Calculate the cost of using codestral-embed from Mistral for your AI applications
Pricing data last updated:
Mode: Embedding
Max: 8,192 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
codestral-embed is an embedding model from Mistral, one of 3 embedding models they offer. It is priced at $0.15 per 1M input tokens, ranking 78 out of 96 embedding models by cost and cheaper than 18% of models in this category. Its 8K-token context window is in the top 49% 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 8,192 input tokens.
At $0.15 per 1M input tokens, codestral-embed ranks 78 out of 96 embedding models by input cost. It is more expensive compared to the median of $0.10 for embedding models, and is cheaper than 18% of models in this category.
codestral-embed is one of 3 Mistral embedding models, its 8K-token context window places it in the top 49% of embedding models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs codestral-embed |
|---|---|---|---|---|
| amazon.nova-2-multimodal-embeddings-v1:0 | AWS Bedrock | $0.14 | $0.0000 | -10% |
| text-embedding-3-large | Azure | $0.13 | $0.0000 | -13% |
| databricks-gte-large-en | Databricks | $0.13 | $0.0000 | -13% |
Similar embedding models from other providers
No. codestral-embed costs $0.15 per 1M input tokens while amazon.nova-2-multimodal-embeddings-v1:0 costs $0.14 per 1M input tokens, making amazon.nova-2-multimodal-embeddings-v1:0 10% more affordable for input. However, codestral-embed may offer different capabilities or performance characteristics that justify the price difference.
codestral-embed input pricing is $0.15 per 1M tokens, which is 50% above the median of $0.10 for embedding models. It ranks 78 out of 96 embedding models by input cost, making it cheaper than 18% of models in this category.
Among Mistral's 3 embedding models, codestral-embed ranks 2 by input cost.
The most comparable embedding models to codestral-embed are: amazon.nova-2-multimodal-embeddings-v1:0 from AWS Bedrock ($0.14/1M input tokens); text-embedding-3-large from Azure ($0.13/1M input tokens); databricks-gte-large-en from Databricks ($0.13/1M input tokens); gemini-embedding-001 from Vertex AI ($0.15/1M 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.
codestral-embed 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.
