ref: '#/components/schemas/NotFoundData' RateLimit: description: RateLimit content: application/json: schema: $ref: '#/components/schemas/RateLimitData' Overloaded: description: Overloaded content: application/json: schema: $ref: '#/components/schemas/OverloadedtData' Timeout: description: Timeout content: application/json: schema: $ref: '#/components/schemas/TimeoutData' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: your api key description: >- Use the following format for authentication: Bearer [](https://cloud.siliconflow.cn/account/ak) ````