# Embedding and reranking APIs for AI agents

> 7 embeddings & rerankers ranked by the Anchor benchmark. Leader OpenAI embeddings (BB). Models that turn text, images and code into vectors for search, and rerankers that reorder search results by relevance. Compared on retrieval quality, dimensions and context length, multilingual support and price per million tokens.

- Canonical: https://www.anchorterminal.com/categories/embeddings
- Markdown: https://www.anchorterminal.com/categories/embeddings.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/categories/embeddings.min.md (~430 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/categories/embeddings.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

Models that turn text, images and code into vectors for search, and rerankers that reorder search results by relevance. Compared on retrieval quality, dimensions and context length, multilingual support and price per million tokens.

- Tools ranked: 7 · agent-ready (BB or better): 3 · accept x402: 0 · hosted endpoints: 7 · desk reviews by the panel: 14
- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)
- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/

- Capabilities in this category: embed.text, embed.multimodal, embed.code, embed.multilingual, rerank
- https://letme.dev/embed.text picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)

## Ranking

| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 59 | OpenAI embeddings | OpenAI | HTTP API | Embeddings | BB | 73.4 | high | no | API key | hosted | 4.5/5 (2) | https://www.anchorterminal.com/tools/openai-embeddings.md |
| 69 | Cohere Embed and Rerank | Cohere | HTTP API | Embeddings | BB | 72.5 | medium | no | API key | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/cohere-embed.md |
| 90 | Gemini Embedding | Google | HTTP API | Embeddings | BB | 71 | medium | no | API key | hosted | 3/5 (2) | https://www.anchorterminal.com/tools/gemini-embedding.md |
| 230 | Jina Embeddings and Reranker | Jina AI (Elastic) | HTTP API | Embeddings | C | 61.3 | medium | no | API key | hosted | 3/5 (2) | https://www.anchorterminal.com/tools/jina-embeddings.md |
| 273 | Voyage AI embeddings and rerankers | Voyage AI (MongoDB) | HTTP API | Embeddings | C | 59 | medium | no | API key | hosted | 4/5 (2) | https://www.anchorterminal.com/tools/voyage-ai.md |
| 283 | Mistral Embed and Codestral Embed | Mistral AI | HTTP API | Embeddings | C | 58.2 | medium | no | API key | hosted | 3.5/5 (2) | https://www.anchorterminal.com/tools/mistral-embeddings.md |
| 450 | ZeroEntropy zerank and zembed | ZeroEntropy | HTTP API | Embeddings | F | 13.8 | medium | no | API key | hosted | 1/5 (2) | https://www.anchorterminal.com/tools/zeroentropy.md |

Scores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.

## Summaries

### 59. OpenAI embeddings, BB (73.4)

OpenAI's text embedding API, with adjustable output dimensions for search and retrieval applications. text-embedding-3-small at $0.02 per million tokens, $0.01 through the Batch API. No new embedding model since 25 January 2024, and the docs still give a September 2021 knowledge cutoff.

- Page: https://www.anchorterminal.com/tools/openai-embeddings · Markdown: https://www.anchorterminal.com/tools/openai-embeddings.md · JSON: https://www.anchorterminal.com/api/v1/tools/openai-embeddings.json
- Capabilities: embed.text, embed.multilingual · endpoint: `https://api.openai.com/v1/embeddings`

### 69. Cohere Embed and Rerank, BB (72.5)

Embed 5 (Pro and Fast, released 2026-09-30) embeds text, images and parsed PDFs at 128K context in 100+ languages, at $0.08 to $0.12 per million tokens. Rerank 4 Pro and Fast with 32K context and top_n, tracked per model on the status page. Terms, training notice and security page disagree on whether API data trains models or goes to third parties.

- Page: https://www.anchorterminal.com/tools/cohere-embed · Markdown: https://www.anchorterminal.com/tools/cohere-embed.md · JSON: https://www.anchorterminal.com/api/v1/tools/cohere-embed.json
- Capabilities: embed.text, embed.multimodal, embed.multilingual, rerank · endpoint: `https://api.cohere.com/v2/embed`

### 90. Gemini Embedding, BB (71)

gemini-embedding-2, Google's multimodal embedding model, takes text, images, video, audio and PDFs into one 3072-dimension space (truncatable to 128) at 8,192 input tokens in 100+ languages. Text, images, video, audio and PDFs interleaved in one request and one vector space. $0.20 per million text tokens, against $0.02 for OpenAI's small model.

- Page: https://www.anchorterminal.com/tools/gemini-embedding · Markdown: https://www.anchorterminal.com/tools/gemini-embedding.md · JSON: https://www.anchorterminal.com/api/v1/tools/gemini-embedding.json
- Capabilities: embed.text, embed.multimodal, embed.code, embed.multilingual · endpoint: `https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent`

### 230. Jina Embeddings and Reranker, C (61.3)

jina-embeddings-v5 in text and omni (text, image, audio, video, PDF) variants at up to 32,768 tokens, plus the jina-reranker-v3.5 at 131,072 tokens a call. jina-reranker-v3.5 (20 July 2026) with a 131,072-token window and no document cap. No price per token in any currency on the public pages.

- Page: https://www.anchorterminal.com/tools/jina-embeddings · Markdown: https://www.anchorterminal.com/tools/jina-embeddings.md · JSON: https://www.anchorterminal.com/api/v1/tools/jina-embeddings.json
- Capabilities: embed.text, embed.multimodal, embed.code, embed.multilingual, rerank · endpoint: `https://api.jina.ai/v1/embeddings`

### 273. Voyage AI embeddings and rerankers, C (59)

Embedding and reranking models for text, code and multimodal retrieval from MongoDB-owned Voyage AI. 200 million free tokens per current model, then $0.02 to $0.12 per million. Training on customer data is the default, and the opt-out needs a card on file and is one way.

- Page: https://www.anchorterminal.com/tools/voyage-ai · Markdown: https://www.anchorterminal.com/tools/voyage-ai.md · JSON: https://www.anchorterminal.com/api/v1/tools/voyage-ai.json
- Capabilities: embed.text, embed.multimodal, embed.code, embed.multilingual, rerank · endpoint: `https://api.voyageai.com/v1/embeddings`

### 283. Mistral Embed and Codestral Embed, C (58.2)

Mistral's API for generating text and code embeddings. EU and US regional endpoints and a French legal entity. Embedding API uptime of 94.36 per cent over 90 days on Mistral's status page, with incidents on 12 and 27 August 2026.

- Page: https://www.anchorterminal.com/tools/mistral-embeddings · Markdown: https://www.anchorterminal.com/tools/mistral-embeddings.md · JSON: https://www.anchorterminal.com/api/v1/tools/mistral-embeddings.json
- Capabilities: embed.text, embed.code · endpoint: `https://api.mistral.ai/v1/embeddings`

### 450. ZeroEntropy zerank and zembed, F (13.8)

Discontinued retrieval API acquired by Notion. Its embedding and reranking models remain available as open weights for self-hosting. All four models now open weights under Apache 2.0 on Hugging Face. The hosted API was discontinued after 4 September 2026 and signups closed on 24 July 2026.

- Page: https://www.anchorterminal.com/tools/zeroentropy · Markdown: https://www.anchorterminal.com/tools/zeroentropy.md · JSON: https://www.anchorterminal.com/api/v1/tools/zeroentropy.json
- Capabilities: rerank, embed.text, embed.multilingual · endpoint: `https://api.zeroentropy.dev/v1/models/rerank`

## How we test this category

The same corpus and queries embedded with each model, then the top results reranked. We check retrieval quality against labelled answers, latency and the cost per million tokens. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.

## Indexed, not reviewed (3)

Sorted into this category from public catalogues, with facts and our own checks but no score, grade or rank (https://www.anchorterminal.com/indexed/index.md).

| Listing | Kind | What it does | Why it's here |
| --- | --- | --- | --- |
| [AI Wave](https://www.anchorterminal.com/tools/elopstudio-ai-wave.md) | MCP server | AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video. | vendor's own |
| [apple-rag.com MCP server](https://www.anchorterminal.com/tools/apple-rag-mcp-server.md) | MCP server | Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients | vendor's own |
| [forge](https://www.anchorterminal.com/tools/voxell-forge.md) | MCP server | MCP server for Forge, Voxell's embedding API. Voxell's Ingot-8B-R3 ranks \#1 for English on MTEB. | vendor's own |