{"seller":{"id":"sel_N9a3wHskbACQi7m8JMg-6","name":"ZeroGPU","slug":"zerogpu","upstreamBaseUrl":"https://api.zerogpu.ai/","description":"Run high-volume AI tasks on specialized small and nano language models across an edge-powered network.","brandColor":"#3FB14E","tagline":"The compute efficiency layer for AI inference.","tags":["inference","small-models","edge","classification","pii-redaction"],"docsUrl":"https://docs.zerogpu.ai/","websiteUrl":"https://zerogpu.ai/","logoUrl":"https://zerogpu.ai/favicon.png","llmsTxtUrl":"https://docs.zerogpu.ai/llms-full.txt","openApiUrl":"https://docs.zerogpu.ai/api-reference/openapi/zeroclick.openapi.json","contactEmail":null,"includedUsageDailyCapMicros":null,"includedUsageWeeklyCapMicros":null,"onboardingRequired":false,"payHost":"agents.zerogpu.ai"},"services":[{"id":"svc_kJDXeoJEklkTrAOUaEPX5","name":"deberta-v3-small","slug":"deberta-v3-small","description":"Microsoft’s DeBERTa-v3-small is a fast, lightweight zero-shot text classifier for high-volume routing, filtering, and tagging. Hand it any text alongside your own candidate labels and it returns a confidence score for each. No training data and no fixed taxonomy, just the categories you define at request time. Because it scores every label rather than forcing one choice, you get soft probabilities to threshold, rank, or route on however your pipeline needs. Purpose-built and CPU-optimized, it runs faster and cheaper than asking a general-purpose frontier model to classify.","icon":"classification","meters":[{"id":"mtr_0j-gxf0wkBuxUYe0bGMDz","key":"input_tokens","unit":"token"},{"id":"mtr_5Ou9BQxxzn0zP0ivcZdO7","key":"output_tokens","unit":"token"}]},{"id":"svc_YCR69XgMKXtrDln-EwEy5","name":"deepseek-v4-flash","slug":"deepseek-v4-flash","description":"DeepSeek's DeepSeek-V4-Flash is an open-weight Mixture-of-Experts model built for efficient reasoning, coding, and agentic workflows, with 284B total parameters activating only 13B per token, served on ZeroGPU for general text generation. It sustains a 1,048,576-token (1M) context well suited for analyzing large codebases, long documents, extensive conversations, and complex research tasks, and supports fast non-thinking responses as well as higher-effort reasoning modes for planning, problem-solving, and multi-step automation. MIT-licensed with no usage restrictions.","icon":"code","meters":[{"id":"mtr_ufHNlZs3AGf7BbjHdBsR6","key":"input_tokens","unit":"token"},{"id":"mtr_yEj83sUq_WGl1UM3-LzLE","key":"output_tokens","unit":"token"}]},{"id":"svc_N2KPFpOlZiYp2PCA3M5ev","name":"gliner2-base-v1","slug":"gliner2-base-v1","description":"gliner2-base-v1 is a versatile extraction-and-classification model for the structured tasks that fill most production pipelines. Point it at any text and, with a single API call, pull named entities by your own labels, populate a typed JSON schema straight from messy input, or classify by sentiment, intent, or topic. No fine-tuning and no prompt engineering, just a label set or schema at inference time. Because it’s purpose-built and CPU-optimized, it runs faster and cheaper than routing this work to a general-purpose frontier model. Reach for gliner-multi-pii-v1 when the job is dedicated PII redaction. When you need clean structure out of raw text, this is the model.","icon":"text-mining","meters":[{"id":"mtr_oo_kkgK3VSDtBZVTKfpdn","key":"input_tokens","unit":"token"},{"id":"mtr_BGYsirx3D8F8AUT-nsvqz","key":"output_tokens","unit":"token"}]},{"id":"svc_w-PM3TF98vW7wnad74AbN","name":"gliner-multi-pii-v1","slug":"gliner-multi-pii-v1","description":"GLiNER Multi PII is a multilingual PII detection and redaction model that supports on-prem deployments as well. It identifies 40+ personally identifiable entity types — identity, contact, government IDs, financial, medical and more. It works natively across six languages: English, French, German, Spanish, Italian, and Portuguese, so a single model covers multi-market and cross-border data without separate per-language pipelines. Built for zero-shot label, it accepts custom label sets at inference time and supports curated PII catalogues, redaction with label or character masks, and generic NER with user-supplied labels.","icon":"fingerprint-recognition","meters":[{"id":"mtr_w256PRMolFgN2lrFNGRUB","key":"input_tokens","unit":"tokens"},{"id":"mtr_MtDZIfAjPF84P22cxiwcO","key":"output_tokens","unit":"tokens"}]},{"id":"svc_q6U7jrT02daD7bBXnDFuE","name":"glm-5.2","slug":"glm-5-2","description":"Z.ai's GLM-5.2 is an open-weight Mixture-of-Experts flagship built for long-horizon tasks, with 753B total parameters activating 8 of 256 experts per token, served on ZeroGPU for general text generation. It sustains a solid 1,048,576-token (1M) context, reasons through a problem with flexible thinking effort before answering, and supports function calling and batch tasks. MIT-licensed with no usage restrictions. When the work spans entire repos, day-long agent sessions, or million-token documents, this is the model.","icon":"mountain","meters":[{"id":"mtr_mXPYw71ZqhftX5OfBt65X","key":"input_tokens","unit":"token"},{"id":"mtr_dYcFXxTrgHBo64lqvkDWT","key":"output_tokens","unit":"token"}]},{"id":"svc_Y_UnnFVooM7U5ok8NONe7","name":"gpt-oss-120b","slug":"gpt-oss-120b","description":"OpenAI's gpt-oss-120b is an open-weight Mixture-of-Experts model with 117B total parameters (5.1B active per token), served on ZeroGPU for general text generation. It reasons through a problem before answering and returns that reasoning trace alongside the final answer, and it supports function calling, batch tasks, and a 131,072-token context window. When a task needs frontier-level reasoning or tool use beyond what the smaller edge models cover, this is the model.","icon":"chip","meters":[{"id":"mtr_R1n8-RGhLJsnvD-KPBWAa","key":"input_tokens","unit":"token"},{"id":"mtr_VN-yIeawWGDsm_NLVouKg","key":"output_tokens","unit":"token"}]},{"id":"svc_XB84IdiP1GXI9t94NieXu","name":"LFM2.5-1.2B-Instruct","slug":"lfm2-5-1-2b-instruct","description":"Liquid AI’s LFM2.5-1.2B-Instruct is a hybrid architecture model purpose-built for on-device deployment, trained on 28 trillion tokens with multi-stage reinforcement learning. It delivers best-in-class instruction following and native tool-calling at the 1B scale — something very few models this size can do reliably. Its hybrid design gives it significantly faster inference with lower memory usage compared to transformer-only models of the same size. If you need a conversational model that can actually run on real devices without a GPU, this is it. Supports 8 languages including English, Chinese, Japanese, and Spanish.","icon":"chat-bot","meters":[{"id":"mtr_GtHoNvzh5_TV6Wz5Hqk0g","key":"input_tokens","unit":"token"},{"id":"mtr_HQeeKxyOvBEH74gZjIVGI","key":"output_tokens","unit":"token"}]},{"id":"svc_TGuGdXjwgQKqxpIuiVTUl","name":"LFM2.5-1.2B-Thinking","slug":"lfm2-5-1-2b-thinking","description":"Liquid AI’s LFM2.5-1.2B-Thinking is a compact reasoning model that works through a problem step by step before it answers. Built by Liquid AI, it generates an explicit chain-of-thought trace so for multi-step math, planning, data extraction, and agentic tool-calling, you get verifiable intermediate reasoning, not just a final guess. At 1.2B parameters it fits under a gigabyte and runs fast on CPU at the edge, rivaling models several times its size on reasoning benchmarks. Reach for a frontier model when the task is knowledge-heavy or code-intensive, and keep this one as the planning brain that decides and orchestrates. When the task needs reasoning, this is the model.","icon":"brain","meters":[{"id":"mtr_pPmH8JjyydftHsPM_isan","key":"input_tokens","unit":"token"},{"id":"mtr_-xoHgAzPpFTqRqAM-i0_e","key":"output_tokens","unit":"token"}]},{"id":"svc_46FOUv0wCeVJQWMmRgWfq","name":"llama-3.1-8b-instruct-fast","slug":"llama-3-1-8b-instruct-fast","description":"Meta’s Llama 3.1 Instruct, tuned for fast, low-cost summarization at scale on the ZeroGPU edge network. Its 128K-token context window takes in entire documents, long transcripts, and full email or chat threads in a single pass. No chunking, no stitching partial summaries back together. Built for the high-volume summarization that runs around your core product: condensing long reports and transcripts, summarizing email and chat threads, and processing articles in bulk. When context length matters and you’re summarizing on every request, this is the model that keeps it fast and affordable.","icon":"lightning","meters":[{"id":"mtr_OR3Qo1PKhbyeSZRD9Tzsz","key":"input_tokens","unit":"token"},{"id":"mtr_oql8RtXo-cfLtskjJxXuw","key":"output_tokens","unit":"token"}]},{"id":"svc_wHTWqyhRhF0aLFuhAvoE1","name":"qwen3-30b-a3b-fp8","slug":"qwen3-30b-a3b-fp8","description":"Alibaba's Qwen3-30B-A3B is an open-weight Mixture-of-Experts model with 30.5B total parameters (3.3B active per token), served on ZeroGPU as an FP8 build for efficient inference. It thinks through a problem before answering and returns that reasoning alongside the final text, and it supports function calling, streaming, batch tasks, and 100+ languages with a 32,768-token context window. When you want frontier-style reasoning and tool use in a lighter, multilingual package, this is the model.","icon":"translate","meters":[{"id":"mtr_4OAO2l0h1c9D6cuIiELNu","key":"input_tokens","unit":"token"},{"id":"mtr_f_om6-ygBpCTcwUUEqjx7","key":"output_tokens","unit":"token"}]},{"id":"svc_RVoZ3FHMxG7RUux6rAP7H","name":"zlm-v1-followup-questions-edge","slug":"zlm-v1-followup-questions-edge","description":"ZeroGPU’s follow-up question generator takes any piece of content — an article, an answer, a chat turn and returns a short set of natural questions a reader would actually ask next. Where a general-purpose model has to be coaxed into this with prompting, this one is purpose built: every output is a ready-to-render question, no parsing or cleanup. Small enough to run inline at the edge, it adds a “what to ask next” layer to any surface for a fraction of a cent per call. When you want to turn a dead end into the next click, this is the model.","icon":"help","meters":[{"id":"mtr_4nvyitko4LYkuJ8VsX22W","key":"input_tokens","unit":"token"},{"id":"mtr_zbEdgLAat2GZbK6tP4whu","key":"output_tokens","unit":"token"}]},{"id":"svc_wacpcZG1r-Xc4TSWKgH16","name":"zlm-v1-iab-classify-edge","slug":"zlm-v1-iab-classify-edge","description":"ZeroGPU’s IAB classifier maps any text to the industry-standard IAB Content Taxonomy in a single, fast inference call. Each call returns categories across both the 1.0 and 2.2 taxonomies plus matched audience segments, every result scored for confidence. At 90M parameters on ONNX, it’s built for the high-volume, sub-millisecond classification that ad tech and content platforms demand, right at the edge. When you need clean category and audience signals on every request, this is the model — and when you need the full profile, reach for the enriched variant.","icon":"category","meters":[{"id":"mtr_wk3AOc9soky38tWGxiqdk","key":"input_tokens","unit":"token"},{"id":"mtr_cX1tIW0GDbpJKNKJqqYXO","key":"output_tokens","unit":"token"}]},{"id":"svc_iyx7xXQJWQrSzn5Ek5Gn5","name":"zlm-v1-iab-domain-classifier","slug":"zlm-v1-iab-domain-classifier","description":"ZeroGPU’s Domain IAB Classifier maps a raw domain name straight to the IAB Content Taxonomy in a single, fast inference call, returning content categories, topics, keywords, and user-intent signals. Because it needs only the domain as input, it reduces payload size by up to 10x compared to page-level classification workflows while still surfacing the contextual signals that bidstream enrichment, contextual targeting, and domain-level intelligence pipelines run on. At 149M parameters on ONNX, it’s built for the high-volume, sub-millisecond classification that ad tech and content platforms demand, right at the edge.","icon":"globe","meters":[{"id":"mtr_BtbaG8iKvNX7iShg1p6pm","key":"input_tokens","unit":"token"},{"id":"mtr_2Eb9RoTOo_IPRg_oyon-B","key":"output_tokens","unit":"token"}]},{"id":"svc_dZSS5dE1nj_CoJQyov22X","name":"zlm-v2-iab-classify-edge-enriched","slug":"zlm-v2-iab-classify-edge-enriched","description":"The enriched variant of ZeroGPU's IAB classifier turns a single inference call into a full content-intelligence profile — not just a label, but everything a contextual pipeline needs to act on. Each call returns IAB categories across both the 1.0 and 2.2 taxonomies (down to tier-3), audience and interest segments, topics, keywords, and user-intent classification — all with confidence scores with edge-native, sub-millisecond speeds. With support for 50+ languages, it delivers the same full profile on multilingual content without a translation step. Built for contextual ad targeting, brand-safety scoring, publisher content categorization, and signal pipelines that need full metadata on every request.","icon":"layers","meters":[{"id":"mtr_-0W8YvKFXL_JYnzWtYuek","key":"input_tokens","unit":"token"},{"id":"mtr_JxGstpK8B70EBmBBle6H0","key":"output_tokens","unit":"token"}]}],"plans":[{"id":"pln_G9sTqYTPMqN-yG1kgeiaY","name":"Credits","slug":"credits","billingMode":"credit","interval":"none","basePriceUsd":"0.000000","includedCreditUsd":"10.000000","minimumPurchaseUsd":"0.010000","estimateUsd":null,"purchase":{"url":"https://agents.zerogpu.ai/plans/pln_G9sTqYTPMqN-yG1kgeiaY/purchase","amountRequired":true,"minimumUsd":"0.010000"},"prices":[{"id":"pmp_9QSGrTEt8TG0LtD_IJG9m","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"llama-3-1-8b-instruct-fast","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_K878pqe3uYEkrZJ8pAEUA","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":131072,"serviceSlug":"llama-3-1-8b-instruct-fast","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_dxWer62r5d9oclR-kPoue","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"deberta-v3-small","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_r9Gz5TYenXavaG14yIrVX","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"gliner2-base-v1","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_NVtUfm8kuErc6j6glRJBR","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"gliner-multi-pii-v1","meterSlug":"input_tokens","unit":"tokens"},{"id":"pmp_kMn6rTHuRO_PcagNCXcRq","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"lfm2-5-1-2b-instruct","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_U4pCCk8NVRIqM9qkmx1hB","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"lfm2-5-1-2b-thinking","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_Bs65bJDCtfJ6Zk_CGxPJW","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"zlm-v1-iab-domain-classifier","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_2L9DQgTlmkA9cRz7ToNcF","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"zlm-v2-iab-classify-edge-enriched","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_9jKdtdMpqx5NnLEWQE7Tp","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"zlm-v1-followup-questions-edge","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_jM7E6_J5IU2PydgwQvLH7","priceUsd":"0.020000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"zlm-v1-iab-classify-edge","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_AXQDP4n-C9Az8GsgymtHn","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1024,"serviceSlug":"zlm-v1-iab-domain-classifier","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_LGWVT-5bDz1HD5W58HoPr","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1024,"serviceSlug":"zlm-v2-iab-classify-edge-enriched","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_3LvaRRmc_i-F9jCu7lUFa","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1024,"serviceSlug":"zlm-v1-iab-classify-edge","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_OKjxrZnWTY-HAaFkD4fC6","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1024,"serviceSlug":"zlm-v1-followup-questions-edge","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_ZcaoH4Cxy8Yeha0i95-__","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":32768,"serviceSlug":"lfm2-5-1-2b-thinking","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_FkLEoKH6VJeWmb5w5f7r4","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":32768,"serviceSlug":"lfm2-5-1-2b-instruct","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_7vXTPON_v0McTMU-3n5ur","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1024,"serviceSlug":"gliner-multi-pii-v1","meterSlug":"output_tokens","unit":"tokens"},{"id":"pmp_2b0Er2lyi4xysRMlHbpVX","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1024,"serviceSlug":"gliner2-base-v1","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_D0OihVR43F1oCk732aphb","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1024,"serviceSlug":"deberta-v3-small","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_OodNuSxCV6sQXyLkNTAf_","priceUsd":"0.030000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"gpt-oss-120b","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_iVfv_juOLQxAh3PWuqjwS","priceUsd":"0.100000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":131072,"serviceSlug":"gpt-oss-120b","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_3-UKSb8i6PjdrA6NxGH-_","priceUsd":"0.050000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"qwen3-30b-a3b-fp8","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_lNI_t-KvAYn27gI1-ntTp","priceUsd":"0.300000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":32768,"serviceSlug":"qwen3-30b-a3b-fp8","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_GuSjVmhh7LX62kPIsXeL7","priceUsd":"1.100000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"glm-5-2","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_t-o_DZ8IAFIEo6dQe9raL","priceUsd":"3.500000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1048576,"serviceSlug":"glm-5-2","meterSlug":"output_tokens","unit":"token"},{"id":"pmp_vL5ePiKMOv7Pp3tLT1cCg","priceUsd":"0.070000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":null,"serviceSlug":"deepseek-v4-flash","meterSlug":"input_tokens","unit":"token"},{"id":"pmp_Idan8pS7CP21IgQsv8zO2","priceUsd":"0.140000","unitSize":1000000,"includedUnits":0,"defaultMaxQuantity":1048576,"serviceSlug":"deepseek-v4-flash","meterSlug":"output_tokens","unit":"token"}]}],"links":{"agentGuide":"https://agents.zerogpu.ai/llms-full.txt","llmsTxt":"https://agents.zerogpu.ai/llms.txt","manifest":"https://agents.zerogpu.ai/manifest.json","openapi":"https://agents.zerogpu.ai/openapi.json"}}