Bedrock supports embedding text and images through Amazon Titan and Cohere models. Portkey provides a standardized interface for embedding multiple modalities.

Bedrock Titan

Embedding Text

from portkey_ai import Portkey

client = Portkey(
    api_key="YOUR_PORTKEY_API_KEY", # defaults to os.environ.get("PORTKEY_API_KEY")
    provider="@PROVIDER",
)

embeddings = client.embeddings.create(
    model="amazon.titan-embed-text-v2:0",
    input="Hello this is a test",
    # normalize=False # if you would like to disable normalization
    # dimensions=1024, # embedding dimensions
    # encoding_format="float", # embedding format
)

import { Portkey } from 'portkey-ai';

const portkey = new Portkey({
    apiKey: "YOUR_API_KEY",
    provider:"@YOUR_PROVIDER"
});

const embedding = await portkey.embeddings.create({
    model: "amazon.titan-embed-text-v2:0",
    input: "Hello this is a test",
    // normalize: false, // if you would like to disable normalization
    // dimensions: 1024, // embedding dimensions
    // encoding_format: "float", // embedding format
});

console.log(embedding);

curl --location 'https://api.portkey.ai/v1/embeddings' \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: PORTKEY_API_KEY' \
--header 'x-portkey-provider: PORTKEY_PROVIDER' \
--data-raw '{
    "model": "amazon.titan-embed-text-v2:0",
    "input": "Hello this is a test",
    "normalize": false, // if you would like to disable normalization
    "dimensions": 1024, // embedding dimensions
    "encoding_format": "float" // embedding format
}'

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

portkey_client = OpenAI(
    api_key='NOT_REQUIRED',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY"
    )
)

embeddings = portkey_client.embeddings.create(
    model="amazon.titan-embed-text-v2:0",
    input="Hello this is a test",
    # normalize=False # if you would like to disable normalization
    # dimensions=1024, # embedding dimensions
    # encoding_format="float", # embedding format
)

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const portkeyClient = new OpenAI({
  apiKey: 'NOT_REQUIRED', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider: "vertex-ai",
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    provider:"@PORTKEY_PROVIDER"
  })
});

const embedding = await portkeyClient.embeddings.create({
    model: "amazon.titan-embed-text-v2:0",
    input: "Hello this is a test",
    // normalize=False, // if you would like to disable normalization
    // dimensions=1024, // embedding dimensions
    // encoding_format="float", // embedding format
});

console.log(embedding);

Embeddings Images

from portkey_ai import Portkey

client = Portkey(
    api_key="YOUR_PORTKEY_API_KEY", # defaults to os.environ.get("PORTKEY_API_KEY")
    provider="@PROVIDER",
)

embeddings = client.embeddings.create(
    model="amazon.titan-embed-image-v1",
    dimensions=256,
    input=[
    {
        "text": "this is the caption of the image",
        "image": {
            "base64": "UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
]
)

import { Portkey } from 'portkey-ai';

const portkey = new Portkey({
    apiKey: "YOUR_API_KEY",
    provider:"@YOUR_PROVIDER"
});

const embedding = await portkey.embeddings.create({
    model: "amazon.titan-embed-image-v1",
    dimensions: 256,
    input: [
    {
        "text": "this is the caption of the image",
        "image": {
            "base64": "UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
]
});

console.log(embedding);

curl --location 'https://api.portkey.ai/v1/embeddings' \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: PORTKEY_API_KEY' \
--header 'x-portkey-provider: PORTKEY_PROVIDER' \
--data-raw '{
"model": "amazon.titan-embed-image-v1",
"dimensions": 256,
"input": [
    {
        "text": "this is the caption of the image",
        "image": {
            "base64": "UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
]
}'

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

portkey_client = OpenAI(
    api_key='NOT_REQUIRED',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY"
    )
)

embeddings = portkey_client.embeddings.create(
    model="amazon.titan-embed-image-v1",
    dimensions=256,
    input=[
    {
        "text": "this is the caption of the image",
        "image": {
            "base64": "UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
    ]
)

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const portkeyClient = new OpenAI({
  apiKey: 'NOT_REQUIRED', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    provider:"@PORTKEY_PROVIDER"
  })
});

const embedding = await portkeyClient.embeddings.create({
    model: "amazon.titan-embed-image-v1",
    dimensions: 256,
    input: [
    {
        text: "this is the caption of the image",
        image: {
            base64: "UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
    ]
});

console.log(embedding);

Cohere

Embedding Text

from portkey_ai import Portkey

client = Portkey(
    api_key="YOUR_PORTKEY_API_KEY", # defaults to os.environ.get("PORTKEY_API_KEY")
    provider="@PROVIDER",
)

embeddings = client.embeddings.create(
    model="cohere.embed-english-v3",
    input=["Hello this is a test", "skibidi"],
    input_type="classification"
)

import { Portkey } from 'portkey-ai';

const portkey = new Portkey({
    apiKey: "YOUR_API_KEY",
    provider:"@YOUR_PROVIDER"
});

const embedding = await portkey.embeddings.create({
    model: "cohere.embed-english-v3",
    input: ["Hello this is a test", "skibidi"],
    input_type: "classification"
});

console.log(embedding);

curl --location 'https://api.portkey.ai/v1/embeddings' \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: PORTKEY_API_KEY' \
--header 'x-portkey-provider: PORTKEY_PROVIDER' \
--data-raw '{
  "model": "cohere.embed-english-v3",
  "input": ["Hello this is a test", "skibidi"],
  "input_type": "classification"
}'

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

portkey_client = OpenAI(
    api_key='NOT_REQUIRED',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY"
    )
)

embeddings = portkey_client.embeddings.create(
    model="cohere.embed-english-v3",
    input=["Hello this is a test", "skibidi"],
    input_type="classification"
)

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const portkeyClient = new OpenAI({
  apiKey: 'NOT_REQUIRED', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider: "vertex-ai",
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    provider:"@PORTKEY_PROVIDER"
  })
});

const embedding = await portkeyClient.embeddings.create({
    model: "cohere.embed-english-v3",
    input: ["Hello this is a test", "skibidi"],
    input_type: "classification"
});

console.log(embedding);

Embeddings Images

from portkey_ai import Portkey

client = Portkey(
    api_key="YOUR_PORTKEY_API_KEY", # defaults to os.environ.get("PORTKEY_API_KEY")
    provider="@PROVIDER",
)

embeddings = client.embeddings.create(
    model="cohere.embed-english-v3",
    input_type="image",
    dimensions=256,
    input=[
    {
        "image": {
            "base64": "Data:image/webp;base64,UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
]
)

import { Portkey } from 'portkey-ai';

const portkey = new Portkey({
    apiKey: "YOUR_API_KEY",
    provider:"@YOUR_PROVIDER"
});

const embedding = await portkey.embeddings.create({
"model": "cohere.embed-english-v3",
"input_type": "image",
"dimensions": 256,
"input": [
    {
        "image": {
            "base64": "Data:image/webp;base64,UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
]
});

console.log(embedding);

curl --location 'https://api.portkey.ai/v1/embeddings' \
--header 'Content-Type: application/json' \
--header 'x-portkey-api-key: PORTKEY_API_KEY' \
--header 'x-portkey-provider: PORTKEY_PROVIDER' \
--data-raw '{
"model": "cohere.embed-english-v3",
"input_type": "image",
"dimensions": 256,
"input": [
    {
        "image": {
            "base64": "Data:image/webp;base64,UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
]
}'

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

portkey_client = OpenAI(
    api_key='NOT_REQUIRED',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY"
    )
)

embeddings = portkey_client.embeddings.create(
    model="cohere.embed-english-v3",
    input_type="image",
    dimensions=256,
    input=[
    {
        image: {
            base64: "Data:image/webp;base64,UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
]
)

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const portkeyClient = new OpenAI({
  apiKey: 'NOT_REQUIRED', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    provider:"@PORTKEY_PROVIDER"
  })
});

const embedding = await portkeyClient.embeddings.create({
    model: "cohere.embed-english-v3",
    input_type: "image",
    dimensions: 256,
    input: [
    {
        image: {
            base64: "Data:image/webp;base64,UklGRkacAABXRUJQVlA4IDqcAACQggKdASqpAn8B....."
        }
    }
  ]
});

console.log(embedding);

Ecosystem

LLM Integrations

Cloud Platforms

Guardrails

Plugins

Vector Databases

Agents

AI Apps

Libraries

Tracing Providers

MCP Clients

MCP Servers

Embeddings

Bedrock Titan

Embedding Text

Embeddings Images

Cohere

Embedding Text

Embeddings Images

Portkey is now PRISMA AIRS AI Gateway. See it in action.

​Bedrock Titan

​Embedding Text

​Embeddings Images

​Cohere

​Embedding Text

​Embeddings Images

Portkey is now PRISMA AIRS AI Gateway. See it in action.

Bedrock Titan

Embedding Text

Embeddings Images

Cohere

Embedding Text

Embeddings Images