# Embed V4 API Pricing

As of October 10, 2026, Embed V4 costs $0.12 per 1M input tokens on Amazon Bedrock. It has a 128,000-token context window.

- Page: https://models.litellm.ai/models/embed-v4
- Lab: Cohere
- LiteLLM model name: `cohere.embed-v4:0`
- Context window: 128,000 tokens
- Added to LiteLLM: October 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Amazon Bedrock | `cohere.embed-v4:0` | $0.12 | $0 | – | – | – | 128K |
| Amazon Bedrock (Global cross-region) | `global.cohere.embed-v4:0` | $0.12 | $0 | – | – | – | 128K |
| Amazon Bedrock (US cross-region) | `us.cohere.embed-v4:0` | $0.12 | $0 | – | – | – | 128K |

## Cost examples

Embedding 10,000 documents of 500 tokens each:

- Amazon Bedrock: $0.60

## Use it with LiteLLM

```python
from litellm import embedding

response = embedding(
    model="cohere.embed-v4:0",
    input=["hello world"],
)
```

## FAQ

### How much does Embed V4 cost?

Embed V4 costs $0.12 per 1M input tokens on Amazon Bedrock.

### What is the context window of Embed V4?

Embed V4 has a 128,000-token context window.

### Which providers offer Embed V4?

Embed V4 is available from Amazon Bedrock through LiteLLM, using the model name cohere.embed-v4:0.

### How do I call Embed V4 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?

Embed V4 was added to LiteLLM's model price file in October 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json