Calculate the cost of using global.cohere.embed-v4:0 from AWS Bedrock for your AI applications
Pricing data last updated:
Mode: Embedding
Max: 128,000 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
global.cohere.embed-v4:0 is an embedding model from AWS Bedrock, one of 15 embedding models they offer. It is priced at $0.12 per 1M input tokens and $0.0000 per 1M output tokens, ranking 112 out of 161 embedding models by cost and cheaper than 21% of models in this category. global.cohere.embed-v4:0 supports vision. Its 128K-token context window is in the top 6% among embedding models.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 128,000 input tokens.
At $0.12 per 1M input tokens and $0.0000 per 1M output tokens, global.cohere.embed-v4:0 ranks 112 out of 161 embedding models by input cost. It is more expensive compared to the median of $0.10 for embedding models, and is cheaper than 21% of models in this category.
global.cohere.embed-v4:0 is one of 15 AWS Bedrock embedding models, with support for vision. its 128K-token context window places it in the top 6% of embedding models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs global.cohere.embed-v4:0 |
|---|---|---|---|---|
| cohere.embed-multilingual-image-v3.0 | Oci | $0.10 | - | -17% |
| voyage-multimodal-3.5 | OpenRouter | $0.12 | - | 0% |
| gemini-embedding-2:batch | OpenRouter | $0.10 | - | -17% |
Similar embedding models from other providers
No. global.cohere.embed-v4:0 costs $0.12 per 1M input tokens while cohere.embed-multilingual-image-v3.0 costs $0.10 per 1M input tokens, making cohere.embed-multilingual-image-v3.0 17% more affordable for input. However, global.cohere.embed-v4:0 may offer different capabilities or performance characteristics that justify the price difference.
global.cohere.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 112 out of 161 embedding models by input cost, making it cheaper than 21% of models in this category. For output, it costs $0.0000 per 1M tokens compared to the median of $0.02.
Among AWS Bedrock's 15 embedding models, global.cohere.embed-v4:0 ranks 12 by input cost.
The most comparable embedding models to global.cohere.embed-v4:0 are: cohere.embed-multilingual-image-v3.0 from Oci ($0.10/1M input tokens); voyage-multimodal-3.5 from OpenRouter ($0.12/1M input tokens); gemini-embedding-2:batch from OpenRouter ($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.
global.cohere.embed-v4:0 supports up to 128,000 input tokens, placing it in the top 6% of embedding models by context window size (rank 6 of 138). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
global.cohere.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.