Quickstart

{
  "id": "resp_e80c520d-2788-4b3d-8662-6a0e3d611e8f",
  "created_at": 1779391438,
  "model": "openai/gpt-5.1",
  "object": "response",
  "output": [
    {
      "results": [
        {
          "id": 1,
          "snippet": "Abstract:The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.\nThe best performing models also connect the encoder and decoder through an attention mechanism.\nWe propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely.\nExperiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train.\nOur model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU.\nOn the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature.\nWe show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.",
          "title": "[1706.03762] Attention Is All You Need - arXiv",
          "url": "https://arxiv.org/abs/1706.03762",
          "date": "2017-06-12",
          "last_updated": "2026-05-19",
          "source": "web"
        },
        {
          "id": 2,
          "snippet": "At each layer, each token is then contextualized within the scope of the context window with other (unmasked) tokens via a parallel multi-head attention mechanism, allowing the signal for key tokens to be amplified and less important tokens to be diminished.\n...\nThe original version of the transformer architecture was proposed in the 2017 paper \"Attention Is All You Need\" by researchers at Google.\nThe predecessors of transformers were developed as an improvement over previous architectures for machine translation, but have found many applications since.\n...\nOn 2017-06-12, the original (100M-parameter) encoder–decoder transformer model was published in the \"Attention is all you need\" paper.\nAt the time, the focus of the research was on improving seq2seq for machine translation, by removing its recurrence to process all tokens in parallel, but preserving its dot-product attention mechanism to keep its text processing performance.\nThis led to the introduction of a multi-head attention model that was easier to parallelize due to the use of independent heads and the lack of recurrence.\nIts parallelizability was an important factor to its widespread use in large neural networks.",
          "title": "Transformer (deep learning) - Wikipedia",
          "url": "https://en.wikipedia.org/wiki/Transformer_(deep_learning)",
          "date": "2019-08-25",
          "last_updated": "2026-05-15",
          "source": "web"
        },
        {
          "id": 3,
          "snippet": "We propose a novel, simple network architecture based solely onan attention mechanism, dispensing with recurrence and convolutions entirely.Experiments on two machine translation tasks show these models to be superiorin quality while being more parallelizable and requiring significantly less timeto train.",
          "title": "Attention is All you Need - NIPS papers",
          "url": "https://papers.nips.cc/paper/7181-attention-is-all-you-need",
          "date": "2017-01-01",
          "last_updated": "2026-05-21",
          "source": "web"
        },
        {
          "id": 4,
          "snippet": "The paper introduced a new deep learning architecture known as the transformer, based on the attention mechanism proposed in 2014 by Bahdanau *et al.* The transformer approach it describes has become the main architecture of a wide variety of artificial intelligence, including large language models.\nAt the time, the focus of the research was on improving Seq2seq techniques for machine translation, but the authors go further in the paper, foreseeing the technique's potential for other tasks like question answering and what is now known as multimodal generative AI.\n...\nThe paper is best known for introducing the Transformer architecture, which underlies most modern large language models (LLMs).\nA key reason why the architecture is preferred by most modern LLMs is the parallelizability of the architecture over its predecessors.\nThis ensures that the operations necessary for training can be accelerated on a GPU, allowing both faster training times and models of bigger sizes to be trained.\n...\nOn 2017-06-12, the original (100M-parameter) encoder–decoder transformer model was published in the \"Attention is all you need\" paper.",
          "title": "Attention Is All You Need - Wikipedia",
          "url": "https://en.wikipedia.org/wiki/Attention_Is_All_You_Need",
          "date": "2023-12-04",
          "last_updated": "2026-05-17",
          "source": "web"
        },
        {
          "id": 5,
          "snippet": "In this video, YC's Ankit Gupta traces how AI learned to understand language — from early RNNs and LSTMs to attention mechanisms and the breakthrough 2017 paper Attention Is All You Need — the discovery that unlocked the modern AI era.\n...\n{ts:17} [Music] A transformer is a neural network that uses self attention to take input data\n{ts:26} like text or images, model the relationships between that data, and finally generate outputs like meaningful\n{ts:32} text responses, translations, or classifications.\n...\nThen came the big breakthrough in 2017 when a team of researchers at\n{ts:387} Google published a paper called attention is all you need, which proposed a new machine translation\n{ts:392} architecture that they called a transformer.\n...\n{ts:409} version of the encoder decoder architecture originally proposed in seek to seek.\nInstead of compressing inputs\n{ts:414} into a single vector embedding, transformers kept separate embeddings for each input token and updated these\n{ts:420} through self attention, a mechanism that updated token representations based on a learned weighted dotproduct over the\n{ts:426} embeddings of all other tokens in the sequence.\nBecause each token in this architecture could attend to all others\n{ts:431} simultaneously, transformers could process an entire sequence in parallel, making them dramatically faster than\n{ts:437} RNN's.\nRemarkably, they were also much more accurate on machine translation benchmarks.",
          "title": "Transformers Explained: The Discovery That Changed AI Forever",
          "url": "https://www.youtube.com/watch?v=JZLZQVmfGn8&vl=en-US",
          "date": "2025-10-23",
          "last_updated": "2026-03-27",
          "source": "web"
        },
        {
          "id": 6,
          "snippet": "●Presents a new neural architecture named the Transformer\n●Based solely on the attention mechanism widely used in SEQ2SEQ models\n●More parallelizable compared to existing state-of-the-art (SOTA) models\n●Achieves SOTA in 2 machine translation datasets\n…\n...\n• Less total computational complexity per layer\n• More parallelizable than existing fully autoregressive models\n• Shorten the path between tokens to enable model to learn long-term \ndependency better\n...\nIntroduces a groundbreaking new model that is solely based on attention\n●\nFaster and better than existing models\n●",
          "title": "[PDF] Attention Is All You Need",
          "url": "https://ysu1989.github.io/courses/au20/cse5539/Transformer.pdf",
          "date": null,
          "last_updated": "2026-05-15",
          "source": "web"
        },
        {
          "id": 7,
          "snippet": "The Transformer architecture has revolutionized natural language processing (NLP) since its introduction, establishing itself as a cornerstone for modern advancements in the field.\nThis architecture offers significant improvements in handling a wide range of NLP tasks, from translation to text summarization, by overcoming limitations inherent in previous models.\nIntroduced by Vaswani et al. in the paper “Attention is All You Need” in 2017, the Transformer architecture is characterized by its use of self-attention mechanisms and feed-forward neural networks.\nUnlike its predecessors, such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), which process data sequentially, the Transformer processes input data in parallel.\nThis parallelization enables the model to leverage modern hardware more efficiently, resulting in faster training times and improved scalability.\nAt the heart of the Transformer is the self-attention mechanism, which allows the model to weigh the significance of different words in a sentence relative to each other.\nThis feature is critical for understanding contextual relationships and dependencies, regardless of the distance between words in the input sequence.\n...\nThis capacity to capture global dependencies without the constraints of sequential data processing is a notable advantage over traditional models.\n...\nThe Transformer architecture’s flexibility makes it suitable for a broad spectrum of NLP applications.\nIn machine translation, it has significantly improved the accuracy and fluency of translated text.\nFor tasks like text summarization, sentiment analysis, and question answering, Transformers provide state-of-the-art results by effectively capturing and modeling complex language patterns.\n...\nIn summary, the Transformer architecture has fundamentally changed the landscape of NLP by introducing a novel approach to processing and understanding language data.\nIts innovative use of self-attention and parallel processing has paved the way for numerous breakthroughs, making it an essential tool for anyone looking to advance in the field of natural language processing.",
          "title": "What is the Transformer architecture in NLP? - Milvus",
          "url": "https://milvus.io/ai-quick-reference/what-is-the-transformer-architecture-in-nlp",
          "date": "2026-03-26",
          "last_updated": "2026-05-13",
          "source": "web"
        },
        {
          "id": 8,
          "snippet": "In “Attention Is All You Need”, we introduce the Transformer, a novel neural network architecture based on a self-attention mechanism that we believe to be particularly well suited for language understanding.\nIn our paper, we show that the Transformer outperforms both recurrent and convolutional models on academic English to German and English to French translation benchmarks.\nOn top of higher translation quality, the Transformer requires less computation to train and is a much better fit for modern machine learning hardware, speeding up training by up to an order of magnitude.\n...\nIn contrast, the Transformer only performs a small, constant number of steps (chosen empirically).\nIn each step, it applies a self-attention mechanism which directly models relationships between all words in a sentence, regardless of their respective position.",
          "title": "Transformer: A Novel Neural Network Architecture for Language ...",
          "url": "https://research.google/blog/transformer-a-novel-neural-network-architecture-for-language-understanding/",
          "date": null,
          "last_updated": "2026-05-17",
          "source": "web"
        },
        {
          "id": 9,
          "snippet": "A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.",
          "title": "[PDF] Attention is All you Need | Semantic Scholar",
          "url": "https://www.semanticscholar.org/paper/Attention-is-All-you-Need-Vaswani-Shazeer/204e3073870fae3d05bcbc2f6a8e263d9b72e776",
          "date": "2017-06-12",
          "last_updated": "2025-03-22",
          "source": "web"
        },
        {
          "id": 10,
          "snippet": "Abstract:Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text.\nThis paper explores the advancements in transformer models, such as BERT and GPT, focusing on their superior performance in text understanding tasks compared to traditional methods like recurrent neural networks (RNNs).\nBy analyzing statistical properties through visual representations-including probability density functions of text length distributions and feature space classifications-the study highlights the models' proficiency in handling long-range dependencies, adapting to conditional shifts, and extracting features for classification, even with overlapping classes.\nDrawing on recent 2024 research, including enhancements in multi-hop knowledge graph reasoning and context-aware chat interactions, the paper outlines a methodology involving data preparation, model selection, pretraining, fine-tuning, and evaluation.\nThe results demonstrate state-of-the-art performance on benchmarks like GLUE and SQuAD, with F1 scores exceeding 90%, though challenges such as high computational costs persist.\nThis work underscores the pivotal role of transformers in modern NLP and suggests future directions, including efficiency optimization and multimodal integration, to further advance language-based AI systems.",
          "title": "Exploring Transformer-Based Architectures for Text Understanding",
          "url": "https://arxiv.org/abs/2503.20227",
          "date": "2025-03-26",
          "last_updated": "2026-02-21",
          "source": "web"
        }
      ],
      "type": "search_results",
      "queries": [
        "Attention Is All You Need transformer paper core contributions",
        "why transformer architecture changed NLP",
        "Vaswani et al 2017 attention is all you need key results"
      ]
    },
    {
      "id": "msg_b9dc751b-50fd-4941-ad3d-00bb2eb98f73",
      "content": [
        {
          "text": "The paper “Attention Is All You Need” introduced the **Transformer**, a sequence‑to‑sequence model built entirely from attention and feed‑forward layers, and showed it could beat recurrent and convolutional models on machine translation while training much faster and scaling better.[web:1][web:8] This architectural shift made self‑attention the default building block for modern NLP and enabled today’s large language models.[web:2][web:4][web:7]\n\n## Core technical ideas\n\n- The Transformer removes recurrence and convolutions, using stacked self‑attention and position‑wise feed‑forward layers in both encoder and decoder.[web:1][web:3] Positional encodings are added to token embeddings so the model can represent order despite having no recurrence.[web:1]  \n- It introduces **multi‑head** attention: several parallel attention heads project queries/keys/values, attend in different subspaces, then concatenate and linearly mix their outputs.[web:1][web:2] This lets the model capture different types of relations (e.g., syntax and coreference) in parallel.[web:1]  \n- The paper emphasizes three attention types within the architecture: encoder self‑attention, decoder masked self‑attention (preventing access to future tokens), and encoder‑decoder attention where the decoder attends over encoder outputs.[web:1][web:8]\n\n## Empirical results in the paper\n\n- On WMT 2014 English→German translation, the base Transformer reaches 28.4 BLEU, surpassing prior state of the art, including ensembles, by over 2 BLEU.[web:1][web:3] On WMT 2014 English→French, a single Transformer achieves 41.8 BLEU after 3.5 days of training on 8 GPUs, outperforming earlier, much more expensive systems.[web:1]  \n- The authors also show the model generalizes beyond translation by achieving strong results on English constituency parsing, even with limited labeled data.[web:1][web:9] These results demonstrate that attention‑only architectures are not just viable but competitive across sequence tasks.[web:1]\n\n## Why it was faster and more scalable\n\n- Self‑attention lets the model process all tokens in a sequence in parallel, unlike RNNs/LSTMs that must step through tokens sequentially, which makes it far more compatible with GPU/TPU hardware.[web:1][web:7] This parallelism reduced training time “by up to an order of magnitude” relative to recurrent models on the same tasks.[web:8]  \n- For typical sequence lengths, the attention‑based layers in the paper have lower or comparable per‑layer computational complexity than recurrent or convolutional alternatives and much shorter paths between distant tokens, which helps learn long‑range dependencies.[web:1][web:6] This combination of efficiency and representational power is what made large‑scale pretraining feasible.[web:7][web:10]\n\n## How it changed NLP\n\n- The Transformer architecture became the foundation for major pretrained models such as BERT (encoder‑only), GPT (decoder‑only), and many others, which now dominate benchmarks in translation, question answering, summarization, and general language modeling.[web:2][web:7][web:10] These models exploit the same self‑attention blocks introduced in the 2017 paper, often with minor variants.[web:2]  \n- By showing that attention‑only, highly parallel architectures can outperform traditional sequence models, the paper shifted the field’s default design pattern from RNNs/CNNs to transformers and opened the path to scaling parameters and data to today’s very large language models.[web:2][web:4][web:7] Its influence now extends beyond NLP to vision, speech, and multimodal models that reuse the same core transformer building blocks.[web:2][web:4]",
          "type": "output_text",
          "annotations": [],
          "logprobs": []
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "status": "completed",
  "error": null,
  "usage": {
    "input_tokens": 6620,
    "output_tokens": 863,
    "total_tokens": 7483,
    "cost": {
      "currency": "USD",
      "input_cost": 0.0038,
      "output_cost": 0.00863,
      "total_cost": 0.01788,
      "cache_creation_cost": null,
      "cache_read_cost": 0.00045,
      "tool_calls_cost": 0.005
    },
    "input_tokens_details": {
      "cache_creation_input_tokens": 0,
      "cache_read_input_tokens": 3584,
      "cached_tokens": 3584
    },
    "tool_calls_details": {
      "search_web": {
        "invocation": 1
      }
    },
    "output_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "background": false,
  "completed_at": 1779391438,
  "frequency_penalty": 0,
  "incomplete_details": null,
  "instructions": "## Abstract\n<role>\nYou are an AI assistant developed by Perplexity AI. Given a user's query, your goal is to generate an expert, useful, factually correct, and contextually relevant response by leveraging available tools and conversation history. First, you will receive the tools you can call iteratively to gather the necessary knowledge for your response. You need to use these tools rather than using internal knowledge. Second, you will receive guidelines to format your response for clear and effective presentation. Third, you will receive guidelines for citation practices to maintain factual accuracy and credibility.\n</role>\n\n## Instructions\n<tools_workflow>\nBegin each turn with tool calls to gather information. You must call at least one tool before answering, even if information exists in your knowledge base. Decompose complex user queries into discrete tool calls for accuracy and parallelization. After each tool call, assess if your output fully addresses the query and its subcomponents. Continue until the user query is resolved or until the <tool_call_limit> below is reached. End your turn with a comprehensive response. Never mention tool calls in your final response as it would badly impact user experience.\n\n<tool_call_limit> Make at most three tool calls before concluding.</tool_call_limit>\n</tools_workflow>\n\n## Citation Instructions\n<citation_instructions>\nYour response must include at least 1 citation. Add a citation to every sentence that includes information derived from tool outputs.\nTool results are provided using `id` in the format `type:index`. `type` is the data source or context. `index` is the unique identifier per citation.\n<common_source_types> are included below.\n\n<common_source_types>\n- `web`: Internet sources\n- `page`: Full web page content\n- `conversation_history`: past queries and answers from your interaction with the user\n</common_source_types>\n\n<formatting_citations>\nUse brackets to indicate citations like this: [type:index]. Commas, dashes, or alternate formats are not valid citation formats. If citing multiple sources, write each citation in a separate bracket like [web:1][web:2][web:3].\n\nCorrect: \"The Eiffel Tower is in Paris [web:3].\"\nIncorrect: \"The Eiffel Tower is in Paris [web-3].\"\n</formatting_citations>\n\nYour citations must be inline - not in a separate References or Citations section. Cite the source immediately after each sentence containing referenced information. If your response presents a markdown table with referenced information from `web`, `memory`, `attached_file`, or `calendar_event` tool result, cite appropriately within table cells directly after relevant data instead in of a new column. Do not cite `generated_image` or `generated_video` inside table cells.\n\n## Response Guidelines\n<response_guidelines>\nResponses are displayed on web interfaces where users should not need to scroll extensively. Limit responses to 5 sections maximum. Users can ask follow-up questions if they need additional detail. Prioritize the most relevant information for the initial query.\n\n### Answer Formatting\n- Begin with a direct 1-2 sentence answer to the core question.\n- Organize the rest of your answer into sections led with Markdown headers (using ##, ###) when appropriate to ensure clarity (e.g. entity definitions, biographies, and wikis).\n- Your answer should be at least 3 sentences long.\n- Each Markdown header should be concise (less than 6 words) and meaningful.\n- Markdown headers should be plain text, not numbered.\n- Between each Markdown header is a section consisting of 2-3 well-cited sentences.\n- When comparing entities with multiple dimensions, use a markdown table to show differences (instead of lists).\n- Whenever possible, present information as bullet point lists to improve readability.\n- You are allowed to bold at most one word (**example**) per paragraph. You can't bold consecutive words.\n- For grouping multiple related items, present the information with a mix of paragraphs and bullet point lists. Do not nest lists within other lists.\n\n### Tone\n<tone>\nExplain clearly using plain language. Use active voice and vary sentence structure to sound natural. Ensure smooth transitions between sentences. Avoid personal pronouns like \"I\". Keep explanations direct; use examples or metaphors only when they meaningfully clarify complex concepts that would otherwise be unclear.\n</tone>\n\n### Lists and Paragraphs\n<lists_and_paragraphs>\nUse lists for: multiple facts/recommendations, steps, features/benefits, comparisons, or biographical information.\n\nAvoid repeating content in both intro paragraphs and list items. Keep intros minimal. Either start directly with a header and list, or provide 1 sentence of context only.\n\nList formatting:\n- Use numbers when sequence matters; otherwise bullets (-) with a space after the dash.\n- Use numbers when sequence matters; otherwise bullets (-).\n- No whitespace before bullets (i.e. no indenting), one item per line.\n- Sentence capitalization; periods only for complete sentences.\n\nParagraphs:\n- Use for brief context (2-3 sentences max) or simple answers\n- Separate with blank lines\n- If exceeding 3 consecutive sentences, consider restructuring as a list\n</lists_and_paragraphs>\n\n### Summaries and Conclusions\n<summaries_and_conclusions>\nAvoid summaries and conclusions. They are not needed and are repetitive. Markdown tables are not for summaries. For comparisons, provide a table to compare, but avoid labeling it as 'Comparison/Key Table', provide a more meaningful title.\n</summaries_and_conclusions>\n\n## Prohibited Meta-Commentary\n<prohibited_commentary>\n- Never reference your information gathering process in your final answer.\n- Do not use phrases such as:\n- \"Based on my search results...\"\n- \"Now I have gathered comprehensive information...\"\n- \"According to my research...\"\n- \"My search revealed...\"\n- \"I found information about...\"\n- \"Let me provide a detailed answer...\"\n- \"Let me compile this information...\"\n- \"Short Answer: ...\"\n- Begin answers immediately with factual content that directly addresses the user's query.\n</prohibited_commentary>\n\n<copyright_requirements>\n- Never reproduce copyrighted content (text, lyrics, etc.)\n- You may share public domain content (expired copyrights, traditional works)\n- When copyright status is uncertain, treat as copyrighted\n- Keep summaries brief (under 30 words) and original — don't reconstruct sources\n- Brief factual statements (names, dates, facts) are always acceptable\n</copyright_requirements>\n\nCurrent date: Thursday, May 21, 2026\n\n",
  "max_output_tokens": 8192,
  "max_tool_calls": null,
  "metadata": {},
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "reasoning": null,
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [
    {
      "type": "web_search"
    },
    {
      "type": "fetch_url"
    }
  ],
  "top_logprobs": 0,
  "top_p": 1,
  "truncation": "disabled",
  "user": null
}

{
  "id": "3dbbb4d2-8102-47e7-8457-402f9f83c4df",
  "results": [
    {
      "snippet": "",
      "title": "SpaceX Starship - Wikipedia",
      "url": "https://en.wikipedia.org/wiki/SpaceX_Starship",
      "date": "2018-11-21",
      "last_updated": "2026-05-19"
    },
    {
      "snippet": "",
      "title": "Starship flight test 1 - Wikipedia",
      "url": "https://en.wikipedia.org/wiki/Starship_flight_test_1",
      "date": "2022-05-28",
      "last_updated": "2026-05-13"
    },
    {
      "snippet": "",
      "title": "SpaceX Starship (spacecraft) - Wikipedia",
      "url": "https://en.wikipedia.org/wiki/SpaceX_Starship_(spacecraft)",
      "date": "2023-04-29",
      "last_updated": "2026-04-05"
    },
    {
      "snippet": "On June 19, a Starship prototype exploded on the launch pad at SpaceX’s Starbase facility in Texas during preparations for what would be its tenth test flight.\nAfter three consecutive failed orbital attempts this year, the upcoming launch is shaping up to be a pivotal moment in Elon Musk’s vision to send humans to Mars and beyond.\nSince its first orbital test flight in April 2023, Starship has made notable progress but has also suffered high-profile setbacks, keeping the project under close scrutiny.\nTo date, Starship has completed nine orbital test flights, following a series of ground-based trials.\nCurrent tests are focused on demonstrating the rocket’s ability to recover its booster, reach target altitudes, deploy payloads and execute controlled landings.\nAll these goals are key to making the vehicle reusable.\n...\n### Every Starship prototype built and tested to date:\n**April 3, 2019:** The Starhopper prototype climbed one foot in a tethered test hop.\n**April 5, 2019:** Starhopper rose three feet in a tethered hop, using the full length of the tether.\n**July 25, 2019:** Starhopper jumped to 65 feet (20 meters) in an untethered test flight.\n**Aug. 27, 2019:** Starhopper flew even higher, reaching 500 feet (150 meters), slewing sideways before descending slowly to a nearby landing pad.\n**Nov. 20, 2019:** A larger prototype, Mk1, was built but blew its top off during a cryogenic proof test (also known as a pressure stress test), rendering it unusable for flight.\n**May 29, 2020:** After earlier prototypes SN1 and SN3 exploded during ground tests, SpaceX found success with SN4, which completed five static fire tests before exploding during the final one.\n**Aug. 5, 2020:** SN5 successfully performed a 500-foot (150-meter) flight and landed on a nearby pad.\n**Sept. 3, 2020:** SN6 completed another 500-foot test flight.\n**Dec. 9, 2020:** SN8, the first prototype with fins and a nose cone, was designed to reach higher altitudes.\nIt ascended to 7.8 miles (12.5 kilometers) but descended too fast and exploded upon landing.\n**Feb. 2, 2021:** SN9 flew to 6 miles (10 kilometers) but crashed on landing after one engine failed to ignite.\n**March 3, 2021:** SN10 nearly completed a 6-mile flight but crushed its landing legs, causing it to tip and explode minutes after touchdown.\n**March 30, 2021:** SN11 successfully reached 6 miles but exploded mid-air during descent.\n(SpaceX skipped SN12, SN13, and SN14.)\n**May 5, 2021:** SN15 successfully completed a high-altitude flight and landed intact.\n**Nov. 18, 2023:** The second orbital test flight reached 93 miles (150 kilometers) and became the first Starship to reach outer space, but it exploded before completing its mission.\n**March 14, 2024:** The third orbital test flight reached approximately 1,515 feet (462 meters) before destructing ahead of a planned splashdown.\n**June 6, 2024:** The fourth orbital flight achieved a full ascent burn and completed a landing burn, concluding with a gentle splashdown in the Gulf of Mexico.\n**Oct. 13, 2024:** The fifth orbital flight marked the first successful booster recovery, with the booster returning to the launch tower.\nThe flight completed its mission with no engine failures and ended in a planned splashdown in the Indian Ocean.\n**Nov. 19, 2024:** During the sixth orbital test, the booster latched onto the catch tower but had to divert for a splashdown in the Gulf of Mexico.\nThe ship ignited one of its six engines in space, successfully reentered the atmosphere, and splashed down in the Indian Ocean.\n**Jan. 16, 2025:** The seventh orbital test launched successfully with all six engines ignited, but a fire eight minutes in caused the rocket to explode.\n**March 6, 2025:** The ship lost several engines during ascent, leading to a loss of altitude control and communication.\nIt diverted into a controlled area to prevent debris from falling into public spaces.\n**May 27, 2025:** The ninth orbital test flight marked the first reuse of a Super Heavy booster.\nHowever, the booster exploded unexpectedly, and the ship lost an engine due to a fuel leak.\nAfter abandoning its payload deployment attempt, Starship exploded over the Indian Ocean when it failed to properly reposition for reentry.",
      "title": "From Hops to Orbit: A Fiery History of SpaceX's Starship Program",
      "url": "https://observer.com/2025/07/spacex-starship-test-timeline/",
      "date": "2025-07-23",
      "last_updated": "2026-05-12"
    },
    {
      "snippet": "",
      "title": "SpaceX Starship design history - Wikipedia",
      "url": "https://en.wikipedia.org/wiki/SpaceX_Starship_design_history",
      "date": "2023-11-14",
      "last_updated": "2026-04-29"
    },
    {
      "snippet": "SpaceX's Starship program, which boasts the world's tallest and most powerful rocket, will eventually put people and cargo on Mars.\nThe latest prototype, SN20, is waiting for the chance to go into orbit.\nSeveral other prototypes have made flights, ground tests and sometimes even testing mistakes in the effort to improve future flights.\nHere's an overview of key milestones on Starship's road to the Red Planet.\n...\nMusk rebranded his Mars-colonizing spaceflight system as Starship in 2018.\n\"Technically, two parts: Starship is the spaceship/upper stage & Super Heavy is the rocket booster needed to escape Earth's deep gravity well (not needed for other planets or moons),\" Musk said in a 2018 tweet.\n...\nAt first, Musk planned to make Starship out of carbon fiber, but in January 2019, he announced that the craft would be built from stainless steel instead, Space.com reported.\n...\nMusk chose to put six Raptor engines on the Starship vehicle instead of seven.\nHe also changed the number of Raptors on the Super Heavy, initially dropping the number from 35 to 31 and then increasing it again to include up to 37 Raptors.\n(Not all engines will be needed on each flight, but at least 24 Raptors are required to carry the huge craft into space, Musk has said.)\n...\nStarhopper was a low-altitude prototype of the Starship system that looked more like a flying tank than an aerodynamic rocket.\nSpaceX did two \"static fire\" tests of the system at its facility in Boca Chica, Texas, to evaluate the performance of the engine in 2019, and then followed that up with four short test flights that same year.\n...\nOn the first free flight, on July 25, 2019, the prototype soared to an expected altitude of 65 feet (20 m).\nIts last flight before retiring on Aug. 27, 2019, was expected to go as high as 500 feet (150 m), in line with a limit imposed by the U.S. Federal Aviation Administration (FAA).\n...\nStarship's program tested several ground prototypes before attempting flight.\nThe list of major prototypes in 2019 to 2020 included MK1 (destroyed during a tank pressure test), MK2 (abandoned for a newer design), MK3/SN1 (destroyed during a pressurization test), SN2 (pressure tested successfully), SN3 (destroyed during a test of its pressure tank) and SN4 (destroyed during a static fire test, following several successful tests).\nStarship's SN5 and SN6 prototypes conducted low-altitude test hops.\nSN5 reached an altitude of about 500 feet on Aug. 4, 2020, and moved sideways in the sky to reach its landing area.\nSN6 also made a 500-foot jaunt on Sept. 3, 2020.\n...\nSpaceX deliberately destroyed SN7 during a ground test to gather data for future flights.\nSN8, which took to the air on Dec. 23, 2020, performed complex aerial maneuvers and flips during the program's first high-altitude launch.\nIt flew to 7.8 miles (12.5 kilometers) but failed to stick the landing, according to a video shot from the landing pad that showed it exploding in a fireball on the ground due to lower-than-expected pressure in the fuel tank header.\n...\nIn a quick sequence in February and March 2021, the Starship program sent aloft three more prototypes on high-altitude flights: SN9, SN10 and SN11.\nThe vehicles flew for about 6 minutes each, but all three experienced technical problems during landing that resulted in fiery crashes or after-touchdown explosions.\n...\nSpaceX's Starship SN15 prototype stuck the landing on the 60th anniversary of the United States' first-ever crewed spaceflight, when astronaut Alan Shepard blasted into space aboard NASA's Mercury capsule.\nOn May 5, 2021, SN15 soared 6.2 miles (10 km) into the sky and made several maneuvers in midair.\nSix minutes after takeoff, the prototype made a safe touchdown on a concrete landing pad at Boca Chica.\nAs of August 2021, this was the latest flight for the Starship program.\n...\n\"SN15 has vehicle improvements across structures, avionics and software, and the engines that will allow more speed and efficiency throughout production and flight: specifically, a new enhanced avionics suite, updated propellant architecture in the aft skirt and a new Raptor engine design and configuration.\"\n...\nSpaceX's newest Starship prototype briefly stood atop a Super Heavy rocket booster for the first time on Aug. 6, 2021, marking the tallest-ever rocket ever built.\n\"Dream come true,\" Musk wrote on Twitter of the stacked Starship.\nThe stacking test at Boca Chica included mating the two vehicles for an hour, with the joined Starship system standing 395 feet (120 m).\nFor comparison, NASA's massive Saturn V moon rocket, used for the Apollo missions, was just 363 feet (110 m) tall.\nIndividually, the Super Heavy stands 230 feet (70 m) tall, and Starship SN20 added another 165 feet (50 m) of height.\nThe two vehicles are expected to undergo numerous technical tests in August to prepare them for an orbital attempt.\n## Orbital flight attempt\nRegulation remains the big uncertainty as Starship awaits its chance to make an orbital flight test.\nIf all goes according to plan, Space.com reported, the spaceship will make a round-the-world trip to splash down off the coast of Hawaii after 90 minutes, while the first stage of the Super Heavy rocket should return to Earth 6 minutes after launch in the Gulf of Mexico.\nHowever, the FAA has undertaken an environmental assessment of the Starship's mission, which delayed SpaceX's plans to attempt the flight in July 2021.\nEven after the assessment is finished, there could be more certifications to consider.\n\"Depending on the outcome of that [environmental] assessment, it [SpaceX] may also be required to go through a more detailed review culminating in an updated environmental impact statement.\nOnly after that process is complete can the Federal Aviation Administration move on to licensing a possible orbital Starship launch,\" CNN Business reported in June 2021.",
      "title": "SpaceX Starship: Key milestones for the world's most powerful rocket",
      "url": "https://www.livescience.com/spacex-starship-key-milestones.html",
      "date": "2021-08-26",
      "last_updated": "2026-05-19"
    },
    {
      "snippet": "",
      "title": "SpaceX - Wikipedia",
      "url": "https://en.wikipedia.org/wiki/SpaceX",
      "date": "2004-07-16",
      "last_updated": "2026-05-21"
    },
    {
      "snippet": "SpaceX launched the third integrated flight test of its Super Heavy booster and Starship upper stage from the company’s Starbase orbital launch pad at 8:25 a.m.\nCT on March 14.\nThis flight test is an important milestone toward providing NASA with a Starship HLS for its Artemis missions.\n...\nOn March 14, SpaceX launched the third integrated flight test of its Super Heavy booster and Starship upper stage, an important milestone toward providing NASA with a Starship HLS for its Artemis missions.\nA complement of 33 Raptor engines, fueled by super-cooled liquid methane and liquid oxygen, powered the Super Heavy booster with Starship stacked on top, from the company’s Starbase orbital launch pad at 8:25 a.m.\nCDT.\nStarship, using six Raptor engines, separated from the Super Heavy booster employing a hot-staging technique to fire the engines before separation at approximately three minutes into the flight, in accordance with the flight plan.\nThis was the third flight test of the integrated Super Heavy-Starship system.\n...\nThis test accomplished several important firsts that will contribute to the development of Starship for Artemis lunar landing missions.\nThe spacecraft reached its expected orbit and Starship completed the full-duration ascent burn.\nOne objective closely tied to future Artemis operations is the transfer of thousands of pounds of cryogenic propellant between internal tanks during the spacecraft’s coast phase as part of NASA’s Space Technology Missions Directorate 2020 Tipping Point awards.\nThe propellant transfer demonstration operations were completed, and the NASA-SpaceX team is currently reviewing the flight data that was received.\nThis Tipping Point technology demonstration is one of more than 20 development activities NASA is undertaking to solve the challenges of using cryogenic fluids during future missions.\nAs a key step toward understanding how super-cooled propellant sloshes within the tanks when the engines shut down, and how that movement affects Starship’s stability while in orbit, engineers will study flight test data to assess the performance of thrusters that control Starship’s orientation in space.",
      "title": "NASA Artemis Mission Progresses with SpaceX Starship Test Flight",
      "url": "https://www.nasa.gov/directorates/esdmd/artemis-campaign-development-division/human-landing-system-program/nasa-artemis-mission-progresses-with-spacex-starship-test-flight/",
      "date": "2024-03-14",
      "last_updated": "2026-04-18"
    },
    {
      "snippet": "SpaceX is continuing to make progress on the development of Starship, the largest rocket ever built, with the third test flight Thursday accomplishing considerably more than the previous two tests.\nThe 400-foot-tall Starship rocket lifted off from SpaceX’s Starbase facility in southeastern Texas at 8:25 a.m. local time.\nAlthough SpaceX has been developing Starship for years, this is only the third time the company has attempted an orbital mission.\nAfter liftoff, Starship proceeded through a nominal — aerospace speak for normal — ascend.\nAll 33 Raptor engines on the Super Heavy booster performed as designed, and the two stages separated around 2 minutes 45 seconds into the mission.\nCritically, the launch vehicle nailed a novel stage separation technique called “hot staging,” where the upper stage (also called Starship) lights its engines to push away the Super Heavy booster.\nThe hot-staging technique was performed for the first time, ever, during the second Starship test flight last November.\nFrom there, the Starship upper stage continued its ascent to orbit.\nSpaceX CEO Elon Musk congratulated the team on X, saying, “Starship reached orbital velocity!”\n> Starship reached orbital velocity!\n> Congratulations @SpaceX team!!\n> — Elon Musk (@elonmusk) March 14, 2024\nThe booster executed what’s called a boostback burn to adjust its trajectory as it aimed to splash down in the Gulf of Mexico — Falcon 9’s booster performs the same maneuver to vertically land back on Earth — but its engines failed to relight for the landing burn phase.\nThe Super Heavy was subsequently lost.\nThe company nailed another new milestone after it opened Starship’s payload door for the first time.\nThis capability is crucial for SpaceX’s plans to rapidly deploy many hundreds of next-generation Starlink satellites.\nAnother demonstration, a propellant transfer demo, was also completed, though the company did not go into the results of this test.\nPropellant transfer is a crucial part of the company’s plans to return humans to the moon for NASA.\nAs part of SpaceX’s plans for that NASA mission, the company has settled on a mission architecture that could include more than a dozen Starship refueling trips.\nBeing able to refuel the vehicle is also necessary for a future Mars mission.\nStarship continued on its coasting phase, but after around a half hour the company said it wouldn’t attempt to relight the engines to proceed with the test.\n...\nInstead, they let gravity do its work, and the Earth’s powerful gravitational forces pulled Starship back through the lower atmosphere.\nUltimately, mission controllers failed to reestablish communications with Starship, leading SpaceX’s Dan Huot to announce that they had lost the ship: “No splashdown today, but again just it’s incredible to see how much further we got this time around,” he said.",
      "title": "SpaceX makes significant progress with third Starship orbital ...",
      "url": "https://techcrunch.com/2024/03/14/spacex-makes-significant-progress-with-third-starship-orbital-test-flight/",
      "date": "2024-03-14",
      "last_updated": "2026-05-20"
    },
    {
      "snippet": "**genesis of Starship** can be traced back to the early 2010s when SpaceX was actively exploring concepts for a fully reusable launch system.\n...\nDuring this phase, SpaceX experimented with different materials and manufacturing techniques, ultimately settling on stainless steel for the Starship's construction.\n...\n**Starhopper**, a scaled-down prototype, marked a pivotal moment in Starship's development.\n...\nIn 2019, Starhopper conducted several successful tethered and untethered hops, reaching altitudes of up to 150 meters.\nThese tests validated the Raptor engine's performance and demonstrated the feasibility of vertical takeoff and landing (VTOL), a critical capability for full reusability.\n...\n**SN15** represented a significant turning point in the Starship program.\n...\nIn May 2021, SN15 successfully completed a high-altitude flight test, reaching an altitude of 10 kilometers and performing a controlled landing.\nThis marked the first time a Starship prototype had successfully completed a full flight profile, including ascent, descent, and landing, without any major issues.\n...\nFollowing SN15, SpaceX shifted its focus to orbital flight tests.\nThe company began constructing Starship prototypes designed for orbital missions, along with the Super Heavy booster, the massive first stage that will propel Starship into orbit.\nThese prototypes, such as\n*Ship 20 and Booster 4*, underwent extensive testing at SpaceX's Starbase facility in Boca Chica, Texas.\nTesting included static fires of the Super Heavy's numerous Raptor engines, as well as cryogenic proof tests to ensure the structural integrity of both Starship and Super Heavy.\nThe development and testing of orbital-class Starship prototypes represent a major step towards realizing the ultimate goal of a fully reusable space transportation system.\nThese efforts pave the way for future orbital flight tests, which will provide critical data on the performance of Starship and Super Heavy in the harsh environment of space.\n...\nThe\n**first orbital flight test** of Starship is a highly anticipated event that will mark a major milestone in the program's development.\nThis test involves launching a Starship prototype atop a Super Heavy booster, sending it into orbit, and then attempting a controlled reentry and splashdown in the Pacific Ocean.\nThe data gathered from this test will be invaluable for understanding the performance of Starship in a real-world orbital environment and for identifying any areas that require further improvement.\nDespite several delays, SpaceX is working closely with regulatory authorities to obtain the necessary approvals for the orbital flight test.\nThe company has made significant progress in addressing environmental concerns and implementing safety measures to minimize risks.\nOnce the necessary approvals are in place, SpaceX plans to conduct the orbital flight test as soon as possible.\nThis test will be a crucial step towards validating the Starship design and demonstrating its capabilities for future missions.\n...\nFrom early concepts and prototypes to successful high-altitude flights and upcoming orbital tests, the Starship program has made remarkable progress in a relatively short period.",
      "title": "SpaceX Starship Timeline: Key Milestones & Future",
      "url": "https://marcoauggiero.com/blog/spacex-starship-timeline-key-milestones-1761214439931",
      "date": "2025-10-23",
      "last_updated": "2025-10-30"
    }
  ],
  "server_time": null
}