A high-performance reasoning model leveraging advanced multi-step CoT reasoning and enhanced information retrieval.

  • Model Type: Reasoning
  • Use Case: Best suited for dealing with complex topics that require advanced multi-step reasoning.
  • Context Length: 128k

Key Features:

  • Enhanced Chain-of-thought (CoT) reasoning
  • 2x more citations on average than Sonar Reasoning
  • Uses advanced information retrieval architecture

Real-World Examples:

  • Performing competitive analyses for new products
  • Understanding and exploring complex scientific topics
  • Making detailed travel plans

Pricing

MetricHigh  Medium  Low  
Input Tokens (Per Million)$2$2$2
Output Tokens (Per Million)$8$8$8
Price per 1,000 Requests$14$10$6

Test the Model

curl --request POST \
  --url https://api.perplexity.ai/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "sonar-reasoning-pro",
  "messages": [
    {"role": "user", "content": "Analyze the feasibility of fusion energy becoming a mainstream power source by 2040."}
  ],
  "max_tokens": 300
}'
  • The sonar-reasoning-pro model is designed to output a <think> section containing reasoning tokens, immediately followed by a valid JSON object. As a result, the response_format parameter does not remove these reasoning tokens from the output. We recommend using a custom parser to extract the valid JSON portion, and an example implementation can be found here.

Sample Response Metadata

{
  'id': '061418a3-25ce-4e75-a8e6-da7fa63f0b4a', 
  'model': 'sonar-reasoning-pro', 
  'created': 1743529577, 
  'usage': {'prompt_tokens': 17, 'completion_tokens': 1412, 'total_tokens': 1429, 'citation_tokens': 9525, 'num_search_queries': 1}, 'citations': ['https://www.euronews.com/green/2022/10/04/world-first-nuclear-fusion-plant-could-generate-carbon-free-energy-by-2040-uk-government-c', 'https://www.weforum.org/stories/2020/12/fusion-experiments/', 'https://www.world-nuclear-news.org/Articles/US-could-operate-a-fusion-plant-by-2040-Academy-sa', 'https://greenly.earth/en-us/blog/industries/will-nuclear-fusion-help-solve-our-future-energy-needs', 'https://www.csis.org/analysis/united-states-looks-fusion-re-inject-energy-global-climate-efforts', 'https://en.wikipedia.org/wiki/Fusion_power', 'https://www.energy.gov/sites/default/files/2024-06/fusion-energy-strategy-2024.pdf', 'https://www.nextbigfuture.com/2024/08/what-can-solve-the-energy-hungry-future-needs-of-an-ai-world.html', 'https://ccfe.ukaea.uk/fusion-energy/fusion-in-brief/', 'https://www.thedailystar.net/opinion/views/news/fusion-energy-the-holy-grail-clean-power-3844036', 'https://world-nuclear.org/information-library/current-and-future-generation/nuclear-fusion-power'], 
  'object': 'chat.completion', 
  'choices': [{'index': 0, 'finish_reason': 'stop', 'message': {'role': 'assistant', 
  'content': "<think>\nOkay, let's start by understanding the query: analyzing whether fusion energy can become a mainstream power source by 2040. \n\nFirst, I need to check the current progress. The UK's STEP program aims for a commercial plant by 2040 [1]. The US also has plans through the NASEM report suggesting a pilot plant by 2035-2040 [3]. However, ITER, a major international project, isn't expected to produce electricity until 2050 [1], which is after 2040. That's a problem because ITER is crucial for proving feasibility. Also, JET's record is 59 megajoules over five seconds [9], which is progress but far from continuous energy production.\n\nNext, technical challenges. Fusion requires sustaining plasma at over 100 million degrees Celsius [2][6]. Materials that can withstand this don't exist yet. Even if they solve that, scaling up to a power grid is another hurdle. The US DOE mentions net energy gain as a key milestone, but achieving this consistently is tough [5][7]. There's also the issue of tritium supply [6], which needs breeding blankets not yet perfected.\n\nEconomic and investment factors. The Fusion Industry Association notes over $6 billion in private investment, mainly in the US [5][7]. Public-private partnerships are driving R&D, like the UK's STEP and US initiatives [7]. However, costs are high. ITER is over budget and delayed [1][4], which could signal similar challenges for other projects.\n\nRegulatory and infrastructure readiness. No commercial fusion plants exist, so regulations are untested. Building the supply chains and workforce will take time. The UK's STEP aims to replace a coal plant by 2040 [1], but that's a single project. Mainstream adoption requires many such plants, which seems unlikely by 2040 given current timelines.\n\nGlobal collaboration vs. competition. ITER involves 35 countries, which is good for shared knowledge but can lead to delays [1][4]. Meanwhile, countries like China and South Korea have their own timelines, potentially leading to fragmented progress [5]. The US strategy focuses on public-private partnerships to accelerate development [7], but it's unclear if this can bridge the gap by 2040.\n\nAlternative approaches. Companies like General Fusion and HB11 Energy are exploring different methods, such as spherical tokamaks and laser-driven fusion [6][8]. HB11's laser approach claims potential for rapid scaling, but it's still experimental [8]. These alternatives might bypass some tokamak issues but are unproven at scale.\n\nEnvironmental and safety aspects. Fusion produces minimal waste compared to fission, which is a plus [9]. Public acceptance might be easier, but without a working plant, this remains theoretical. \n\nConsidering all factors, while there's significant progress and investment, technical and logistical hurdles remain. Pilot plants might come online by 2040, but mainstream adoption would require rapid scaling and solving unresolved issues. Historical delays in projects like ITER suggest caution. Likely, fusion will start contributing post-2040 but not be mainstream by then.\n</think>\n\nFusion energy has made significant strides, but its feasibility as a mainstream power source by 2040 hinges on overcoming technical, economic, and logistical challenges. Here's an analysis based on current progress and projections:\n\n### Key Developments and Timelines\n- **UK’s STEP Program** aims to build the world’s first commercial fusion plant in Nottinghamshire by 2040, with £220 million (€252 million) committed to develop a spherical tokamak design[1]. \n- **ITER**, the multinational tokamak project in France, will begin plasma experiments in 2025 but won’t produce electricity until 2050[1][9]. \n- The **U.S.** targets a pilot fusion plant by 2035–2040 through public-private partnerships, as outlined in the NASEM report[3][7]. \n- **China** and **South Korea** aim for prototype reactors by 2035 and commercialization by 2050[5][10].\n\n### Technical Challenges\n1. **Plasma Confinement and Energy Gain**:  \n   - Current reactors, like JET, have achieved 59 megajoules of energy over 5 seconds—enough to boil 60 kettles but insufficient for grid-scale power[1][11].  \n   - Sustaining plasma at over 100 million°C requires advanced materials and magnet systems that don’t yet exist[2][6].  \n   - The U.S. National Ignition Facility achieved a net energy gain (5.2 MJ output vs. 2.2 MJ input), but scaling this to continuous operation remains unproven[8].\n\n2. **Fuel Supply**:  \n   - Tritium, a key fusion fuel, is rare and must be bred within reactors using lithium. No reactor has demonstrated a self-sustaining fuel cycle[6][9].\n\n3. **Economic Viability**:  \n   - Fusion R&D is expensive: ITER’s budget exceeds $22 billion, and delays are common[1][4].  \n   - Private investment ($6.2 billion globally) is growing, but commercialization requires reactors to produce >50 MW of net electricity at competitive costs[5][7].\n\n### Prospects for 2040\n- **Pilot Plants**: The UK’s STEP and U.S. public-private ventures could demonstrate net electricity production by 2040, but these will likely be experimental, not commercial[1][7].  \n- **Infrastructure Gaps**: No regulatory frameworks or supply chains exist for fusion reactors. Materials resistant to neutron damage (e.g., tungsten alloys) are still in development[6][9].  \n- **Global Competition**: While international projects like ITER collaborate, nations like China and the U.K. are racing to deploy proprietary designs, potentially fragmenting progress[5][11].\n\n### Environmental and Safety Advantages\n- **Zero Carbon Emissions**: Fusion produces no greenhouse gases, with helium as the only byproduct[9].  \n- **Minimal Waste**: Unlike fission, fusion generates short-lived radioactive waste (decaying within 50–100 years)[9][11].  \n- **Inherent Safety**: Reactions stop instantly if containment fails, eliminating meltdown risks[1][5].\n\n### Conclusion\nWhile fusion energy could see **limited demonstration projects by 2040**, mainstream adoption faces steep hurdles:  \n- **Technical**: Solving plasma stability, materials science, and fuel cycling.  \n- **Economic**: Reducing costs to compete with renewables and fission.  \n- **Logistical**: Developing regulations and global supply chains.  \n\nOptimistic scenarios suggest fusion may contribute to grid power by the **2050s**, but 2040 appears too early for widespread deployment. The next decade will focus on proving scientific viability, with commercialization likely requiring sustained investment and international coordination[3][5][7]."}, 
  'delta': {'role': 'assistant', 'content': ''}}]
}