All datasets

Open data: Embeddings

Models for semantic search, RAG and code retrieval.

Published values, excluding taxes. A missing value is not zero. Plans may share resources or charge by usage; check their conditions. Third-party indexes are excluded from these downloads.

Most recent review:

Download JSON Download CSV

Embeddings

ProductText price (USD / M tokens)Reference dimensions (dimensiones)Input per document (tokens)Product review date
Mistral Embed0.11,0248,000
Codestral Embed0.153,0728,000
Voyage 4 Lite0.021,02432,000
Cohere Embed 5 Pro0.122,048128,000
Cohere Embed 5 Fast0.082,048128,000
Voyage 40.06——
Voyage 4 Large0.12——
Cohere Embed 4—1,536128,000

What each field means

input · USD / M tokens
Embeddings API price for text; index storage is not included.
dimensions · dimensiones
Reference setting listed on the product page. More dimensions mean more storage, not guaranteed higher quality.
context · tokens
Published limit per individual text. A batch limit may differ.

Conditions and sources

Mistral Embed

Text model; vectors aren't compatible with another model's just because they share a dimension. Context published as 8k.

Codestral Embed

3072 is the configurable maximum, not a quality score. A smaller dimension requires regenerating and versioning the index. Context published as 8k.

Voyage 4 Lite

Rate after initial credits; the comparison doesn't deduct credits. Shows the default 1024 dimensions; 256, 512 and 2048 are also supported.

Cohere Embed 5 Pro

Text rate; images cost $0.40 per million tokens. The default 2048 dimensions are shown; it also supports 256, 512, 768, 1024 and 1536, in float, int8 and binary formats.

Cohere Embed 5 Fast

Text rate; images cost $0.40 per million tokens. The default 2048 dimensions are shown; it also supports 256, 512, 768, 1024 and 1536, in float, int8 and binary formats.

Voyage 4

Rate after initial credits; credits are not deducted in the comparator. Context and dimensions are not included in this review.

Voyage 4 Large

Rate after initial credits; credits are not deducted in the comparator. Context and dimensions are not included in this review.

Cohere Embed 4

No comparable per-token rate is included: price depends on modality and deployment. Dedicated per-instance offerings aren't artificially converted to tokens.

License and attribution

Credit Codifly and link to this page when reusing the data. CC BY 4.0

Compare options