Embeddings pricing
Embedding API pricing, per million tokens
10 providers' embedding model prices, each read off the provider's own pricing page with a link on every row.
10
Providers
24
Prices listed
$0.004
Lowest per 1M tokens
2026-10-25
Prices checked
Prices
Embeddings prices, every provider
Sorted by price per 1M input tokens. Batch prices, where listed, are in the notes.
| Model | Provider | Price as listed | Per 1M tokens | Notes | Source |
|---|---|---|---|---|---|
| pplx-embed-v1-0.6b | Perplexity | $0.004 per 1M tokens | $0.004 | Sourcechecked 2026-10-25 | |
| Embedding models up to 150M parameters | Fireworks AI | $0.008 per 1M tokens | $0.008 | Sourcechecked 2026-10-25 | |
| pplx-embed-context-v1-0.6b | Perplexity | $0.008 per 1M tokens | $0.008 | Contextualized embeddings. | Sourcechecked 2026-10-25 |
| Embedding models 150M to 350M parameters | Fireworks AI | $0.016 per 1M tokens | $0.016 | Sourcechecked 2026-10-25 | |
| Amazon Titan Text Embeddings V2us-east-1 on-demand | Amazon Web Services | $0.02 per 1M tokens | $0.02 | Batch: $0.01 per 1M input tokens. | Sourcechecked 2026-10-25 |
| text-embedding-3-smallStandard | OpenAI | $0.02 per 1M tokens | $0.02 | Sourcechecked 2026-10-25 | |
| text-embedding-3-smallus-east | Microsoft Azure | $0.022 per 1M tokens | $0.022 | Page lists $0.000022 per 1,000 tokens; converted to per 1M. | Sourcechecked 2026-10-25 |
| pplx-embed-v1-4b | Perplexity | $0.03 per 1M tokens | $0.03 | Sourcechecked 2026-10-25 | |
| pplx-embed-context-v1-4b | Perplexity | $0.05 per 1M tokens | $0.05 | Contextualized embeddings. | Sourcechecked 2026-10-25 |
| text-embedding-v3 | Alibaba Cloud | $0.07 per 1M tokens | $0.07 | Singapore region. | Sourcechecked 2026-10-25 |
| text-embedding-v4 | Alibaba Cloud | $0.07 per 1M tokens | $0.07 | Singapore region. Beijing lists $0.072. | Sourcechecked 2026-10-25 |
| Embed 5 Fast | Cohere | $0.08 per 1M tokens | $0.08 | Sourcechecked 2026-10-25 | |
| Embed 3 English (Cohere)us-east-1 on-demand | Amazon Web Services | $0.10 per 1M tokens | $0.10 | Image input is $0.0001 per image. | Sourcechecked 2026-10-25 |
| Mistral Embed | Mistral AI | $0.10 per 1M tokens | $0.10 | Sourcechecked 2026-10-25 | |
| Qwen3 8B | Fireworks AI | $0.10 per 1M tokens | $0.10 | Sourcechecked 2026-10-25 | |
| text-embedding-ada-002Standard | OpenAI | $0.10 per 1M tokens | $0.10 | Sourcechecked 2026-10-25 | |
| Embed 4 Model (Cohere)us-east-1 on-demand | Amazon Web Services | $0.12 per 1M tokens | $0.12 | Sourcechecked 2026-10-25 | |
| Embed 5 Pro | Cohere | $0.12 per 1M tokens | $0.12 | Sourcechecked 2026-10-25 | |
| text-embedding-3-largeStandard | OpenAI | $0.13 per 1M tokens | $0.13 | Sourcechecked 2026-10-25 | |
| Amazon Nova Multimodal Embeddingsus-east-1 on-demand, text input | Amazon Web Services | $0.135 per 1M tokens | $0.135 | Batch: $0.0675 per 1M text tokens. | Sourcechecked 2026-10-25 |
| text-embedding-3-largeus-east | Microsoft Azure | $0.143 per 1M tokens | $0.143 | Page lists $0.000143 per 1,000 tokens; converted to per 1M. | Sourcechecked 2026-10-25 |
| Codestral Embed | Mistral AI | $0.15 per 1M tokens | $0.15 | Sourcechecked 2026-10-25 | |
| Gemini Embedding 2 (Unified Multimodal, Preview)online requests, text input | Google Cloud | $0.20 per 1M tokens | $0.20 | Batch: $0.10. No charge for output tokens. | Sourcechecked 2026-10-25 |
| gemini-embedding-2Paid, Standard | $0.20 per 1M tokens | $0.20 | Batch $0.10. Free tier is free of charge. | Sourcechecked 2026-10-25 |
Terms on this page: Embedding · Vector database · RAG · Token
Estimator
Estimate a month of embeddings
Enter your monthly volume. Every row that bills in the same unit is priced, cheapest first.
Write 40k, 250M or 5B.
100M tokens a month costs from $0.40 (pplx-embed-v1-0.6b) to $20.00 (gemini-embedding-2).
| Model | Provider | Per month | Per 1M tokens |
|---|---|---|---|
| pplx-embed-v1-0.6b | Perplexity | $0.40 | $0.004 |
| Embedding models up to 150M parameters | Fireworks AI | $0.80 | $0.008 |
| pplx-embed-context-v1-0.6b | Perplexity | $0.80 | $0.008 |
| Embedding models 150M to 350M parameters | Fireworks AI | $1.60 | $0.016 |
| Amazon Titan Text Embeddings V2us-east-1 on-demand | Amazon Web Services | $2.00 | $0.02 |
| text-embedding-3-smallStandard | OpenAI | $2.00 | $0.02 |
| text-embedding-3-smallus-east | Microsoft Azure | $2.20 | $0.022 |
| pplx-embed-v1-4b | Perplexity | $3.00 | $0.03 |
| pplx-embed-context-v1-4b | Perplexity | $5.00 | $0.05 |
| text-embedding-v3 | Alibaba Cloud | $7.00 | $0.07 |
| text-embedding-v4 | Alibaba Cloud | $7.00 | $0.07 |
| Embed 5 Fast | Cohere | $8.00 | $0.08 |
| Embed 3 English (Cohere)us-east-1 on-demand | Amazon Web Services | $10.00 | $0.10 |
| Mistral Embed | Mistral AI | $10.00 | $0.10 |
| Qwen3 8B | Fireworks AI | $10.00 | $0.10 |
| text-embedding-ada-002Standard | OpenAI | $10.00 | $0.10 |
| Embed 4 Model (Cohere)us-east-1 on-demand | Amazon Web Services | $12.00 | $0.12 |
| Embed 5 Pro | Cohere | $12.00 | $0.12 |
| text-embedding-3-largeStandard | OpenAI | $13.00 | $0.13 |
| Amazon Nova Multimodal Embeddingsus-east-1 on-demand, text input | Amazon Web Services | $13.50 | $0.135 |
| text-embedding-3-largeus-east | Microsoft Azure | $14.30 | $0.143 |
| Codestral Embed | Mistral AI | $15.00 | $0.15 |
| Gemini Embedding 2 (Unified Multimodal, Preview)online requests, text input | Google Cloud | $20.00 | $0.20 |
| gemini-embedding-2Paid, Standard | $20.00 | $0.20 |
List prices in USD on 2026-10-25, before tax, free tiers and add-ons. Rows billed another way are in the price table only.
How to choose
How to choose on price
Embed once, store long
A document is embedded when it is added and again only when it changes. Plan the budget on new and changed content, not total size.
Batch the backfill
The first load of a large document set rarely needs answers in seconds. Several providers list a cheaper batch price.
Mind the dimensions
Bigger vectors cost more to store and search in a vector database. A smaller model can cost less overall even at the same embedding price.
You cannot mix models
Vectors from different models do not compare. Switching models means re-embedding everything, so test before you commit.
FAQ
Embeddings pricing questions
Which embedding API is cheapest?
By list price, pplx-embed-v1-0.6b from Perplexity at $0.004 per 1M tokens, checked 2026-10-25. The dearest row here is gemini-embedding-2 at $0.20. Retrieval quality on your own documents matters more than the price gap.
Do embeddings have an output price?
No. Embedding models are billed on the tokens you send in. What comes back is a list of numbers, not text, and none of the providers here charge for it.
Is embedding the big cost in a RAG app?
Usually not. You embed a document once, and again only when it changes. The ongoing costs are storing the vectors in a vector database and the LLM calls that answer each question.
How current are these prices?
Every row was read off the provider's own pricing page on 2026-10-25 and links to it. Prices listed per 1,000 tokens are shown per 1M tokens.
Related
Vendor pages and tools
OpenAI API pricing10 models and 20 other prices, checked 2026-10-25.Gemini API pricing9 models and 9 other prices, checked 2026-10-25.Qwen API pricing10 models and 2 other prices, checked 2026-10-25.Amazon Bedrock pricing10 models and 7 other prices, checked 2026-10-25.Azure OpenAI pricing9 models and 7 other prices, checked 2026-10-25.Cohere API pricing5 models and 2 other prices, checked 2026-10-25.Fireworks AI API pricing10 models and 3 other prices, checked 2026-10-25.Vertex AI pricing10 models and 4 other prices, checked 2026-10-25.Mistral API pricing9 models and 6 other prices, checked 2026-10-25.Perplexity API pricing6 models and 4 other prices, checked 2026-10-25.Embedding cost calculatorWhat it costs to embed a document set, and to keep it fresh.RAG cost calculatorEmbeddings, a vector database and LLM calls for one RAG app.Image generation pricingEvery image generation price we track.Speech to text pricingEvery speech to text price we track.Text to speech pricingEvery text to speech price we track.Vector databases pricingEvery vector databases price we track.LLM API pricing comparedToken prices for every LLM vendor we track.All pricing pagesEvery vendor we track, with the day each was checked.
Building this into a product? OceanLab builds AI into business workflows, with people kept in charge. AI automation →
