# Nomic Embed (slim)

> Nomic's hosted embedding endpoints on the Atlas API turn text and images into vectors with the open-weight Nomic Embed models. Agents call them over HTTP with an API key or through the Python and TypeScript clients.

- Full: https://www.anchorterminal.com/tools/nomic-embed.md (~6,700 tokens) · this version ~1,530 tokens · JSON https://www.anchorterminal.com/tools/nomic-embed.json · canonical https://www.anchorterminal.com/tools/nomic-embed
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-08

**D · 49.2/100 · rank #613 of 722 · #7 in Embeddings & rerankers · not agent-ready · confidence medium**


Assessment: The text models have Apache-2.0 weights and a public OpenAPI 3.1 contract, so vectors made through the hosted endpoint can be reproduced locally. Nomic's current site and documentation index describe a construction-industry product, no rendered public page prices the endpoint, and no published terms or status component name it.

## Facts

- Kind: HTTP API · vendor: Nomic, Inc. · category: Embeddings & rerankers · legal entity: Nomic, Inc. · provenance 45/100
- Endpoint: `https://api-atlas.nomic.ai/v1/embedding/text` (HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: Proprietary hosted API. Model weights Apache-2.0 on Hugging Face. The Python client declares Apache in setup.py and the TypeScript client is MIT
- Probe metrics: not measured yet (probes haven't run)
- Endpoints: POST /v1/embedding/text and POST /v1/embedding/image on https://api-atlas.nomic.ai (Atlas API v0.57.0)
- Models: nomic-embed-text-v1 and v1.5 on the docs page. The OpenAPI document adds nomic-embed-text-v2, nomic-embed-code, gte-multilingual-base and all-MiniLM-L6-v2, with nomic-embed-vision-v1 and v1.5 for images
- Dimensions: 768. nomic-embed-text-v1.5 can be reduced to between 64 and 768
- Max context: 8,192 tokens per text. Longer texts are truncated or averaged across chunks
- Languages: English on nomic-embed-text-v1 and v1.5. Over 70 languages on gte-multilingual-base, per the docs
- Modalities: Text, and images in PNG, JPEG or WebP
- Rate limits: 1,200 requests per five-minute rolling window per IP address
- Free tier: 10M tokens on the starter plan, per the Atlas web app's script. Not confirmed on a rendered page
- Trains on API data: Not stated for this API. No published terms name it
- Open weights: Apache-2.0 on Hugging Face, also on Amazon SageMaker per the docs
- Prices: Text embedding tokens beyond the plan's monthly allowance $0.10 per 1M tokens

- Scores: Reliability 38, Performance pending, Schema & documentation 65, Agent ergonomics 69, Security & auth 62, Payments & pricing 20, Task success pending, Maintenance & community 28, Transparency & trust 46 · total over the 7 assessed categories
- Why: Reliability, Graded as a hosted service, on the embedding endpoints at api-atlas.nomic.ai. · Schema & documentation, OpenAPI 3.1 document for the Atlas API, v0.57.0, public at api-atlas.nomic.ai/v1/api-reference/openapi.json (25). · Agent ergonomics, dimensionality from 64 to 768 on nomic-embed-text-v1.5, floats only, with no binary or base64 output (18 of 25). · Security & auth, Bearer API keys created and deleted in the Atlas dashboard or through key endpoints, scoped to an organisation, a dataset or a user. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, The Atlas API reports v0.57.0 with no date. · Transparency & trust, The hosted API is closed, while the weights for the text, code and vision models are Apache-2.0 on Hugging Face and the Python client declar…
- Sources: 22, open questions: 8, both in the full twin
- Capabilities: embed.text, embed.multimodal, embed.multilingual, embed.code
- JSON: https://www.anchorterminal.com/api/v1/tools/nomic-embed.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/nomic-embed.svg` or a link to https://www.anchorterminal.com/tools/nomic-embed from a page on nomic.ai or one of its subdomains, or the README of github.com/nomic-ai/nomic, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Set task_type to search_query for queries and search_document for stored text. The default is search_document
2. Name the model in every request. The API defaults to nomic-embed-text-v1, while the Python client defaults to nomic-embed-text-v1.5
3. Keep under 1,200 requests per five minutes per IP address. The Python client sends at most 10 texts a request
4. Set long_text_mode to truncate or mean. Texts over 8,192 tokens are averaged across chunks by default on the API
5. Pass dimensionality only with nomic-embed-text-v1.5, between 64 and 768

## Connect

```bash
pip install nomic
```

```bash
curl -X POST https://api-atlas.nomic.ai/v1/embedding/text \
  -H "Authorization: Bearer $NOMIC_API_KEY" -H "Content-Type: application/json" \
  -d '{"texts":["The text you want to embed."],"model":"nomic-embed-text-v1.5","task_type":"search_document"}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/nomic-embed

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Gemini Embedding | BB | 70.6 | embed.text, embed.multimodal, embed.code, embed.multilingual | https://www.anchorterminal.com/tools/gemini-embedding.min.md |
| Jina Embeddings and Reranker | C | 61 | embed.text, embed.multimodal, embed.code, embed.multilingual | https://www.anchorterminal.com/tools/jina-embeddings.min.md |
| Voyage AI embeddings and rerankers | C | 58.8 | embed.text, embed.multimodal, embed.code, embed.multilingual | https://www.anchorterminal.com/tools/voyage-ai.min.md |
| Cohere Embed and Rerank | BB | 72.5 | embed.text, embed.multimodal, embed.multilingual | https://www.anchorterminal.com/tools/cohere-embed.min.md |
| OpenAI embeddings | BB | 73.2 | embed.text, embed.multilingual | https://www.anchorterminal.com/tools/openai-embeddings.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)