---
source_url: "https://docs.perplexity.ai/docs/getting-started/quickstart"
title: Quickstart - Perplexity
mirrored_at: 2026-08-25T01:01:01.473Z
host: docs.perplexity.ai
cited_in_42a: true
mirror_canonical: "https://index.42a.ai/docs.perplexity.ai/docs/getting-started/quickstart"
---
> **Original source:** https://docs.perplexity.ai/docs/getting-started/quickstart
```
{
"id": "resp_a8dc1444-8a50-40c1-a918-f3d8de35c2f7",
"created_at": 1779391840,
"model": "openai/gpt-5.1",
"object": "response",
"output": [
{
"results": [
{
"id": 1,
"snippet": "Superconducting qubits are one of the most widely used\nphysical realizations of quantum computing due to their scalability [6] and the\nsuccess researchers have had in creating a universal set of quantum logic gates\nfor superconducting qubits [1].\nBoth Google and IBM have built functioning su-\nperconducting quantum computers with 72 and 53 qubits respectively, demon-\nstrating the feasibility of constructing a superconducting quantum computer.\nFinally, superconducting qubits are based on circuit systems that can be reli-\nably constructed in a modular fashion [2] making them an excellent foundation\non which to build quantum computers.\n...\nSuperconducting qubits are constructed out of what amount to classical\ncircuit elements that are supercooled and made small enough that the law of\nQuantum Mechanics apply.\nThis means that we will have to develop a means\nof constructing quantum Hamiltonians for systems which are usually treated\nand understood classically.\n...\nThis is incredibly\n...\nA Cooper pair is a system constructed out of a metallic superconducting is-\nland connected by a thin insulating barrier, called a Josephson Junction, to a\nsuperconducting electron reservoir (or in some cases a second superconducting\nisland).\nA Cooper pair box can be used to build a type of superconducting\nqubit known as a charge qubit where the state of the qubit is determined by\nthe number of Cooper pairs that have tunneled across the Josephson Junction\nto the superconducting island.\n...\nDespite the fact that tremendous advances have been made in the construction\nand manipulation of superconducting qubits, there is still great potential for\nimprovement.\nFor example, superconducting qubits, have fairly low coherence\n...\nThis is\ncan be remedied by using fluxonium qubits which couple the superconducting\nisland to the reservoir through an inductor rather than a capacitor and can\ncombine the benefits of the traditional Cooper-pair box and Transmon qubits\nwhile avoiding their drawbacks [3].\nHowever, fluxonium qubits have not been\nsuccessfully incorporated into large-scale circuits and their operation is far more\ndifficult, requiring further research [3].",
"title": "[PDF] A Brief Introduction to Superconducting Charge Qubits - Chicago U",
"url": "https://homes.psd.uchicago.edu/~sethi/Teaching/P243-W2021/Final%20Papers/MFarrington_Advanced_Quantum_Mechanics_Final_Project%20(1).pdf",
"date": null,
"last_updated": "2026-03-29",
"source": "web"
},
{
"id": 2,
"snippet": "These atoms are the heart of our quantum processing units.\nWe trap them in 3D space, and then use lasers to do everything from initial preparation to final readout.\n...\nMost quantum computers rely on superconducting circuits or exotic materials.\nIonQ takes a simpler, more powerful approach: we use single atoms—identical, stable, and natural—as the building blocks of computation.\n...\nOnce we've turned our atom into an ion, we use a specialized chip called a *linear ion trap* to hold it precisely in 3D space.\n...\nWe can (and do!) load any number of ions into a *linear chain*.\nThis on-demand reconfigurability allows us to theoretically create anything from a one-qubit system to a 100+ qubit system without having to fabricate a new chip or change the underlying hardware.\n...\nBefore we can use our ions to perform quantum computations, we have to prepare them for the task.\nThis has two major steps: *cooling*, which reduces computational noise and makes our ions better qubits, followed by *state preparation*, which initializes each ion into a well-defined “zero” state, ready to perform algorithms.\n...\nWe compute using a series of operations called *gates* to manipulate the qubits’ state, first encoding and then operating on the information we want to calculate.\n...\nUsing Doppler Cooling, we can create qubits that are half of one one-thousandth of a degree above absolute zero, without needing to refrigerate any of the supporting hardware.\nThis is extremely cold, but for optimal performance, we need to go colder, as close to absolute zero as we can.\nTo accomplish this, we use a collection of laser-based techniques called *resolved-sideband cooling* to produce qubits so cold that they are almost perfectly still at an atomic level.",
"title": "Our Trapped Ion Technology - IonQ",
"url": "https://www.ionq.com/technology",
"date": null,
"last_updated": "2026-05-20",
"source": "web"
},
{
"id": 3,
"snippet": "The theory of quantum computations is agnostic to the physical system—a quantum bit (qubit) is represented by the same vector regardless of the physical system that implements the quantum computation.\nThe physical system can be based on matter, e.g. trapped ions and superconducting qubits, or based on photons, referred to as photonic quantum computation.",
"title": "Photonic Quantum Computing - arXiv",
"url": "https://arxiv.org/html/2404.03367v1",
"date": "2024-04-04",
"last_updated": "2026-05-17",
"source": "web"
},
{
"id": 4,
"snippet": "**Superconducting qubits** are among the most promising approaches to building quantum computers.\nIt is no surprise that this technology is being used by well-known tech companies in their quest to pioneer the quantum era.\nGoogle’s Sycamore claimed quantum advantage back in 2019 and, in 2021, IBM built its Eagle quantum computer with 127 qubits ! The central insight that allows for these quantum computers is that superconductivity is a quantum phenomenon, so we can use superconducting circuits as quantum systems that we can control at will.\nWe can actually bring the quantum world to a larger scale and manipulate it more freely!\n...\n1. **Well-characterized and scalable qubits**.\nMany of the quantum systems that we find in nature are not qubits, so we must find a way to make them behave as such.\nMoreover, we need to put many of these systems together.\n2. **Qubit initialization**.\nWe must be able to prepare the same state repeatedly within an acceptable margin of error.\n3. **Long coherence times**.\nQubits will lose their quantum properties after interacting with their environment for a while.\nWe would like them to last long enough so that we can perform quantum operations.\n4. **Universal set of gates**.\nWe need to perform arbitrary operations on the qubits.\nTo do this, we require both single-qubit gates and two-qubit gates.\n...\nIf we build a somewhat **small electric circuit using superconducting wires** and bring it to temperatures of about 10 mK, it becomes a quantum system with discrete energy levels.\n...\nThe regime that has been proven ideal is known as the **transmon regime**, and artificial atoms in this regime are called **transmons**.\nThey have proven to be highly effective as qubits, and they are used in many applications nowadays.\nWe can thus work with the first two energy levels of the transmon, which we will also denote \\(\\left\\lvert g \\right\\rangle\\) and \\(\\left\\lvert e \\right\\rangle,\\) the ground and excited states respectively.\n...\nthe second criterion is satisfied effortlessly.\n...\nThe typical times in which a single-qubit gate is executed are in the order of the nanoseconds, making superconducting\nquantum computers the fastest ones out there.\n...\nSuperconducting quantum computing has gained momentum in the last decade as a leading competitor\nin the race for building a functional quantum computer.\nIt is based on artificial versions of atomic systems\ndone using superconducting circuits, which allows for versatility and control.\nThey have been easy to scale so far, but increasing the qubit coherence time and the speed of quantum\noperations and measurements is essential to scaling this technology further.",
"title": "Quantum computing with superconducting qubits | PennyLane Demos",
"url": "https://www.pennylane.ai/qml/demos/tutorial_sc_qubits",
"date": "2022-03-21",
"last_updated": "2026-05-17",
"source": "web"
},
{
"id": 5,
"snippet": "To create a functional quantum computer, we need to produce and control a\nlarge number of qubits.\nThis feat has proven difficult, although significant\nprogress has been made using trapped ions, superconducting circuits,\nand many other technologies.",
"title": "Photonic quantum computers | PennyLane Demos",
"url": "https://pennylane.ai/qml/demos/tutorial_photonics",
"date": "2022-05-30",
"last_updated": "2026-05-05",
"source": "web"
},
{
"id": 6,
"snippet": "The aim of this review is to provide quantum engineers with an introductory guide to the central concepts and challenges in the rapidly accelerating field of superconducting quantum circuits.\nOver the past twenty years, the field has matured from a predominantly basic research endeavor to a one that increasingly explores the engineering of larger-scale superconducting quantum systems.\nHere, we review several foundational elements—qubit design, noise properties, qubit control, and readout techniques—developed during this period, bridging fundamental concepts in circuit quantum electrodynamics and contemporary, state-of-the-art applications in gate-model quantum computation.\n...\nOne prominent platform for constructing a multiqubit quantum processor involves superconducting qubits, in which information is stored in quantum degrees of freedom (DOFs) of nanofabricated, anharmonic oscillators (AHOs) constructed from superconducting circuit elements.\nIn contrast to other platforms, e.g., electron spins in silicon\n9–14 and quantum dots, 15–18 trapped ions, 19–23 ultracold atoms, 24–27 nitrogen-vacancies in diamonds, 28,29 and polarized photons, 30–33 where the quantum information is encoded in natural microscopic quantum systems, superconducting qubits are macroscopic in size and lithographically defined.\nOne remarkable feature of superconducting qubits is that their energy-level spectra are governed by circuit element parameters and thus are configurable; they can be designed to exhibit “atomlike” energy spectra with the desired properties.\nTherefore, superconducting qubits are also often referred to as “artificial atoms,” offering a rich parameter space of possible qubit properties and operation regimes, with predictable performance in terms of transition frequencies, anharmonicity, and complexity.",
"title": "A quantum engineer's guide to superconducting qubits",
"url": "https://pubs.aip.org/aip/apr/article/6/2/021318/570326/A-quantum-engineer-s-guide-to-superconducting",
"date": "2019-06-17",
"last_updated": "2025-06-08",
"source": "web"
},
{
"id": 7,
"snippet": "Photonic offers a unique quantum modality (spin-photon qubits) as the foundation for scalable, distributed, fault tolerant QC systems.\nPhotonic’s core technology offers a plausible shortcut to large-scale fault-tolerant quantum computing.",
"title": "Photonic Inc.: Distributed Quantum Computing at Scale",
"url": "https://photonic.com",
"date": "2025-11-04",
"last_updated": "2026-05-20",
"source": "web"
},
{
"id": 8,
"snippet": "Superconducting qubits are solid state electrical circuits fabricated using techniques adapted from those of conventional integrated microprocessors.\nThey are based on the Josephson tunnel junction, which is so far the only non-dissipative, strongly nonlinear circuit element compatible with low temperature operation.\nIn contrast to microscopic entities such as spins, atoms, or ions, superconducting qubits can be held firmly in one location in space and coupled strongly to their neighbors, an appealing feature for 2-qubit gate array implementation.\nRecently, the coherence factor of bare superconducting artificial atoms has reached that of the hydrogen atom for its 1S-2P transition (~ 20 million).\nThis opinionated review will compare the prospects of the transmon and fluxonium artificial atoms for large scale quantum information processing.",
"title": "Keynote: Superconducting qubits for quantum computation - YouTube",
"url": "https://www.youtube.com/watch?v=qsizrKrUZDg",
"date": "2022-09-07",
"last_updated": "2026-03-31",
"source": "web"
},
{
"id": 9,
"snippet": "In optical systems for quantum information processing, the unit of light in a given mode—or photon—is used to represent a qubit.",
"title": "Linear optical quantum computing - Wikipedia",
"url": "https://en.wikipedia.org/wiki/Linear_optical_quantum_computing",
"date": "2013-12-09",
"last_updated": "2026-04-17",
"source": "web"
},
{
"id": 10,
"snippet": "Superconducting circuits are one of the most promising platforms for scalable quantum technology.\nIn the last couple of decades, it has undergone significant development and is currently being explored by several large tech companies as the future of quantum computing.\nThe analysis of superconducting circuits usually revolves around making efficient two-level quantum systems, also known as qubits, from circuits consisting of capacitors, linear inductors, and a nonlinear inductor also known as a Josephson junction.\nSuperconducting qubits were sparked by the invention of the Josephson junction in the sixties, but a breakthrough came with the transmon qubit in 2007, which increased the lifetime of the qubits.\nDespite all this, no introductory text on the subject exists.",
"title": "Superconducting Circuit Companion---an Introduction with Worked ...",
"url": "https://link.aps.org/doi/10.1103/PRXQuantum.2.040204",
"date": "2021-12-14",
"last_updated": "2025-11-11",
"source": "web"
}
],
"type": "search_results",
"queries": [
"superconducting qubits overview",
"trapped ion quantum computing overview",
"photonic qubits quantum computing overview"
]
},
{
"id": "msg_78f55417-7dad-435b-a49b-98933d85c9ee",
"content": [
{
"text": "Superconducting qubits, trapped ions, and photonic qubits all implement the same abstract idea of a qubit but use very different physical systems, which leads to distinct strengths and weaknesses in speed, coherence, scalability, and engineering complexity.[web:3][web:4][web:5] Together they define the three main hardware “families” that leading labs and companies are pursuing for large‑scale quantum computers.[web:4][web:6] \n\n## Superconducting qubits \n\nSuperconducting qubits are tiny electrical circuits made from superconducting materials, typically incorporating Josephson junctions to create a nonlinear “artificial atom” whose lowest two energy levels serve as the qubit states |0⟩ and |1⟩.[web:4][web:6] These circuits are cooled to millikelvin temperatures (∼10 mK) so that quantum effects dominate, enabling fast microwave control of the qubits.[web:4] \n\nKey features: \n- **Speed and gate operations**: Single- and two-qubit gates are driven by microwave pulses and can operate in a few to tens of nanoseconds, making superconducting platforms among the fastest gate-based architectures.[web:4][web:6] \n- Scalability and fabrication: Qubits and couplers are patterned lithographically on chips, similar to classical integrated circuits, which supports dense 2D arrays and has enabled devices in the 50–100+ qubit range from companies like Google and IBM.[web:1][web:4][web:10] \n- Coherence and noise: Coherence times have improved dramatically (through designs like the transmon and fluxonium), but they remain limited by materials defects, electromagnetic noise, and crosstalk; engineering larger, error-corrected systems requires substantial advances in coherence and packaging.[web:1][web:4][web:6] \n\nSuperconducting circuits are attractive because they are highly **configurable**: their energy spectra and coupling strengths can be engineered by design, but this flexibility comes at the cost of complex cryogenics and sensitive microwave control infrastructure.[web:6][web:8] \n\n## Trapped‑ion qubits \n\nTrapped‑ion quantum computers encode qubits in internal electronic or hyperfine states of individual atomic ions (such as ytterbium or calcium) held in electromagnetic traps in ultra‑high vacuum.[web:2] The ions are arranged in linear chains or small 2D configurations, and lasers are used for cooling, state preparation, gate operations, and readout.[web:2] \n\nKey features: \n- **Identical, high‑fidelity qubits**: Because they use natural atoms, each qubit is effectively identical and extremely stable, with very long coherence times compared to most other platforms.[web:2][web:5] \n- Gate mechanisms: Multi-qubit gates exploit shared motional modes of the ions; tailored laser pulses entangle qubits by coupling internal states to collective motion.[web:2] \n- Coherence and error rates: Coherence times can be seconds to minutes, and gate and readout fidelities are among the highest in any architecture, but gate speeds (typically microseconds or longer) are slower than in superconducting systems.[web:2][web:5] \n\nScaling trapped‑ion systems involves engineering larger traps, complex laser delivery, and strategies like modular architectures where chains of ions are interconnected optically or through shuttling, which is technically demanding but conceptually compatible with fault‑tolerant schemes.[web:2][web:5] \n\n## Photonic qubits \n\nPhotonic quantum computing uses single photons as the carriers of quantum information, typically encoding qubits in degrees of freedom such as polarization, spatial modes, or time bins.[web:3][web:9] Computation is implemented using optical elements like beam splitters, phase shifters, nonlinear devices, and photon detectors, often in integrated photonic circuits.[web:3][web:5] \n\nKey features: \n- **Room‑temperature operation and low decoherence**: Photons interact weakly with the environment, so they can maintain quantum coherence over long distances, and many photonic platforms operate at or near room temperature (apart from some sources and detectors that may need cooling).[web:3][web:5] \n- Linear optical approaches: In linear optical quantum computing, single photons and linear optics plus measurements and feed‑forward can in principle realize universal quantum computation, though it requires complex resource states and high‑performance single‑photon sources and detectors.[web:3][web:9] \n- Integration and networking: Photonic qubits are naturally suited for quantum communication and for **distributed** architectures, and integrated photonic chips aim to combine sources, interferometers, and detectors for scalable, manufacturable systems.[web:3][web:5][web:7] \n\nMajor challenges for photonic platforms include generating indistinguishable single photons on demand, achieving high-efficiency, low-noise detection, and scaling up error-corrected architectures given the probabilistic nature of many photonic operations.[web:3][web:5] \n\n## Side‑by‑side comparison \n\n| Aspect | Superconducting qubits | Trapped‑ion qubits | Photonic qubits |\n|-----------------------|---------------------------------------------------|-------------------------------------------------------|--------------------------------------------------------|\n| Physical system | Superconducting circuits with Josephson junctions.[web:4][web:6] | Atomic ions in EM traps in vacuum.[web:2] | Single photons in optical modes.[web:3][web:9] |\n| Operating conditions | Millikelvin cryogenic temperatures.[web:4] | Ultra‑high vacuum; laser cooling near motional ground state.[web:2] | Often room temperature optics; some cryogenic detectors.[web:3][web:5] |\n| Gate speed | Nanoseconds (very fast).[web:4][web:6] | Microseconds or slower.[web:2] | Varies; many operations effectively instantaneous but often probabilistic.[web:3][web:5] |\n| Coherence | Microseconds–milliseconds; improving but limited by materials and noise.[web:4][web:6] | Very long (up to seconds or more).[web:2] | Very long in principle; limited by loss rather than dephasing.[web:3][web:5] |\n| Scalability outlook | Good near‑term chip‑scale scaling; packaging and error correction are main hurdles.[web:4][web:6][web:10] | Excellent qubit quality; scaling control and optics is challenging.[web:2][web:5] | Natural fit for large‑scale networking and integration; resource overhead still large.[web:3][web:5][web:7] |\n\nEach of these three approaches offers a different balance between speed, coherence, control complexity, and manufacturability, which is why all continue to be actively pursued as contenders for practical, fault‑tolerant quantum computers.[web:3][web:4][web:5]",
"type": "output_text",
"annotations": [],
"logprobs": []
}
],
"role": "assistant",
"status": "completed",
"type": "message"
}
],
"status": "completed",
"error": null,
"usage": {
"input_tokens": 6872,
"output_tokens": 1528,
"total_tokens": 8400,
"cost": {
"currency": "USD",
"input_cost": 0.00411,
"output_cost": 0.01528,
"total_cost": 0.02234,
"cache_creation_cost": null,
"cache_read_cost": 0.00045,
"tool_calls_cost": 0.0025
},
"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": 1779391840,
"frequency_penalty": 0,
"incomplete_details": null,
"instructions": "## Abstract\n\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\n\n## Instructions\n\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 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 Make at most three tool calls before concluding.\n\n\n## Citation Instructions\n\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 are included below.\n\n\n- `web`: Internet sources\n- `page`: Full web page content\n- `conversation_history`: past queries and answers from your interaction with the user\n\n\n\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\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\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\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\n\n### Lists and Paragraphs\n\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\n\n### Summaries and Conclusions\n\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\n\n## Prohibited Meta-Commentary\n\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\n\n\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\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
}
```