[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"user-page:swift-ai":3},{"code":4,"user":5,"seo":331},"success",{"id":6,"username":7,"name":8,"created_at":9,"photo_url":10,"links":11,"apis":12,"joined_on":330},"tcmi","swift-ai","Dev AI","2025-03-07 02:04:46",null,{},[13,21,29,37,45,53,61,69,77,85,93,101,109,116,124,132,140,148,156,164,172,180,187,194,201,208,215,223,231,238,245,252,259,266,274,282,290,298,306,314,322],{"name":14,"slug":15,"created_at":16,"description":17,"logo":18,"seo":19},"Claude 3.7-Sonnet","claude-3-7-sonnet","2025-03-08 11:53:48","Claude 3.7 Sonnet is designed to deliver exceptional AI performance. With supporting stream, Claude 3.7 Sonnet features advanced \"hybrid reasoning\" capabilities that allow users to switch between fast responses and in-depth, step-by-step thinking. It introduces an \"extended thinking\" mode, where users can control how long the AI processes information before responding, balancing speed and depth. Additionally, the new \"scratchpad\" feature transparently displays its reasoning, improving collaboration and prompt refinement.","https://cdn.jojapi.com/api/93dbb50d-de65-40c2-8764-77ef1616632b",{"name":20},"Claude 3.7-Sonnet API",{"name":22,"slug":23,"created_at":24,"description":25,"logo":26,"seo":27},"Claude 3.5-Haiku","claude-3-5-haiku","2025-03-08 12:57:52","Claude 3.5 Haiku is designed for optimal data management. With supporting stream, it efficiently processes and categorizes information, making it effective for rapid data extraction and automated labeling tasks","https://cdn.jojapi.com/api/1c4046fd-4a05-432f-9937-c3af36de3208",{"name":28},"Claude 3.5-Haiku API",{"name":30,"slug":31,"created_at":32,"description":33,"logo":34,"seo":35},"Claude 3.5-Sonnet","claude-3-5-sonnet","2025-03-08 13:05:26","Claude 3.5 Sonnet is designed for enhanced efficiency. With supporting stream and a 200K context window, Claude 3.5 Sonnet operates at twice the speed of Claude 3 Opus. This performance boost, combined with cost-effective pricing, makes Claude 3.5 Sonnet ideal for complex tasks such as context-sensitive customer support and orchestrating multi-step workflows.","https://cdn.jojapi.com/api/22c882ab-d23f-4473-b5f9-93ae0b71a831",{"name":36},"Claude 3.5-Sonnet API",{"name":38,"slug":39,"created_at":40,"description":41,"logo":42,"seo":43},"Gemini Pro","gemini-pro","2025-03-08 13:18:00","The Gemini 2 Pro is designed for exceptional AI performance. With supporting stream, the Gemini 2 Pro is an advanced AI model that seamlessly integrates text, image, and speech capabilities with robust tool support for coding and real-time information retrieval.","https://cdn.jojapi.com/api/75f7e884-faa4-4b98-9b83-e4d7f2282910",{"name":44},"Gemini Pro API",{"name":46,"slug":47,"created_at":48,"description":49,"logo":50,"seo":51},"Gemini Flash","gemini-flash","2025-03-08 14:21:07","The Gemini 2.0 Flash is designed for cutting-edge performance. With supporting stream, the Gemini 2.0 Flash is an advanced AI model developed by Google DeepMind. Key features include native tool use, image creation and editing, speech generation, and real-time streaming.","https://cdn.jojapi.com/api/d3ba7f94-d386-4a52-934a-e38e609f79cb",{"name":52},"Gemini Flash API",{"name":54,"slug":55,"created_at":56,"description":57,"logo":58,"seo":59},"xAI","xai","2025-03-13 02:27:25","Direct Official Grok AI API supports stream,developed by Elon Musk's xAI, is an advanced language model designed to enhance business operations through automation and integration","https://cdn.jojapi.com/api/a3a1a8e1-6c31-4486-9cd0-5674e48feb92",{"name":60},"xAI API",{"name":62,"slug":63,"created_at":64,"description":65,"logo":66,"seo":67},"DeepSeek-V3","deepseek-v3","2025-03-15 09:45:18","DeepSeek Chat V3 is a powerful AI model with 671 billion parameters, designed for advanced conversational capabilities and integration via OpenAI-compatible APIs. It excels in tasks like problem-solving, programming, and reasoning, making it ideal for developers to enhance their applications.","https://cdn.jojapi.com/api/d32c2fbd-df64-4e3b-aa2c-3db316f01e38",{"name":68},"DeepSeek-V3 API",{"name":70,"slug":71,"created_at":72,"description":73,"logo":74,"seo":75},"DeepSeek-R1","deepseek-r1","2025-03-15 10:44:38","With supporting stream, DeepSeek-R1 is an open-source large language model (LLM) from the AI startup DeepSeek, designed for advanced reasoning tasks like mathematics, coding, and general knowledge. Trained using reinforcement learning (RL) followed by supervised fine-tuning, it self-evolves and refines its outputs for clarity and accuracy. The model achieves 79.8% on AIME 2024 math tests, a 2,029 Codeforces rating (outperforming 96.3% of programmers), and 90.8% accuracy on MMLU benchmarks, rivaling OpenAI's o1 model. Fully open-source under the MIT license, it is accessible via Hugging Face, encouraging collaboration. Its API service, DeepSeek Reasoner, offers competitive pricing, making it a cost-effective and high-performing solution for developers and researchers alike.","https://cdn.jojapi.com/api/3c678bfb-0a78-4dad-b85c-32db88c2279d",{"name":76},"DeepSeek-R1 API",{"name":78,"slug":79,"created_at":80,"description":81,"logo":82,"seo":83},"Google Gemma 3","google-gemma-3","2025-03-21 12:11:40","With 128K context, image input, and multilingual support. The Gemma family of open models is foundational to our commitment to making useful AI technology accessible","https://cdn.jojapi.com/api/b27c6fce-a3f2-4f13-8e56-a611f62b0144",{"name":84},"Google Gemma 3 API",{"name":86,"slug":87,"created_at":88,"description":89,"logo":90,"seo":91},"Open AI Text to Speech","open-ai-text-to-speech","2025-04-08 01:02:38","OpenAI TTS turns text into lifelike spoken audio, supporting more than 60 different languages and experiment with different voices (alloy, echo, fable, onyx, nova, and shimmer) to find one that matches your desired tone and audience","https://cdn.jojapi.com/api/d02db1b3-60b2-45b4-88a8-6c067f9f4a68",{"name":92},"Open AI Text to Speech API",{"name":94,"slug":95,"created_at":96,"description":97,"logo":98,"seo":99},"Gemini 2.5 Pro","gemini-2-5-pro","2025-04-13 05:54:05","","https://cdn.jojapi.com/api/59be7766-6c57-4933-a70b-c6a53137759a",{"name":100},"Gemini 2.5 Pro API",{"name":102,"slug":103,"created_at":104,"description":105,"logo":106,"seo":107},"Mercury Coder AI","mercury-coder-ai","2025-04-14 04:59:40","A very fast and Ultra speed AI model, Mercury Coder uses a diffusion-based architecture—unlike traditional LLMs. This allows ultra-fast generation of code and responses.","https://cdn.jojapi.com/api/e4201a17-29e4-4041-8f40-550d63d2d644",{"name":108},"Mercury Coder AI API",{"name":110,"slug":7,"created_at":111,"description":112,"logo":113,"seo":114},"Swift AI","2025-05-26 00:29:21","Access a wide range of AI models⚡, including OpenAI 🤖,DeepSeek 🔍, Claude 🧠, Gemini 🌟, and Meta LLaMA 🦙, with seamless compatibility via the Swift API ⚡","https://cdn.jojapi.com/api/be203347-e019-42a9-87f4-1b66161223ae",{"name":115},"Swift AI API",{"name":117,"slug":118,"created_at":119,"description":120,"logo":121,"seo":122},"GPT-5","gpt-5","2025-09-07 04:37:38","GPT‑5 is OpenAI’s most advanced and unified AI model, combining fast, real-time responsiveness with deep reasoning capabilities. It supports multimodal inputs—including text, image, audio, and video—and features a dynamic architecture that switches between quick-answer and “thinking” modes based on prompt complexity. With improved accuracy, reduced hallucinations, and expert-level performance in coding, writing, health, and science, GPT‑5 delivers intelligent, context-aware responses across a wide range of tasks.","https://cdn.jojapi.com/api/9b0a2e37-397c-477e-bbfb-c84a997bb493",{"name":123},"GPT-5 API",{"name":125,"slug":126,"created_at":127,"description":128,"logo":129,"seo":130},"GPT-5 mini","gpt-5-mini","2025-09-08 05:03:00","GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts","https://cdn.jojapi.com/api/0372b184-1926-47ae-9452-76cda3fb48df",{"name":131},"GPT-5 mini API",{"name":133,"slug":134,"created_at":135,"description":136,"logo":137,"seo":138},"GPT-5 nano","gpt-5-nano","2025-09-08 05:15:11","GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks","https://cdn.jojapi.com/api/df15b928-8f79-4f6d-bceb-49b0d241a95f",{"name":139},"GPT-5 nano API",{"name":141,"slug":142,"created_at":143,"description":144,"logo":145,"seo":146},"GPT-4.1","gpt-4-1-kmazrp","2025-09-09 08:16:18","GPT-4.1 excels at instruction following and tool calling, with broad knowledge across domains. It features a 1M token context window, and low latency without a reasoning step.","https://cdn.jojapi.com/api/bb57b229-c6ea-451f-8338-f20a24bc0c60",{"name":147},"GPT-4.1 API",{"name":149,"slug":150,"created_at":151,"description":152,"logo":153,"seo":154},"GPT-4.1 mini","gpt-4-1-mini-zotejo","2025-09-09 08:28:56","GPT-4.1 mini excels at instruction following and tool calling. It features a 1M token context window, and low latency without a reasoning step.","https://cdn.jojapi.com/api/f418e0f6-bc94-494b-bf56-7e2e893ec7a9",{"name":155},"GPT-4.1 mini API",{"name":157,"slug":158,"created_at":159,"description":160,"logo":161,"seo":162},"GPT-4.1 nano","gpt-4-1-nano-ivelsa","2025-09-09 08:35:44","GPT-4.1 nano excels at instruction following and tool calling. It features a 1M token context window, and low latency without a reasoning step.","https://cdn.jojapi.com/api/8fa5e7b4-2114-43cd-ba6e-662cd1ee1ece",{"name":163},"GPT-4.1 nano API",{"name":165,"slug":166,"created_at":167,"description":168,"logo":169,"seo":170},"GPT-4o","gpt-4o-ksdwzw","2025-09-09 14:15:07","GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is the best model for most tasks, and is OpenAI most capable model outside of our o-series models.","https://cdn.jojapi.com/api/61d4d590-669c-41ea-8456-da8f5fe6e04b",{"name":171},"GPT-4o API",{"name":173,"slug":174,"created_at":175,"description":176,"logo":177,"seo":178},"GPT-4o mini","gpt-4o-mini-harfoo","2025-09-09 14:27:04","GPT-4o mini (“o” for “omni”) is a fast, affordable small model for focused tasks. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is ideal for fine-tuning, and model outputs from a larger model like GPT-4o can be distilled to GPT-4o-mini to produce similar results at lower cost and latency.","https://cdn.jojapi.com/api/01b0e056-1a26-443c-8429-a3895349ba65",{"name":179},"GPT-4o mini API",{"name":181,"slug":181,"created_at":182,"description":183,"logo":184,"seo":185},"o3","2025-09-10 05:49:25","o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.","https://cdn.jojapi.com/api/ae6850d8-953f-4d52-90b0-547b48255d56",{"name":186},"o3 API",{"name":188,"slug":188,"created_at":189,"description":190,"logo":191,"seo":192},"o3-mini","2025-09-10 05:57:32","o3-mini is OpenAI newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini supports key developer features, like Structured Outputs, and function calling.","https://cdn.jojapi.com/api/99a7e2e1-a498-448e-9c62-0051d7ddfb11",{"name":193},"o3-mini API",{"name":195,"slug":195,"created_at":196,"description":197,"logo":198,"seo":199},"o1","2025-09-11 07:31:03","The o1 series of models are trained with reinforcement learning to perform complex reasoning. o1 models think before they answer, producing a long internal chain of thought before responding to the user.","https://cdn.jojapi.com/api/a3f9113e-ad77-4e2e-a954-34142fb31b8c",{"name":200},"o1 API",{"name":202,"slug":202,"created_at":203,"description":204,"logo":205,"seo":206},"o1-mini","2025-09-11 07:44:06","The o1 reasoning model is designed to solve hard problems across domains. o1-mini is a faster and more affordable reasoning model, but we recommend using the newer o3-mini model that features higher intelligence at the same latency and price as o1-mini.","https://cdn.jojapi.com/api/b10a9b18-a82d-456f-a304-035fae2755c8",{"name":207},"o1-mini API",{"name":209,"slug":209,"created_at":210,"description":211,"logo":212,"seo":213},"o4-mini","2025-09-12 15:38:42","o4-mini is our latest small o-series model. It's optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks.","https://cdn.jojapi.com/api/d588d171-02e3-4b78-811c-2b27ac0938be",{"name":214},"o4-mini API",{"name":216,"slug":217,"created_at":218,"description":219,"logo":220,"seo":221},"GPT-3.5 Turbo","gpt-3-5-turbo","2025-09-12 15:48:26","GPT-3.5 Turbo models can understand and generate natural language or code and have been optimized for chat using the Chat Completions API but work well for non-chat tasks as well. As of July 2024, use gpt-4o-mini in place of GPT-3.5 Turbo, as it is cheaper, more capable, multimodal, and just as fast. GPT-3.5 Turbo is still available for use in the API.","https://cdn.jojapi.com/api/266f9535-cc15-4019-b170-caae53c5366c",{"name":222},"GPT-3.5 Turbo API",{"name":224,"slug":225,"created_at":226,"description":227,"logo":228,"seo":229},"GPT-4 Turbo","gpt-4-turbo","2025-09-12 15:56:16","GPT-4 Turbo is the next generation of GPT-4, an older high-intelligence GPT model. It was designed to be a cheaper, better version of GPT-4. Today, we recommend using a newer model like GPT-4o.","https://cdn.jojapi.com/api/f39624d9-7ad3-422f-b066-6d967701696b",{"name":230},"GPT-4 Turbo API",{"name":232,"slug":232,"created_at":233,"description":234,"logo":235,"seo":236},"text-embedding-3-small","2025-09-16 11:34:40","text-embedding-3-small is our improved, more performant version of our ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","https://cdn.jojapi.com/api/e7b620a4-cd07-480c-a7af-49f628a3a4a7",{"name":237},"text-embedding-3-small API",{"name":239,"slug":239,"created_at":240,"description":241,"logo":242,"seo":243},"text-embedding-3-large","2025-09-16 11:54:43","text-embedding-3-large is most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","https://cdn.jojapi.com/api/79fd7681-99e3-49f2-8399-46601b286e40",{"name":244},"text-embedding-3-large API",{"name":246,"slug":246,"created_at":247,"description":248,"logo":249,"seo":250},"text-embedding-ada-002","2025-09-20 22:29:07","text-embedding-ada-002 is OpenAI improved, more performant version of OpenAI ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.","https://cdn.jojapi.com/api/9738f00c-e798-49f5-8fad-2c40260158fe",{"name":251},"text-embedding-ada-002 API",{"name":253,"slug":253,"created_at":254,"description":255,"logo":256,"seo":257},"omni-moderation","2025-09-20 22:38:26","Moderation models are free models designed to detect harmful content. This model is our most capable moderation model, accepting images as input as well.","https://cdn.jojapi.com/api/281dfe4c-d7ff-414f-812a-d8c1bf001d4f",{"name":258},"omni-moderation API",{"name":260,"slug":260,"created_at":261,"description":262,"logo":263,"seo":264},"text-moderation","2025-09-20 22:51:57","Moderation models are models designed to detect harmful content. This is our text only moderation model; we expect omni-moderation-* models to be the best default moving forward.","https://cdn.jojapi.com/api/f2acc88d-4848-4a48-b921-bb4772e27091",{"name":265},"text-moderation API",{"name":267,"slug":268,"created_at":269,"description":270,"logo":271,"seo":272},"Claude Haiku 4.5","claude-haiku-4-5","2025-10-25 00:40:22","Claude Haiku 4.5, the newest and fastest model from Anthropic offers coding performance comparable to the top-tier model, Claude Sonnet 4, while being more than twice as fast and costing only a third as much.","https://cdn.jojapi.com/api/cacb0a7e-32be-480d-800e-311829de2b9a",{"name":273},"Claude Haiku 4.5 API",{"name":275,"slug":276,"created_at":277,"description":278,"logo":279,"seo":280},"Claude Sonnet 4.5","claude-sonnet-4-5","2025-10-25 00:47:59","Claude Sonnet 4.5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math.","https://cdn.jojapi.com/api/56a85d83-4bae-4b0b-982c-298c7191fdc5",{"name":281},"Claude Sonnet 4.5 API",{"name":283,"slug":284,"created_at":285,"description":286,"logo":287,"seo":288},"Claude Opus 4.1","claude-opus-4-1","2025-10-25 00:52:18","Claude Opus 4.1 is our most intelligent model to date with a 200K context window, pushing the frontier in coding, agentic search, and creative writing. We’ve also made it possible to run Claude Code in the background, enabling developers to assign long-running coding tasks for Opus to handle independently.","https://cdn.jojapi.com/api/6a9a4297-bd79-45c7-9dc7-cc2e65491f0a",{"name":289},"Claude Opus 4.1 API",{"name":291,"slug":292,"created_at":293,"description":294,"logo":295,"seo":296},"Claude Sonnet 4","claude-sonnet-4","2025-10-25 00:58:02","Claude Sonnet 4 improves on Claude Sonnet 3.7 across a variety of areas with a 200K context window, especially coding. It is a hybrid reasoning model with superior intelligence for high-volume use cases","https://cdn.jojapi.com/api/c3fbaf9a-71c8-4776-8535-1eafb885a192",{"name":297},"Claude Sonnet 4 API",{"name":299,"slug":300,"created_at":301,"description":302,"logo":303,"seo":304},"Claude Opus 3","opus-3","2025-10-31 07:46:32","Opus, the most intelligent model, outperforms its peers on most of the common evaluation benchmarks for AI systems, including undergraduate level expert knowledge (MMLU), graduate level expert reasoning (GPQA), basic mathematics (GSM8K), and more. It exhibits near-human levels of comprehension and fluency on complex tasks, leading the frontier of general intelligence.","https://cdn.jojapi.com/api/a0be3386-4c6c-46cf-960e-4605a01be0e8",{"name":305},"Claude Opus 3 API",{"name":307,"slug":308,"created_at":309,"description":310,"logo":311,"seo":312},"Claude 3 Haiku","claude-3-haiku","2025-11-02 06:58:52","Claude 3 Haiku is the fastest, most compact model for near-instant responsiveness. It answers simple queries and requests with unmatched speed. Users will be able to build seamless AI experiences that mimic human interactions.","https://cdn.jojapi.com/api/7dc95672-e4ff-450d-b59e-1bfd3704ac75",{"name":313},"Claude 3 Haiku API",{"name":315,"slug":316,"created_at":317,"description":318,"logo":319,"seo":320},"Claude Sonnet 3","claude-sonnet-3","2025-11-02 07:09:40","With online search supports, Claude 3.7 Sonnet is the first hybrid reasoning model and our most intelligent model to date. It’s state-of-the art for coding and delivers significant improvements in content generation, data analysis, and planning.","https://cdn.jojapi.com/api/3527643b-a932-4084-974b-685474ea38bd",{"name":321},"Claude Sonnet 3 API",{"name":323,"slug":324,"created_at":325,"description":326,"logo":327,"seo":328},"Gemini 2.5 Flash","gemini-2-5-flash","2025-11-03 06:52:13","Gemini 2.5 Flash is Google’s best model in terms of price and performance, and offers well-rounded capabilities. Gemini 2.5 Flash is Google’s first Flash model that features thinking capabilities, which lets you see the thinking process that the model goes through when generating its response.","https://cdn.jojapi.com/api/951839b3-2a26-4c52-99f8-0d21a0fbfd9f",{"name":329},"Gemini 2.5 Flash API","2025-03-07",{"canonical":332,"page_title":333,"meta":334},"https://jojapi.com/hub/user/swift-ai","swift-ai Developer Profile & APIs - JoJ API",{"description":335},"@swift-ai publishes 41 API(s) on JoJ API, including Claude 3.7-Sonnet, Claude 3.5-Haiku, Claude 3.5-Sonnet, Gemini Pro."]