Embed V4.0 API Pricing
As of October 10, 2026, Embed V4.0 costs $0.12 per 1M input tokens on Cohere. It has a 128,000-token context window.
- Input
- $0.12 / 1M tokens
- Output
- $0 / 1M tokens
- Context window
- 128,000 tokens
- Providers
- 4
- Added to LiteLLM
- May 2025
Embed V4.0 pricing by provider
4 listings across 4 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| Cohere | cohere/embed-v4.0 | $0.12 | $0 | 128K |
| Azure AI Foundry | azure_ai/embed-v-4-0 | $0.12 | $0 | 128K |
| Oracle Cloud (OCI) | oci/cohere.embed-v4.0 | $0.12 | $0 | 128K |
| Vercel AI Gateway | vercel_ai_gateway/cohere/embed-v4.0 | $0.12 | $0 | – |
What Embed V4.0 costs in practice
Embedding 10,000 documents of 500 tokens each
| Cohere | $0.60 |
| Azure AI Foundry | $0.60 |
| Oracle Cloud (OCI) | $0.60 |
| Vercel AI Gateway | $0.60 |
Use Embed V4.0 with LiteLLM
Call Embed V4.0 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.
from litellm import embedding
response = embedding(
model="cohere/embed-v4.0",
input=["hello world"],
)model_list:
- model_name: embed-v4.0
litellm_params:
model: cohere/embed-v4.0
api_key: os.environ/COHERE_API_KEYcurl http://0.0.0.0:4000/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "embed-v4.0",
"input": "hello world"
}'Embed V4.0 FAQ
How much does Embed V4.0 cost?
Embed V4.0 costs $0.12 per 1M input tokens on Cohere.
What is the context window of Embed V4.0?
Embed V4.0 has a 128,000-token context window.
Which providers offer Embed V4.0?
Embed V4.0 is available from 4 providers through LiteLLM: Cohere, Azure AI Foundry, Oracle Cloud (OCI) and Vercel AI Gateway.
How do I call Embed V4.0 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="cohere/embed-v4.0", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/embeddings from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
When did LiteLLM add Embed V4.0?
Embed V4.0 was added to LiteLLM's model price file in May 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- cohere.com/pricing
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
- www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing
LiteLLM docs: Cohere, Azure AI Foundry, Oracle Cloud (OCI), Vercel AI Gateway.
Provider pages: Cohere, Azure AI Foundry, Oracle Cloud (OCI), Vercel AI Gateway.