What are the best alternatives to Postgres for analytics?

While PostgreSQL is a robust and versatile object-relational database, specialized databases often offer superior performance and features for analytical workloads. The best alternatives to PostgreSQL for analytics typically include columnar databases, hybrid transactional/analytical processing (HTAP) databases, and other relational systems optimized for complex queries and large datasets. Here are some top alternatives to PostgreSQL for analytics: * **ClickHouse**: This open-source, column-oriented database is designed for high-performance analytics and excels at processing large volumes of data for Online Analytical Processing (OLAP) tasks. Its architecture, which leverages data compression, columnar storage, and a vector computation engine, allows for fast query execution, making it ideal for real-time data analytics and managing structured data at scale. * **Snowflake**: A cloud-native data warehousing platform, Snowflake offers advanced flexibility and scalability by separating storage from compute resources. It's a fully managed Software as a Service (SaaS) platform suitable for data warehousing, data lakes, and real-time analytics, supporting a wide variety of data types and workloads. * **Firebolt**: Built specifically for low-latency analytics workloads at terabyte-plus scale, Firebolt uses a columnar data warehouse architecture. It provides efficient data pruning through sparse indexes and simplified partition management, delivering fast dashboards and offloading analytical workloads from production PostgreSQL instances. Firebolt also leverages object storage for cost efficiency and scalability. * **DuckDB**: Often called the "SQLite for analytics," DuckDB is a lightweight, in-process analytical database. It integrates seamlessly with data science tools like pandas, features vectorized query execution, and uses column-oriented storage, making it powerful for large-scale data analysis, ETL processes, and embedded analytics. * **SingleStore**: This database combines transactional and analytical workloads within a single system, utilizing a hybrid storage architecture with in-memory rowstores for transactions and disk-based columnstores for analytics. SingleStore is recognized for real-time analytics and horizontal scalability. * **TiDB**: An open-source HTAP database, TiDB offers horizontal scalability and hybrid transactional-analytical processing. It separates compute from storage and is compatible with the MySQL protocol, making it a strong option for handling both types of workloads without requiring separate data warehouses. * **Microsoft SQL Server**: A widely used relational database, SQL Server offers advanced analytics capabilities, including in-database machine learning and AI Vector Search. It's designed for high availability, scalability, and robust security, making it a strong competitor for complex analytical tasks. * **Oracle Database**: Known for its advanced analytics capabilities, high availability, and scalability, Oracle Database is another powerful relational database alternative for mission-critical applications and complex analyses. * **Google BigQuery**: This fully managed, serverless enterprise data warehouse enables businesses to manage and analyze large data volumes using standard SQL queries. It's highly scalable, cost-effective, and integrates well with other Google Cloud services, supporting features like machine learning and geospatial analysis. * **Apache Cassandra**: A column-oriented NoSQL database, Cassandra is designed for handling large and heterogeneous datasets, offering high availability across multiple nodes and impressive query speeds for specific use cases. Many of these alternatives address PostgreSQL's limitations in handling very large datasets, complex analytical queries, and real-time analytics, where its row-based storage and traditional architecture can introduce bottlenecks and require extensive tuning.

{ "attempts": 1, "backoff_ms_total": 0, "grounding_enabled": true, "latency_ms": 9414, "model": "gemini-2.5-flash", "raw_response": { "automatic_function_calling_history": [], "candidates": [ { "avg_logprobs": null, "citation_metadata": null, "content": { "parts": [ { "code_execution_result": null, "executable_code": null, "file_data": null, "function_call": null, "function_response": null, "inline_data": null, "media_resolution": null, "text": "While PostgreSQL is a robust and versatile object-relational database, specialized databases often offer superior performance and features for analytical workloads. The best alternatives to PostgreSQL for analytics typically include columnar databases, hybrid transactional/analytical processing (HTAP) databases, and other relational systems optimized for complex queries and large datasets.\n\nHere are some top alternatives to PostgreSQL for analytics:\n\n* **ClickHouse**: This open-source, column-oriented database is designed for high-performance analytics and excels at processing large volumes of data for Online Analytical Processing (OLAP) tasks. Its architecture, which leverages data compression, columnar storage, and a vector computation engine, allows for fast query execution, making it ideal for real-time data analytics and managing structured data at scale.\n* **Snowflake**: A cloud-native data warehousing platform, Snowflake offers advanced flexibility and scalability by separating storage from compute resources. It\u0027s a fully managed Software as a Service (SaaS) platform suitable for data warehousing, data lakes, and real-time analytics, supporting a wide variety of data types and workloads.\n* **Firebolt**: Built specifically for low-latency analytics workloads at terabyte-plus scale, Firebolt uses a columnar data warehouse architecture. It provides efficient data pruning through sparse indexes and simplified partition management, delivering fast dashboards and offloading analytical workloads from production PostgreSQL instances. Firebolt also leverages object storage for cost efficiency and scalability.\n* **DuckDB**: Often called the \"SQLite for analytics,\" DuckDB is a lightweight, in-process analytical database. It integrates seamlessly with data science tools like pandas, features vectorized query execution, and uses column-oriented storage, making it powerful for large-scale data analysis, ETL processes, and embedded analytics.\n* **SingleStore**: This database combines transactional and analytical workloads within a single system, utilizing a hybrid storage architecture with in-memory rowstores for transactions and disk-based columnstores for analytics. SingleStore is recognized for real-time analytics and horizontal scalability.\n* **TiDB**: An open-source HTAP database, TiDB offers horizontal scalability and hybrid transactional-analytical processing. It separates compute from storage and is compatible with the MySQL protocol, making it a strong option for handling both types of workloads without requiring separate data warehouses.\n* **Microsoft SQL Server**: A widely used relational database, SQL Server offers advanced analytics capabilities, including in-database machine learning and AI Vector Search. It\u0027s designed for high availability, scalability, and robust security, making it a strong competitor for complex analytical tasks.\n* **Oracle Database**: Known for its advanced analytics capabilities, high availability, and scalability, Oracle Database is another powerful relational database alternative for mission-critical applications and complex analyses.\n* **Google BigQuery**: This fully managed, serverless enterprise data warehouse enables businesses to manage and analyze large data volumes using standard SQL queries. It\u0027s highly scalable, cost-effective, and integrates well with other Google Cloud services, supporting features like machine learning and geospatial analysis.\n* **Apache Cassandra**: A column-oriented NoSQL database, Cassandra is designed for handling large and heterogeneous datasets, offering high availability across multiple nodes and impressive query speeds for specific use cases.\n\nMany of these alternatives address PostgreSQL\u0027s limitations in handling very large datasets, complex analytical queries, and real-time analytics, where its row-based storage and traditional architecture can introduce bottlenecks and require extensive tuning.", "thought": null, "thought_signature": null, "video_metadata": null } ], "role": "model" }, "finish_message": null, "finish_reason": "STOP", "grounding_metadata": { "google_maps_widget_context_token": null, "grounding_chunks": [ { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "cdata.com", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQF2Vo1G7TsPSD2pCA0exoak8utea0wb9Ac_HgiRHaup4NsVE43lhlKLbYCH3rdTlM3soABZtzvl8eSbWx43QPtNkXLSoqEuPwZHzOl1vuvAWH7Fp8vhhqRB-SNvvOJFq9kylwoAjkbD0g==" } }, { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "tigerdata.com", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFmFM6GwHgDaxLuKDfQxn_0fstCXgJ7j9jKNwDll1VrOJ5yP-x_WZaP1itSBwWmA56rZP0YVEBOv0XpSX2HKC38Z-Jczuh3SNoB8t8aTEKwnd1d_wrgouXZkzqN_sdHWuI3njWqIsBzPCysRUK0LPh9eMutbzETSWOTdX2UGNcuBxwo6ST4k4rg_MMydw==" } }, { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "firebolt.io", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQF2buKBoppiptHYdCVBynvPdbuMWbV0w2gnibngW5FT6Hg0WQTWDvQmH9-SA9L8HqeFN54l6kGvRrA4X-xLPSiEq8vIewqoWQNmWs9zNoEnG9W_deBSts-hx7zkZw6g-OUF5IWF9uFD6AoKPNlTkEEaes0gZfoON6x7A0sx" } }, { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "medium.com", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGra8XaDSajKvNFXgFQXBHgDAaiRuLWt4hjPOr8Z0TYcKTwY_Leawp_tKvy2ECO5gjkfzvgIiW2uOOjHE_hcEad_N3EDSuAd9PHxGGU-OGrb5IRNiviptfX7k3w0u8LuZV_knPtWhNJKBFbtOX15Lcy7x_EMb6_AWGLVEkIGrv6_w7ogUlELQQze_815dP9pw7aMS1C3Zsz6z9wQcju9Judh3ksqJQLYsRWc2ZbVJ8VNawZ58sjF-a7XNYYWYWILw==" } }, { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "betterstack.com", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFH2qAkY861esdCW9asNiBnZvKQqmgfYxIy-_gdSohTP23OsoTFpy6R5DOIr87afYrrU3tI5FX0gHt1eCXh6xL7cVnWX-IZtOcBgKaXI6hgH4XbEgjVJ1nNAr8rCmnJ8vo1JYMqni01T97uoD33FyHeDxakDZCfZNIaqB2bZcUorsiCZw==" } }, { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "g2.com", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQGpesHQfFHorSKH1Gry4NAd9JUASEAncaqVYP5P3CCXUrD-9bNVAEG52McMyaWGBHYwZQ4AjZee0BkCA3tDEkbxX1PIwljsA7GlVEV9v3FIJV_ReAtTGgdWnASomdkymPk4c0UJK7rtslIUxU30c3LDP5NkqV-mW4iK1A==" } }, { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "toucantoco.com", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQG612eX9lsshDcH2hrOPPjnPSnFyanhU8XWvchNTjta4rh583uqpjVeO2vpMRBzFqECnjqBDamgwTDdGkKQJFTiFaQKo50V507RzPTFwZU0kqaOLXD3R8AZcgjezhfGV8vIuCkLdsaBp5vPmHB2TyZ1Bp4Q4h2Vq3d01QifWA==" } }, { "maps": null, "retrieved_context": null, "web": { "domain": null, "title": "ionos.com", "uri": "https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEzHnrKAcM_BqWf3rbIp39kjj7FIDmGQdIc6eM8u6ZPk7UIeE8fAkcE168ybudM_Q9w-Wk0SW2S19Au-pAqLX0s48k15zEyfmjXMgj3djFjfeG82BiNG9_ldE1h3Refu1MCp4RShysai-BqC4VeTSgG0RBWMR07LzW9qAPMDb2giovKYIM9xA==" } } ], "grounding_supports": [ { "confidence_scores": null, "grounding_chunk_indices": [ 0, 1 ], "segment": { "end_index": 874, "part_index": null, "start_index": 655, "text": "Its architecture, which leverages data compression, columnar storage, and a vector computation engine, allows for fast query execution, making it ideal for real-time data analytics and managing structured data at scale." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 0 ], "segment": { "end_index": 1217, "part_index": null, "start_index": 1036, "text": "It\u0027s a fully managed Software as a Service (SaaS) platform suitable for data warehousing, data lakes, and real-time analytics, supporting a wide variety of data types and workloads." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 2 ], "segment": { "end_index": 1640, "part_index": null, "start_index": 1565, "text": "Firebolt also leverages object storage for cost efficiency and scalability." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 3 ], "segment": { "end_index": 1976, "part_index": null, "start_index": 1755, "text": "It integrates seamlessly with data science tools like pandas, features vectorized query execution, and uses column-oriented storage, making it powerful for large-scale data analysis, ETL processes, and embedded analytics." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 4 ], "segment": { "end_index": 2286, "part_index": null, "start_index": 2209, "text": "SingleStore is recognized for real-time analytics and horizontal scalability." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 4 ], "segment": { "end_index": 2597, "part_index": null, "start_index": 2414, "text": "It separates compute from storage and is compatible with the MySQL protocol, making it a strong option for handling both types of workloads without requiring separate data warehouses." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 5 ], "segment": { "end_index": 2905, "part_index": null, "start_index": 2775, "text": "It\u0027s designed for high availability, scalability, and robust security, making it a strong competitor for complex analytical tasks." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 5 ], "segment": { "end_index": 3137, "part_index": null, "start_index": 2906, "text": "* **Oracle Database**: Known for its advanced analytics capabilities, high availability, and scalability, Oracle Database is another powerful relational database alternative for mission-critical applications and complex analyses." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 6 ], "segment": { "end_index": 3466, "part_index": null, "start_index": 3308, "text": "It\u0027s highly scalable, cost-effective, and integrates well with other Google Cloud services, supporting features like machine learning and geospatial analysis." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 7 ], "segment": { "end_index": 3696, "part_index": null, "start_index": 3467, "text": "* **Apache Cassandra**: A column-oriented NoSQL database, Cassandra is designed for handling large and heterogeneous datasets, offering high availability across multiple nodes and impressive query speeds for specific use cases." } }, { "confidence_scores": null, "grounding_chunk_indices": [ 2, 1 ], "segment": { "end_index": 3956, "part_index": null, "start_index": 3698, "text": "Many of these alternatives address PostgreSQL\u0027s limitations in handling very large datasets, complex analytical queries, and real-time analytics, where its row-based storage and traditional architecture can introduce bottlenecks and require extensive tuning." } } ], "retrieval_metadata": null, "retrieval_queries": null, "search_entry_point": { "rendered_content": "\u003cstyle\u003e\n.container {\n align-items: center;\n border-radius: 8px;\n display: flex;\n font-family: Google Sans, Roboto, sans-serif;\n font-size: 14px;\n line-height: 20px;\n padding: 8px 12px;\n}\n.chip {\n display: inline-block;\n border: solid 1px;\n border-radius: 16px;\n min-width: 14px;\n padding: 5px 16px;\n text-align: center;\n user-select: none;\n margin: 0 8px;\n -webkit-tap-highlight-color: transparent;\n}\n.carousel {\n overflow: auto;\n scrollbar-width: none;\n white-space: nowrap;\n margin-right: -12px;\n}\n.headline {\n display: flex;\n margin-right: 4px;\n}\n.gradient-container {\n position: relative;\n}\n.gradient {\n position: absolute;\n transform: translate(3px, -9px);\n height: 36px;\n width: 9px;\n}\n@media (prefers-color-scheme: light) {\n .container {\n background-color: #fafafa;\n box-shadow: 0 0 0 1px #0000000f;\n }\n .headline-label {\n color: #1f1f1f;\n }\n .chip {\n background-color: #ffffff;\n border-color: #d2d2d2;\n color: #5e5e5e;\n text-decoration: none;\n }\n .chip:hover {\n background-color: #f2f2f2;\n }\n .chip:focus {\n background-color: #f2f2f2;\n }\n .chip:active {\n background-color: #d8d8d8;\n border-color: #b6b6b6;\n }\n .logo-dark {\n display: none;\n }\n .gradient {\n background: linear-gradient(90deg, #fafafa 15%, #fafafa00 100%);\n }\n}\n@media (prefers-color-scheme: dark) {\n .container {\n background-color: #1f1f1f;\n box-shadow: 0 0 0 1px #ffffff26;\n }\n .headline-label {\n color: #fff;\n }\n .chip {\n background-color: #2c2c2c;\n border-color: #3c4043;\n color: #fff;\n text-decoration: none;\n }\n .chip:hover {\n background-color: #353536;\n }\n .chip:focus {\n background-color: #353536;\n }\n .chip:active {\n background-color: #464849;\n border-color: #53575b;\n }\n .logo-light {\n display: none;\n }\n .gradient {\n background: linear-gradient(90deg, #1f1f1f 15%, #1f1f1f00 100%);\n }\n}\n\u003c/style\u003e\n\u003cdiv class=\"container\"\u003e\n \u003cdiv class=\"headline\"\u003e\n \u003csvg class=\"logo-light\" width=\"18\" height=\"18\" viewBox=\"9 9 35 35\" fill=\"none\" xmlns=\"http://www.w3.org/2000/svg\"\u003e\n \u003cpath fill-rule=\"evenodd\" clip-rule=\"evenodd\" d=\"M42.8622 27.0064C42.8622 25.7839 42.7525 24.6084 42.5487 23.4799H26.3109V30.1568H35.5897C35.1821 32.3041 33.9596 34.1222 32.1258 35.3448V39.6864H37.7213C40.9814 36.677 42.8622 32.2571 42.8622 27.0064V27.0064Z\" fill=\"#4285F4\"/\u003e\n \u003cpath fill-rule=\"evenodd\" clip-rule=\"evenodd\" d=\"M26.3109 43.8555C30.9659 43.8555 34.8687 42.3195 37.7213 39.6863L32.1258 35.3447C30.5898 36.3792 28.6306 37.0061 26.3109 37.0061C21.8282 37.0061 18.0195 33.9811 16.6559 29.906H10.9194V34.3573C13.7563 39.9841 19.5712 43.8555 26.3109 43.8555V43.8555Z\" fill=\"#34A853\"/\u003e\n \u003cpath fill-rule=\"evenodd\" clip-rule=\"evenodd\" d=\"M16.6559 29.8904C16.3111 28.8559 16.1074 27.7588 16.1074 26.6146C16.1074 25.4704 16.3111 24.3733 16.6559 23.3388V18.8875H10.9194C9.74388 21.2072 9.06992 23.8247 9.06992 26.6146C9.06992 29.4045 9.74388 32.022 10.9194 34.3417L15.3864 30.8621L16.6559 29.8904V29.8904Z\" fill=\"#FBBC05\"/\u003e\n \u003cpath fill-rule=\"evenodd\" clip-rule=\"evenodd\" d=\"M26.3109 16.2386C28.85 16.2386 31.107 17.1164 32.9095 18.8091L37.8466 13.8719C34.853 11.082 30.9659 9.3736 26.3109 9.3736C19.5712 9.3736 13.7563 13.245 10.9194 18.8875L16.6559 23.3388C18.0195 19.2636 21.8282 16.2386 26.3109 16.2386V16.2386Z\" fill=\"#EA4335\"/\u003e\n \u003c/svg\u003e\n \u003csvg class=\"logo-dark\" width=\"18\" height=\"18\" viewBox=\"0 0 48 48\" xmlns=\"http://www.w3.org/2000/svg\"\u003e\n \u003ccircle cx=\"24\" cy=\"23\" fill=\"#FFF\" r=\"22\"/\u003e\n \u003cpath d=\"M33.76 34.26c2.75-2.56 4.49-6.37 4.49-11.26 0-.89-.08-1.84-.29-3H24.01v5.99h8.03c-.4 2.02-1.5 3.56-3.07 4.56v.75l3.91 2.97h.88z\" fill=\"#4285F4\"/\u003e\n \u003cpath d=\"M15.58 25.77A8.845 8.845 0 0 0 24 31.86c1.92 0 3.62-.46 4.97-1.31l4.79 3.71C31.14 36.7 27.65 38 24 38c-5.93 0-11.01-3.4-13.45-8.36l.17-1.01 4.06-2.85h.8z\" fill=\"#34A853\"/\u003e\n \u003cpath d=\"M15.59 20.21a8.864 8.864 0 0 0 0 5.58l-5.03 3.86c-.98-2-1.53-4.25-1.53-6.64 0-2.39.55-4.64 1.53-6.64l1-.22 3.81 2.98.22 1.08z\" fill=\"#FBBC05\"/\u003e\n \u003cpath d=\"M24 14.14c2.11 0 4.02.75 5.52 1.98l4.36-4.36C31.22 9.43 27.81 8 24 8c-5.93 0-11.01 3.4-13.45 8.36l5.03 3.85A8.86 8.86 0 0 1 24 14.14z\" fill=\"#EA4335\"/\u003e\n \u003c/svg\u003e\n \u003cdiv class=\"gradient-container\"\u003e\u003cdiv class=\"gradient\"\u003e\u003c/div\u003e\u003c/div\u003e\n \u003c/div\u003e\n \u003cdiv class=\"carousel\"\u003e\n \u003ca class=\"chip\" href=\"https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQHBge0V8FN8oEBqlv4TTtrmS6NM6yTf-ubcAzXr8nWuTB2MCd2Qw6T2AteIVi29Ffpgm8C23oLACKjIZXbkzVDElvzbb4sEscGbpBZtLLTrknikQyUinFNPKsFddtsnUQMGUQZGw-kdCvGeCnvai0gh2qdPZiUkDkelCbpzDvuKTqaTSRGFG0fFyrdxfAC2pHjtrWeZmFMg5IYauMmCBCrpbYv-Cw==\"\u003edatabases optimized for analytics\u003c/a\u003e\n \u003ca class=\"chip\" href=\"https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQEAuoWfPAKap2z8GYrUzv_D0qkBf-aD1738GLA_BQPjqfdx-Q9cFRx1YTU1cHgoqUEFGs0uPDrds63O9hhcJ-7MrsE0peDCRuF60fnZ7U_7LF9xo5-z0ciNOMAxXpl6QG3Jye4DFguP7bHKWog3GvbeQJrmVq7VJZB41pTPlJQMqahcMOGelq5gb78LCtv7fuL1KveB3EBVsAI4B3iXNjELc6xR2yGS7OqiW9p5lECnvw==\"\u003ebest alternatives to PostgreSQL for analytics\u003c/a\u003e\n \u003ca class=\"chip\" href=\"https://vertexaisearch.cloud.google.com/grounding-api-redirect/AUZIYQFZ04DxJzHzoApUiz5ChO9ipNMWd0fu2DQmsnWXad2-VPo14Pq70UPfx4a9MJimWAwT6z8LPptmNX67b9I_5S0c1Ckv69RemAT5BTcCNQFMZVBbr7D_75POY2pzhUELU2ZSToiS7RYZ8BFZS-EU9ieSEW6FJ5LSKIVAAzsmyQaP47taJAMnqSBxp5UIE42uNuE54PA1z9EkC9VIMhSdxLNiagqCVU8XMEH5GM3oY8TzIzKs\"\u003edatabase alternatives to Postgres for analytics\u003c/a\u003e\n \u003c/div\u003e\n\u003c/div\u003e\n", "sdk_blob": null }, "source_flagging_uris": null, "web_search_queries": [ "best alternatives to PostgreSQL for analytics", "database alternatives to Postgres for analytics", "databases optimized for analytics" ] }, "index": 0, "logprobs_result": null, "safety_ratings": null, "token_count": null, "url_context_metadata": null } ], "create_time": null, "model_version": "gemini-2.5-flash", "parsed": null, "prompt_feedback": null, "response_id": "PaiMacnPDOSCvdIPlffX6Aw", "sdk_http_response": { "body": null, "headers": { "alt-svc": "h3=\":443\"; ma=2592000,h3-29=\":443\"; ma=2592000", "content-encoding": "gzip", "content-type": "application/json; charset=UTF-8", "date": "Wed, 11 Feb 2026 16:03:09 GMT", "server": "scaffolding on HTTPServer2", "server-timing": "gfet4t7; dur=9160", "transfer-encoding": "chunked", "vary": "Origin, X-Origin, Referer", "x-content-type-options": "nosniff", "x-frame-options": "SAMEORIGIN", "x-xss-protection": "0" } }, "usage_metadata": { "cache_tokens_details": null, "cached_content_token_count": null, "candidates_token_count": 730, "candidates_tokens_details": null, "prompt_token_count": 70, "prompt_tokens_details": [ { "modality": "TEXT", "token_count": 70 } ], "thoughts_token_count": 428, "tool_use_prompt_token_count": 170, "tool_use_prompt_tokens_details": [ { "modality": "TEXT", "token_count": 170 } ], "total_token_count": 1398, "traffic_type": null } }, "request_payload": { "input": { "contents": "You are answering a user query. Be concise but helpful.\nIf you mention products or brands, be specific.\nDo not invent facts. If unsure, say you are unsure.\n\nBrand under analysis: Metabase1\nBrand website: https://metabase.com\n\nUser query: What are the best alternatives to Postgres for analytics?", "model": "gemini-2.5-flash" }, "model": "gemini-2.5-flash", "provider": "gemini" }, "retry_policy": { "base_backoff_s": 0.6, "max_retries": 3, "timeout_s": 60 }, "usage": { "cost_usd": 0.0018459999999999998, "input_tokens": 70, "model": "gemini-2.5-flash", "output_tokens": 730, "pricing_source": "local_price_table_v1", "provider": "gemini", "total_tokens": 1398 }, "usage_raw": { "cache_tokens_details": null, "cached_content_token_count": null, "candidates_token_count": 730, "candidates_tokens_details": null, "prompt_token_count": 70, "prompt_tokens_details": [ { "modality": "TEXT", "token_count": 70 } ], "thoughts_token_count": 428, "tool_use_prompt_token_count": 170, "tool_use_prompt_tokens_details": [ { "modality": "TEXT", "token_count": 170 } ], "total_token_count": 1398, "traffic_type": null } }

{ "input": { "contents": "You are answering a user query. Be concise but helpful.\nIf you mention products or brands, be specific.\nDo not invent facts. If unsure, say you are unsure.\n\nBrand under analysis: Metabase1\nBrand website: https://metabase.com\n\nUser query: What are the best alternatives to Postgres for analytics?", "model": "gemini-2.5-flash" }, "model": "gemini-2.5-flash", "provider": "gemini" }

null