[ { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true, "model_id": "azure_ai/Cohere-embed-v3-english", "model_name": "Cohere Embed V3 English", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true, "model_id": "azure_ai/Cohere-embed-v3-multilingual", "model_name": "Cohere Embed V3 Multilingual", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_tokens": 128000, "output_vector_size": 3072, "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image" ], "supports_embedding_image_input": true, "model_id": "azure_ai/embed-v-4-0", "model_name": "Embed V 4 0", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "azure/ada", "model_name": "Ada", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "azure/text-embedding-3-large", "model_name": "Text Embedding 3 Large", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 8191, "deprecation_date": "2026-04-30", "max_tokens": 8191, "model_id": "azure/text-embedding-3-small", "model_name": "Text Embedding 3 Small", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "azure/text-embedding-ada-002", "model_name": "Text Embedding Ada 002", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.35e-7, "output_cost_per_token": 0, "max_input_tokens": 8172, "max_tokens": 8172, "input_cost_per_image": 0.00006, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "output_vector_size": 3072, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0", "supports_embedding_image_input": true, "supports_image_input": true, "supports_video_input": true, "supports_audio_input": true, "model_id": "amazon.nova-2-multimodal-embeddings-v1:0", "model_name": "Nova 2 Multimodal Embeddings", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.135, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "output_vector_size": 1536, "model_id": "amazon.titan-embed-g1-text-02", "model_name": "Titan Embed G1 Text 02", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0, "max_input_tokens": 128, "input_cost_per_image": 0.00006, "max_tokens": 128, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "output_vector_size": 1024, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", "supports_embedding_image_input": true, "supports_image_input": true, "model_id": "amazon.titan-embed-image-v1", "model_name": "Titan Embed Image V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "output_vector_size": 1536, "model_id": "amazon.titan-embed-text-v1", "model_name": "Titan Embed Text V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "output_vector_size": 1024, "provider_specific_entry": { "bedrock_invocation_schema": "titan_v2" }, "model_id": "amazon.titan-embed-text-v2:0", "model_name": "Titan Embed Text", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "supports_embedding_image_input": true, "model_id": "cohere.embed-english-v3", "model_name": "Embed English V3", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "supports_embedding_image_input": true, "model_id": "cohere.embed-multilingual-v3", "model_name": "Embed Multilingual V3", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_tokens": 128000, "output_vector_size": 1536, "supports_embedding_image_input": true, "model_id": "cohere.embed-v4:0", "model_name": "Embed", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00007, "output_cost_per_token": 0, "max_input_tokens": 77, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "max_tokens": 77, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true, "model_id": "eu.twelvelabs.marengo-embed-2-7-v1:0", "model_name": "Marengo Embed 2 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 70, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00007, "output_cost_per_token": 0, "max_input_tokens": 77, "max_tokens": 77, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true, "model_id": "twelvelabs.marengo-embed-2-7-v1:0", "model_name": "Twelvelabs.marengo Embed 2 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 70, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "output_vector_size": 1536, "model_id": "us-gov-east-1/amazon.titan-embed-text-v1", "model_name": "Amazon.titan Embed Text V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "output_vector_size": 1024, "model_id": "us-gov-east-1/amazon.titan-embed-text-v2:0", "model_name": "Amazon.titan Embed Text", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "output_vector_size": 1536, "model_id": "us-gov-west-1/amazon.titan-embed-text-v1", "model_name": "Amazon.titan Embed Text V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "output_vector_size": 1024, "model_id": "us-gov-west-1/amazon.titan-embed-text-v2:0", "model_name": "Amazon.titan Embed Text", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00007, "output_cost_per_token": 0, "max_input_tokens": 77, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "input_cost_per_image": 0.0001, "max_tokens": 77, "output_vector_size": 1024, "supports_embedding_image_input": true, "supports_image_input": true, "model_id": "us.twelvelabs.marengo-embed-2-7-v1:0", "model_name": "Marengo Embed 2 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 70, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 1024, "max_tokens": 1024, "model_id": "embed-english-light-v2.0", "model_name": "Embed English Light V2.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 1024, "max_tokens": 1024, "model_id": "embed-english-light-v3.0", "model_name": "Embed English Light V3.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "model_id": "embed-english-v2.0", "model_name": "Embed English V2.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 1024, "input_cost_per_image": 0.0001, "max_tokens": 1024, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, "supports_embedding_image_input": true, "supports_image_input": true, "model_id": "embed-english-v3.0", "model_name": "Embed English V3.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0001, "output_cost_per_token": 0, "max_input_tokens": 1024, "max_tokens": 1024, "supports_embedding_image_input": true, "model_id": "embed-multilingual-light-v3.0", "model_name": "Embed Multilingual Light V3.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 100, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 768, "max_tokens": 768, "model_id": "embed-multilingual-v2.0", "model_name": "Embed Multilingual V2.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 1024, "max_tokens": 1024, "supports_embedding_image_input": true, "model_id": "embed-multilingual-v3.0", "model_name": "Embed Multilingual V3.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_tokens": 128000, "output_vector_size": 1536, "supports_embedding_image_input": true, "model_id": "embed-v4.0", "model_name": "Embed V4.0", "provider_id": "cohere", "provider_name": "Cohere", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.0003e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "input_dbu_cost_per_token": 0.000001429, "max_tokens": 512, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0, "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "model_id": "databricks-bge-large-en", "model_name": "Databricks Bge Large En", "provider_id": "databricks", "provider_name": "Databricks", "max_output_tokens": 0, "input_cost_per_million": 0.10003000000000001, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2999000000000001e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_dbu_cost_per_token": 0.000001857, "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0, "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "model_id": "databricks-gte-large-en", "model_name": "Databricks Gte Large En", "provider_id": "databricks", "provider_name": "Databricks", "max_output_tokens": 0, "input_cost_per_million": 0.12999000000000002, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "model_id": "fireworks_ai/accounts/fireworks/models/", "model_name": "Fireworks_ai/accounts/fireworks/models/", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "model_id": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-0p6b", "model_name": "Qwen3 Embedding 0p6B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "model_id": "fireworks_ai/accounts/fireworks/models/qwen3-embedding-4b", "model_name": "Qwen3 Embedding 4B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "source": "https://fireworks.ai/pricing", "model_id": "fireworks_ai/nomic-ai/nomic-embed-text-v1", "model_name": "Nomic Embed Text V1", "provider_id": "fireworks", "provider_name": "Fireworks AI", "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "source": "https://fireworks.ai/pricing", "model_id": "fireworks_ai/nomic-ai/nomic-embed-text-v1.5", "model_name": "Nomic Embed Text V1.5", "provider_id": "fireworks", "provider_name": "Fireworks AI", "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "source": "https://fireworks.ai/pricing", "model_id": "fireworks_ai/thenlper/gte-base", "model_name": "Gte Base", "provider_id": "fireworks", "provider_name": "Fireworks AI", "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "source": "https://fireworks.ai/pricing", "model_id": "fireworks_ai/thenlper/gte-large", "model_name": "Gte Large", "provider_id": "fireworks", "provider_name": "Fireworks AI", "max_output_tokens": 0, "input_cost_per_million": 0.016, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "source": "https://fireworks.ai/pricing", "model_id": "fireworks_ai/WhereIsAI/UAE-Large-V1", "model_name": "UAE Large V1", "provider_id": "fireworks", "provider_name": "Fireworks AI", "max_output_tokens": 0, "input_cost_per_million": 0.016, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "model_id": "gigachat/Embeddings", "model_name": "Embeddings", "provider_id": "gigachat", "provider_name": "Gigachat", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "model_id": "gigachat/Embeddings-2", "model_name": "Embeddings 2", "provider_id": "gigachat", "provider_name": "Gigachat", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "output_vector_size": 2560, "model_id": "gigachat/EmbeddingsGigaR", "model_name": "EmbeddingsGigaR", "provider_id": "gigachat", "provider_name": "Gigachat", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "github_copilot/text-embedding-3-small", "model_name": "Text Embedding 3 Small", "provider_id": "github", "provider_name": "Github", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "github_copilot/text-embedding-3-small-inference", "model_name": "Text Embedding 3 Small Inference", "provider_id": "github", "provider_name": "Github", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "github_copilot/text-embedding-ada-002", "model_name": "Text Embedding Ada 002", "provider_id": "github", "provider_name": "Github", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 0, "max_input_tokens": 8192, "deprecation_date": "2025-09-29", "input_cost_per_token_above_128k_tokens": 1.5e-7, "max_tokens": 8192, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", "supports_multimodal": true, "tpm": 10000000, "model_id": "1.5-flash", "model_name": "1.5 Flash", "provider_id": "google", "provider_name": "Google", "max_output_tokens": 0, "input_cost_per_million": 0.075, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "max_tokens": 2048, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", "tpm": 10000000, "model_id": "embedding-001", "model_name": "Embedding 001", "provider_id": "google", "provider_name": "Google", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_video_per_second": 0.00079, "max_tokens": 8192, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_multimodal": true, "tpm": 10000000, "model_id": "embedding-2", "model_name": "Embedding 2", "provider_id": "google", "provider_name": "Google", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_video_per_second": 0.00079, "max_tokens": 8192, "output_vector_size": 3072, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_multimodal": true, "tpm": 10000000, "model_id": "embedding-2-preview", "model_name": "Embedding 2 Preview", "provider_id": "google", "provider_name": "Google", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-8, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "source": "https://docs.libertai.io/apis/text/", "model_id": "libertai/bge-m3", "model_name": "Bge M3", "provider_id": "libertai", "provider_name": "Libertai", "max_output_tokens": 0, "input_cost_per_million": 0.01, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "model_id": "llamagate/nomic-embed-text", "model_name": "Nomic Embed Text", "provider_id": "llamagate", "provider_name": "Llamagate", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 40960, "max_tokens": 40960, "model_id": "llamagate/qwen3-embedding-8b", "model_name": "Qwen3 Embedding 8B", "provider_id": "llamagate", "provider_name": "Llamagate", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "max_input_tokens": 8192, "max_tokens": 8192, "model_id": "codestral-embed", "model_name": "Codestral Embed", "provider_id": "mistral", "provider_name": "Mistral AI", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "max_input_tokens": 8192, "max_tokens": 8192, "model_id": "codestral-embed-2505", "model_name": "Codestral Embed (May 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "max_input_tokens": 8192, "max_tokens": 8192, "model_id": "mistral-embed", "model_name": "Mistral Embed", "provider_id": "mistral", "provider_name": "Mistral AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-8, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_tokens": 32768, "source": "https://nebius.com/prices-ai-studio", "model_id": "nebius/BAAI/bge-en-icl", "model_name": "Bge En Icl", "provider_id": "nebius", "provider_name": "Nebius", "max_output_tokens": 0, "input_cost_per_million": 0.01, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-8, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "source": "https://nebius.com/prices-ai-studio", "model_id": "nebius/BAAI/bge-multilingual-gemma2", "model_name": "Bge Multilingual Gemma2", "provider_id": "nebius", "provider_name": "Nebius", "max_output_tokens": 0, "input_cost_per_million": 0.01, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-8, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_tokens": 32768, "source": "https://nebius.com/prices-ai-studio", "model_id": "nebius/intfloat/e5-mistral-7b-instruct", "model_name": "E5 Mistral 7B Instruct", "provider_id": "nebius", "provider_name": "Nebius", "max_output_tokens": 0, "input_cost_per_million": 0.01, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-8, "output_cost_per_token": 1e-8, "max_input_tokens": 8192, "max_output_tokens": 96000, "max_tokens": 96000, "model_id": "novita/baai/bge-m3", "model_name": "Bge M3", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.01, "output_cost_per_million": 0.01, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "model_id": "novita/qwen/qwen3-embedding-0.6b", "model_name": "Qwen3 Embedding 0.6B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.07, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "novita/qwen/qwen3-embedding-8b", "model_name": "Qwen3 Embedding 8B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.07, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true, "model_id": "oci/cohere.embed-english-image-v3.0", "model_name": "Cohere.embed English Image V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true, "model_id": "oci/cohere.embed-english-light-image-v3.0", "model_name": "Cohere.embed English Light Image V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "model_id": "oci/cohere.embed-english-light-v3.0", "model_name": "Cohere.embed English Light V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "model_id": "oci/cohere.embed-english-v3.0", "model_name": "Cohere.embed English V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 1e-7, "max_input_tokens": 512, "output_vector_size": 1024, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "model_id": "oci/cohere.embed-multilingual-image-v3.0", "model_name": "Cohere.embed Multilingual Image V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true, "model_id": "oci/cohere.embed-multilingual-light-image-v3.0", "model_name": "Cohere.embed Multilingual Light Image V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 384, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "model_id": "oci/cohere.embed-multilingual-light-v3.0", "model_name": "Cohere.embed Multilingual Light V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "model_id": "oci/cohere.embed-multilingual-v3.0", "model_name": "Cohere.embed Multilingual V3.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_tokens": 128000, "output_vector_size": 1536, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_embedding_image_input": true, "model_id": "oci/cohere.embed-v4.0", "model_name": "Cohere.embed V4.0", "provider_id": "oci", "provider_name": "Oci", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "input_cost_per_token_batches": 6.5e-8, "max_tokens": 8191, "output_cost_per_token_batches": 0, "output_vector_size": 3072, "model_id": "text-embedding-3-large", "model_name": "Text Embedding 3 Large", "provider_id": "openai", "provider_name": "OpenAI", "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 8191, "input_cost_per_token_batches": 1e-8, "max_tokens": 8191, "output_cost_per_token_batches": 0, "output_vector_size": 1536, "model_id": "text-embedding-3-small", "model_name": "Text Embedding 3 Small", "provider_id": "openai", "provider_name": "OpenAI", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "max_tokens": 8191, "output_vector_size": 1536, "model_id": "text-embedding-ada-002", "model_name": "Text Embedding Ada 002", "provider_id": "openai", "provider_name": "OpenAI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "input_cost_per_token_batches": 5e-8, "max_tokens": 8191, "output_cost_per_token_batches": 0, "model_id": "text-embedding-ada-002-v2", "model_name": "Text Embedding Ada 002 V2", "provider_id": "openai", "provider_name": "OpenAI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4e-9, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_tokens": 32768, "output_vector_size": 1024, "source": "https://docs.perplexity.ai/docs/embeddings/quickstart", "model_id": "pplx-embed-v1-0.6b", "model_name": "Pplx Embed V1 0.6B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 0.004, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-8, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_tokens": 32768, "output_vector_size": 2560, "source": "https://docs.perplexity.ai/docs/embeddings/quickstart", "model_id": "pplx-embed-v1-4b", "model_name": "Pplx Embed V1 4B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 0.03, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "model_id": "scaleway/BAAI/bge-multilingual-gemma2", "model_name": "Bge Multilingual Gemma2", "provider_id": "scaleway", "provider_name": "Scaleway", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "model_id": "scaleway/qwen/qwen3-embedding-8b", "model_name": "Qwen3 Embedding 8B", "provider_id": "scaleway", "provider_name": "Scaleway", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "model_id": "snowflake/snowflake-arctic-embed-l-v2.0", "model_name": "Snowflake Arctic Embed L V2.0", "provider_id": "snowflake", "provider_name": "Snowflake", "max_output_tokens": 0, "input_cost_per_million": 0.07, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_tokens": 8192, "model_id": "snowflake/snowflake-arctic-embed-m-v2.0", "model_name": "Snowflake Arctic Embed M V2.0", "provider_id": "snowflake", "provider_name": "Snowflake", "max_output_tokens": 0, "input_cost_per_million": 0.07, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "max_input_tokens": 512, "output_vector_size": 768, "model_id": "baai/bge-base-en-v1.5", "model_name": "Bge Base En V1.5", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "max_input_tokens": 512, "output_vector_size": 768, "model_id": "BAAI/bge-base-en-v1.5", "model_name": "Bge Base En V1.5", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.6e-8, "output_cost_per_token": 0, "model_id": "together-ai-embedding-151m-to-350m", "model_name": "Together AI Embedding 151m To 350m", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.016, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-9, "output_cost_per_token": 0, "model_id": "together-ai-embedding-up-to-150m", "model_name": "Together AI Embedding Up To 150m", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.008, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0, "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "model_id": "vercel_ai_gateway/google/gemini-embedding-001", "model_name": "Gemini Embedding 001", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.15, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 0, "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "model_id": "vercel_ai_gateway/google/text-embedding-005", "model_name": "Text Embedding 005", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.024999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2.5e-8, "output_cost_per_token": 0, "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "model_id": "vercel_ai_gateway/google/text-multilingual-embedding-002", "model_name": "Text Multilingual Embedding 002", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.024999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 0, "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "model_id": "vercel_ai_gateway/openai/text-embedding-3-large", "model_name": "Text Embedding 3 Large", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.13, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "model_id": "vercel_ai_gateway/openai/text-embedding-3-small", "model_name": "Text Embedding 3 Small", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 0, "max_output_tokens": 0, "max_tokens": 0, "model_id": "vercel_ai_gateway/openai/text-embedding-ada-002", "model_name": "Text Embedding Ada 002", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "max_tokens": 2048, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "gemini-embedding-001", "model_name": "Gemini Embedding 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_video_per_second": 0.00079, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true, "model_id": "gemini-embedding-2", "model_name": "Gemini Embedding 2", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_video_per_second": 0.00079, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true, "model_id": "gemini-embedding-2-preview", "model_name": "Gemini Embedding 2 Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 1000000, "max_output_tokens": 8192, "input_cost_per_character": 0, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "uses_embed_content": true, "model_id": "gemini-flash-experimental", "model_name": "Gemini Flash Experimental", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ], "model_id": "multimodalembedding", "model_name": "Multimodalembedding", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ], "model_id": "multimodalembedding@001", "model_name": "Multimodalembedding@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "deprecation_date": "2026-01-14", "input_cost_per_character": 2.5e-8, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-embedding-004", "model_name": "Text Embedding 004", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2.5e-8, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-embedding-005", "model_name": "Text Embedding 005", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_character": 2.5e-8, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-embedding-large-exp-03-07", "model_name": "Text Embedding Large Exp 03 07", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.25e-9, "output_cost_per_token": 0, "max_input_tokens": 3072, "max_tokens": 3072, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "text-embedding-preview-0409", "model_name": "Text Embedding Preview (Sep 2004)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.0062499999999999995, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2.5e-8, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-multilingual-embedding-002", "model_name": "Text Multilingual Embedding 002", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" }, "output_vector_size": 2560, "model_id": "doubao-embedding", "model_name": "Doubao Embedding", "provider_id": "volcengine", "provider_name": "Volcengine", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" }, "output_vector_size": 2048, "model_id": "doubao-embedding-large", "model_name": "Doubao Embedding Large", "provider_id": "volcengine", "provider_name": "Volcengine", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" }, "output_vector_size": 4096, "model_id": "doubao-embedding-large-text-240915", "model_name": "Doubao Embedding Large Text 240915", "provider_id": "volcengine", "provider_name": "Volcengine", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" }, "output_vector_size": 2048, "model_id": "doubao-embedding-large-text-250515", "model_name": "Doubao Embedding Large Text 250515", "provider_id": "volcengine", "provider_name": "Volcengine", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" }, "output_vector_size": 2560, "model_id": "doubao-embedding-text-240715", "model_name": "Doubao Embedding Text 240715", "provider_id": "volcengine", "provider_name": "Volcengine", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 4000, "max_tokens": 4000, "model_id": "voyage-2", "model_name": "Voyage 2", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6e-8, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-3", "model_name": "Voyage 3", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.06, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-3-large", "model_name": "Voyage 3 Large", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.18, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-3-lite", "model_name": "Voyage 3 Lite", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6e-8, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-3.5", "model_name": "Voyage 3.5", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.06, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-3.5-lite", "model_name": "Voyage 3.5 Lite", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 16000, "max_tokens": 16000, "model_id": "voyage-code-2", "model_name": "Voyage Code 2", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-code-3", "model_name": "Voyage Code 3", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.18, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 0, "max_input_tokens": 120000, "max_tokens": 120000, "model_id": "voyage-context-3", "model_name": "Voyage Context 3", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.18, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-finance-2", "model_name": "Voyage Finance 2", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 16000, "max_tokens": 16000, "model_id": "voyage-large-2", "model_name": "Voyage Large 2", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 16000, "max_tokens": 16000, "model_id": "voyage-law-2", "model_name": "Voyage Law 2", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_tokens": 4096, "model_id": "voyage-lite-01", "model_name": "Voyage Lite 01", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 4000, "max_tokens": 4000, "model_id": "voyage-lite-02-instruct", "model_name": "Voyage Lite 02 Instruct", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "voyage-multimodal-3", "model_name": "Voyage Multimodal 3", "provider_id": "voyage", "provider_name": "Voyage AI", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]