api14
Get API key

We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.

Embeddings API

Convert text into vectors for semantic search, retrieval-augmented generation (RAG), recommendations and clustering. Batch many inputs in one request.

  • Semantic search
  • RAG pipelines
  • Deduplication and clustering
  • Recommendations
Sign in to use thisCreate free account

Results will appear here.

5 of 5 free messages left today. A free account adds free usage and an API key.Create free accountSign inSession cost $0.00

Embeddings API · 39 models

ModelPrice
NVIDIA: Nemotron 3.5 Embed 1B (free)nvidia/nemotron-3.5-embed-1b:freeFree
NVIDIA: Nemotron 3.5 Embed 8B (free)nvidia/nemotron-3.5-embed-8b:freeFree
LiquidAI: LFM2.5-Embedding-350M (free)liquid/lfm-2.5-embedding-350m:freeFree
NVIDIA: Nemotron 3 Embed 1B (free)nvidia/nemotron-3-embed-1b:freeFree
NVIDIA: Llama Nemotron Embed VL 1B V2 (free)nvidia/llama-nemotron-embed-vl-1b-v2:freeFree
Perplexity: Embed V1 0.6Bperplexity/pplx-embed-v1-0.6b$0.01 / 1M tokens
Thenlper: GTE-Basethenlper/gte-base$0.02 / 1M tokens
Intfloat: E5-Base-v2intfloat/e5-base-v2$0.02 / 1M tokens
Sentence Transformers: paraphrase-MiniLM-L6-v2sentence-transformers/paraphrase-minilm-l6-v2$0.02 / 1M tokens
Sentence Transformers: all-MiniLM-L12-v2sentence-transformers/all-minilm-l12-v2$0.02 / 1M tokens
BAAI: bge-base-en-v1.5baai/bge-base-en-v1.5$0.02 / 1M tokens
Sentence Transformers: multi-qa-mpnet-base-dot-v1sentence-transformers/multi-qa-mpnet-base-dot-v1$0.02 / 1M tokens
Sentence Transformers: all-mpnet-base-v2sentence-transformers/all-mpnet-base-v2$0.02 / 1M tokens
Sentence Transformers: all-MiniLM-L6-v2sentence-transformers/all-minilm-l6-v2$0.02 / 1M tokens
Thenlper: GTE-Largethenlper/gte-large$0.04 / 1M tokens
Intfloat: E5-Large-v2intfloat/e5-large-v2$0.04 / 1M tokens
Intfloat: Multilingual-E5-Largeintfloat/multilingual-e5-large$0.04 / 1M tokens
BAAI: bge-large-en-v1.5baai/bge-large-en-v1.5$0.04 / 1M tokens
BAAI: bge-m3baai/bge-m3$0.04 / 1M tokens
OpenAI: Text Embedding 3 Small (batch)openai/text-embedding-3-small:batch$0.04 / 1M tokens
Qwen: Qwen3 Embedding 8Bqwen/qwen3-embedding-8b$0.04 / 1M tokens
VoyageAI by MongoDB: voyage-4-litevoyageai/voyage-4-lite$0.07 / 1M tokens
OpenAI: Text Embedding 3 Smallopenai/text-embedding-3-small$0.07 / 1M tokens
Qwen: Qwen3 Embedding 4Bqwen/qwen3-embedding-4b$0.07 / 1M tokens
Perplexity: Embed V1 4Bperplexity/pplx-embed-v1-4b$0.11 / 1M tokens
OpenAI: Text Embedding Ada 002 (batch)openai/text-embedding-ada-002:batch$0.18 / 1M tokens
VoyageAI by MongoDB: voyage-4voyageai/voyage-4$0.21 / 1M tokens
OpenAI: Text Embedding 3 Large (batch)openai/text-embedding-3-large:batch$0.23 / 1M tokens
Mistral: Mistral Embed 2312mistralai/mistral-embed-2312$0.35 / 1M tokens
OpenAI: Text Embedding Ada 002openai/text-embedding-ada-002$0.35 / 1M tokens
VoyageAI by MongoDB: voyage-code-4voyageai/voyage-code-4$0.42 / 1M tokens
VoyageAI by MongoDB: voyage-multimodal-3.5voyageai/voyage-multimodal-3.5$0.42 / 1M tokens
VoyageAI by MongoDB: voyage-4-largevoyageai/voyage-4-large$0.42 / 1M tokens
OpenAI: Text Embedding 3 Largeopenai/text-embedding-3-large$0.45 / 1M tokens
Google: Gemini Embedding 001google/gemini-embedding-001$0.52 / 1M tokens
Mistral: Codestral Embed 2505mistralai/codestral-embed-2505$0.52 / 1M tokens
Google: Gemini Embedding 2 (batch)google/gemini-embedding-2:batch$0.35 / 1M tokens$11.38 / 1M tokens
Google: Gemini Embedding 2google/gemini-embedding-2$0.70 / 1M tokens$22.75 / 1M tokens
Google: Gemini Embedding 2 Previewgoogle/gemini-embedding-2-preview$0.70 / 1M tokens$22.75 / 1M tokens

How to call the Embeddings API API

  1. Create an API key in your dashboard.
  2. Install the official openai SDK for your language.
  3. Set baseURL to https://api14.com/api/v1 and model to "openai/text-embedding-3-small:batch".

How much do embeddings cost?

Usually a few cents per million tokens. See the table for exact prices.

Can I mix embedding models?

No, vectors from different models are not comparable. Re-embed your whole corpus when you switch models.

How many inputs per request?

Send an array of strings in one request to embed many texts at once; it is faster and cheaper per text than one request each.

How do I measure similarity?

Use cosine similarity between vectors. Normalised vectors make it a simple dot product.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.embeddings.create({
  "model": "openai/text-embedding-3-small:batch",
  "input": [
    "The quick brown fox",
    "Lorem ipsum"
  ]
});
console.log(result.data.map((d) => d.embedding.length));

Popular AI API services

LLM APIImage generation APIVideo generation APIText to speech APISpeech to text APIMusic generation APIRerank APIDecision model API