Nomic AI Embedding API
63
AI ReadinessAI-Aware (B)63/100
Official vendor OpenAPI document · agent-readyAI/MLEmbeddings Searchbearer3 EndpointsREST
For Agents
Generate text and image embeddings with Nomic's models for semantic search, classification, and clustering. Returns vectors in a shared space for cross-modal retrieval.
Use for: Generate embeddings for a batch of documents, Embed an image for visual similarity search, List the embedding models Nomic offers, Create vectors for a semantic search index
Not supported: Does not handle text generation, vector storage, or chat completion. Use for generating text and image embeddings only.
The Nomic AI Embedding API generates vector embeddings for text and images using Nomic's embedding models. It embeds text inputs for a chosen task type such as search, classification, or clustering, embeds image inputs into the same vector space, and lists the embedding models available. Applications use the resulting vectors for semantic search, retrieval, and similarity grouping.
Install Jentic One Beta
Connect the Nomic AI Embedding API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Nomic AI Embedding API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnomic.ai%2Fnomic" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fnomic.ai%2Fnomic" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Nomic AI Embedding API.
Generate text embeddings for a task type such as search, classification, or clustering
Embed images into the same vector space as text for cross-modal retrieval
List the available Nomic embedding models
Produce vectors sized for a chosen Nomic model to power a semantic search index
Use Cases
Patterns agents use Nomic AI Embedding API for, with concrete tasks.
★ AI Retrieval Agent
An AI agent connected through Jentic builds and queries a retrieval index by embedding documents and search queries with Nomic, so a question gets matched to the most relevant passages without the developer wiring the embedding calls by hand. The agent picks a model and the search task type, then stores or compares the returned vectors.
Embed a set of documents and a user query with the search task type and return the top matches by vector similarity
Multimodal Image Search
A visual search product embeds both images and text descriptions into Nomic's shared vector space so a text query can retrieve matching images and vice versa. Because image and text vectors are comparable, the product runs cross-modal similarity without maintaining two separate models.
Embed a catalogue of product images and a text query, then return the images whose vectors are closest to the query
Clustering and Classification
A data-labelling or analytics tool embeds records with the clustering or classification task type and groups them by vector proximity, surfacing themes or routing items to categories. Choosing the task type tunes the vectors so downstream grouping and labelling stay accurate.
Embed a batch of support tickets with the clustering task type and group them by similarity to surface common themes
Key Endpoints
3 endpoints — the nomic ai embedding api generates vector embeddings for text and images using nomic's embedding models.
METHOD
PATH
DESCRIPTION
POST
/v1/embedding/text
Generate embeddings for text inputs
POST
/v1/embedding/image
Generate embeddings for image inputs
GET
/v1/models
List available embedding models
POST
/v1/embedding/text
Generate embeddings for text inputs
POST
/v1/embedding/image
Generate embeddings for image inputs
GET
/v1/models
List available embedding models
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
N
Nomic AI Embedding API
- AI-Aware (B)63/100
100
Foundational Compliance62
Developer Experience & Jentic Compatibility45
AI-Readiness & Agent Experience94
Agent Usability60
Security54
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
100
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
99%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
62
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
5%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
42%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
45
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: DSignals: 4
29%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
50%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
60
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
60%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
54
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: CSignals: 1
54%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Nomic Embedding API by hand means handling its bearer token, picking a model and task type, and batching inputs yourself. Through Jentic you install once, import Nomic from the API Directory, store the token once, and your agent calls it.
Permission scoping
The API only reads inputs and returns vectors, so a rule can keep your agent to just the text and image embedding operations. You choose which operations it may call, and nothing it does changes account state.
Credential isolation
Your Nomic API token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'embed text for search' or 'embed an image', and Jentic returns the matching Nomic operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Nomic AI Embedding API through Jentic.
What authentication does the Nomic AI Embedding API use?
The Nomic AI Embedding API authenticates with a bearer token in the Authorization header, per its OpenAPI spec. Through Jentic that token is held encrypted by your own Jentic One instance and injected at call time, so it never appears in the agent's prompt or logs.
Can I embed images with the Nomic AI Embedding API?
Yes. The image embedding operation maps images into the same vector space as text, so you can run cross-modal similarity and retrieval. The text embedding operation accepts a task type such as search or clustering so the vectors suit your downstream use.
What are the rate limits for the Nomic AI Embedding API?
The OpenAPI spec does not define rate limits for the Nomic AI Embedding API. Nomic documents current limits and model details at https://docs.nomic.ai, so check there before embedding large batches.
Can I limit what my agent is allowed to do with the Nomic AI Embedding API?
Yes. Write a rule that allows only the text and image embedding operations, so the agent generates vectors and nothing else. None of the operations change account state, and every call the agent makes is logged.
How do I generate embeddings with the Nomic AI Embedding API through Jentic?
Search by intent in Jentic with a query like 'embed text for search', add the Nomic AI Embedding API from the Jentic API Directory, and your agent calls the text or image embedding operation with your chosen model. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED