---
title: "embed-v4.0 - Model Details & Comparison"
description: "embed-v4.0 from Cohere: capabilities, context limits, pricing, and side-by-side comparisons with alternative models."
url: "https://www.getmaxim.ai/bifrost/model-library/compare/cohere/embed-v4.0"
markdown: "https://www.getmaxim.ai/bifrost/model-library/compare/cohere/embed-v4.0.md"
---

# embed-v4.0 - Model Details & Comparison

> embed-v4.0 from Cohere: capabilities, context limits, pricing, and side-by-side comparisons with alternative models.

## Important Links

- [View MCP Gateway](https://www.getmaxim.ai/bifrost/resources/mcp-gateway.md)
- [Features](https://www.getmaxim.ai/bifrost/#features)
- [Enterprise](https://www.getmaxim.ai/enterprise)
- [Pricing](https://www.getmaxim.ai/pricing)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://www.getmaxim.ai/book-a-demo)

## About embed-v4.0

embed-v4.0 is an embedding model from Cohere, one of 8 embedding models they offer. It is priced at $0.12 per 1M input tokens and $0.0000 per 1M output tokens, ranking 117 out of 163 embedding models by cost and cheaper than 20% of models in this category. Its 128K-token context window is in the top 4% among embedding models.

## Specifications

- **Cohere Provider.**
- **Embedding Mode.**
- **128,000 Max Input Tokens.**
- **128,000 Max Tokens.**
- **$0.12 / 1M tokens Input Price.**
- **$0.0000 / 1M tokens Output Price.**

## embed-v4.0 Pricing Overview

At $0.12 per 1M input tokens and $0.0000 per 1M output tokens, embed-v4.0 ranks 117 out of 163 embedding models by input cost. It is more expensive compared to the median of $0.10 for embedding models, and is cheaper than 20% of models in this category.

embed-v4.0 is one of 8 Cohere embedding models, its 128K-token context window places it in the top 4% of embedding models.

## Models to Compare

Alternatives to embed-v4.0 with comparable capabilities.

| Model | Provider | Input $/1M | Output $/1M |
| --- | --- | --- | --- |
| amazon.nova-2-multimodal-embeddings-v1:0 | AWS Bedrock | $0.14 | $0.0000 |
| amazon.titan-embed-text-v1 | AWS Bedrock | $0.10 | $0.0000 |
| amazon.titan-embed-g1-text-02 | AWS Bedrock | $0.10 | $0.0000 |
| ada | Azure | $0.10 | $0.0000 |
| text-embedding-3-large | Azure | $0.13 | $0.0000 |

- [Compare amazon.nova-2-multimodal-embeddings-v1:0](https://www.getmaxim.ai/bifrost/model-library/compare/bedrock/amazon.nova-2-multimodal-embeddings-v1-0.md)
- [Compare amazon.titan-embed-text-v1](https://www.getmaxim.ai/bifrost/model-library/compare/bedrock/amazon.titan-embed-text-v1.md)
- [Compare amazon.titan-embed-g1-text-02](https://www.getmaxim.ai/bifrost/model-library/compare/bedrock/amazon.titan-embed-g1-text-02.md)
- [Compare ada](https://www.getmaxim.ai/bifrost/model-library/compare/azure/ada.md)
- [Compare text-embedding-3-large](https://www.getmaxim.ai/bifrost/model-library/compare/azure/text-embedding-3-large.md)

## Related Resources

- [Calculate embed-v4.0 costs](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/cohere/model/embed-v4.0.md)
- [Check Cohere status](https://www.getmaxim.ai/bifrost/provider-status/cohere.md)
- [All Cohere pricing](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/cohere.md)

## FAQ

### Is embed-v4.0 cheaper than amazon.nova-2-multimodal-embeddings-v1:0?

Yes. embed-v4.0 costs $0.12 per 1M input tokens compared to amazon.nova-2-multimodal-embeddings-v1:0's $0.14 per 1M input tokens, making it 13% more affordable. Both are embedding models and share support for audio input.

### How does embed-v4.0 pricing compare to the average embedding model?

embed-v4.0 input pricing is $0.12 per 1M tokens, which is 20% above the median of $0.10 for embedding models. It ranks 117 out of 163 embedding models by input cost, making it cheaper than 20% of models in this category. For output, it costs $0.0000 per 1M tokens compared to the median of $0.0090.

### What makes embed-v4.0 different from other Cohere models?

Among Cohere's 8 embedding models, embed-v4.0 ranks 7 by input cost.

### What are the best alternatives to embed-v4.0?

The most comparable embedding models to embed-v4.0 are: amazon.nova-2-multimodal-embeddings-v1:0 from AWS Bedrock ($0.14/1M input tokens); amazon.titan-embed-text-v1 from AWS Bedrock ($0.10/1M input tokens); amazon.titan-embed-g1-text-02 from AWS Bedrock ($0.10/1M input tokens); ada from Azure ($0.10/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.

### How large is embed-v4.0's context window?

embed-v4.0 supports up to 128,000 input tokens, placing it in the top 4% of embedding models by context window size (rank 6 of 161). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.

### How do I check if Cohere is down?

You can monitor Cohere service health in real time on the Bifrost Cohere Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.

### How do I calculate embed-v4.0 costs?

embed-v4.0 is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.12 and generating 1M output tokens costs $0.0000.

## Related Resources

- [Cohere models](https://www.getmaxim.ai/bifrost/model-library/provider/cohere.md)
- [Model library](https://www.getmaxim.ai/bifrost/model-library.md)
- [LLM cost calculator](https://www.getmaxim.ai/bifrost/llm-cost-calculator.md)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost)
- [Pricing: Bifrost pricing](https://www.getmaxim.ai/pricing)
- [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/enterprise)
- [Book a Demo: Bifrost demo](https://www.getmaxim.ai/book-a-demo)
- [Resources: Bifrost resources](https://www.getmaxim.ai/bifrost/resources.md)

---

*This is a markdown version of [https://www.getmaxim.ai/bifrost/model-library/compare/cohere/embed-v4.0](https://www.getmaxim.ai/bifrost/model-library/compare/cohere/embed-v4.0) for AI/LLM consumption.*