LiteLLMModels

Text Embedding 004 API Pricing

As of October 10, 2026, Text Embedding 004 costs $0.10 per 1M input tokens on Google Vertex AI. It has a 2,048-token context window.

By GoogleModel ID vertex_ai/text-embedding-004Prices updated Checked
Scheduled for deprecation: Google Vertex AI lists April 1, 2027 as the deprecation date for vertex_ai/text-embedding-004.
Per 1M characters
$0.025
Input
$0.10 / 1M tokens
Output
$0 / 1M tokens
Context window
2,048 tokens
Providers
1
Added to LiteLLM
June 2024

Text Embedding 004 pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMPer 1M charsInputOutputContext
Google Vertex AIvertex_ai/text-embedding-004$0.025$0.10$02K

What Text Embedding 004 costs in practice

Embedding 10,000 documents of 500 tokens each

Google Vertex AI$0.50

Use Text Embedding 004 with LiteLLM

Call Text Embedding 004 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/embeddings. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import embedding

response = embedding(
    model="vertex_ai/text-embedding-004",
    input=["hello world"],
)
Proxy config.yaml
model_list:
  - model_name: text-embedding-004
    litellm_params:
      model: vertex_ai/text-embedding-004
      vertex_project: os.environ/VERTEX_PROJECT
      vertex_location: os.environ/VERTEX_LOCATION
Call the proxy
curl http://0.0.0.0:4000/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "text-embedding-004",
    "input": "hello world"
  }'

Text Embedding 004 FAQ

How much does Text Embedding 004 cost?

Text Embedding 004 costs $0.10 per 1M input tokens on Google Vertex AI.

What is the context window of Text Embedding 004?

Text Embedding 004 has a 2,048-token context window.

Which providers offer Text Embedding 004?

Text Embedding 004 is available from Google Vertex AI through LiteLLM, using the model name vertex_ai/text-embedding-004.

How do I call Text Embedding 004 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="vertex_ai/text-embedding-004", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/embeddings from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

When did LiteLLM add Text Embedding 004?

Text Embedding 004 was added to LiteLLM's model price file in June 2024.

Is Text Embedding 004 being deprecated?

Google Vertex AI lists a deprecation date of April 1, 2027 for vertex_ai/text-embedding-004.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Google Vertex AI.

Provider pages: Google Vertex AI.