Skip to main content
POST /v1/data/ai/embeddings/run Pricing: Metered: you pay exactly each call’s cost at the selected model’s rates (default OpenAI: Text Embedding 3 Small: $0.02 per 1M input tokens).

Request

Send the inputs under params. Only the keys below are accepted; any other key returns 422 invalid_params.
string[]
required
The texts to embed, one row per text (up to 100,000 characters each).
string
default:"openai/text-embedding-3-small"
The embedding model. Pick from the list (popular models first). Each model shows its own rate per 1M input tokens, and that is exactly what each call costs.35 allowed values, for example openai/text-embedding-3-small (OpenAI: Text Embedding 3 Small), openai/text-embedding-3-large (OpenAI: Text Embedding 3 Large), google/gemini-embedding-2 (Google: Gemini Embedding 2), google/gemini-embedding-2-preview (Google: Gemini Embedding 2 Preview), cohere/embed-5-fast (Cohere: Embed 5 Fast), cohere/embed-5-pro (Cohere: Embed 5 Pro), mongodb/voyage-4-lite (VoyageAI by MongoDB: voyage-4-lite), mongodb/voyage-4 (VoyageAI by MongoDB: voyage-4), qwen/qwen3-embedding-8b (Qwen: Qwen3 Embedding 8B), amazon/titan-embed-text-v1 (Amazon: Titan Embeddings G1 - Text). Fetch the full list with GET /v1/data/ai/embeddings?expand=options.
integer
The vector size, for models that support choosing it (OpenAI text-embedding-3, Gemini, Cohere Embed 5, Voyage 4, Qwen3 and others). Leave empty for the model’s native size.Allowed values: 256, 512, 768, 1024, 1536, 2048, 3072, 4096.

Example

Response fields

Each row in data is one embedding, keyed by these fields.

Example response

Abridged: long text and lists are shortened.