Text Classification · ZeroGPU
zlm-v1-signal-extract is a specialized ZeroGPU model for turning unstructured text into structured signals that downstream systems can act on.
View detailsThe agent storefront at https://agents.zerogpu.ai/llms.txt publishes prices, payment instructions, and setup. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there instantly, no signup. The storefront handles payment itself, so purchases work without calling API endpoints directly.
Every model on ZeroGPU. Pick an output above to narrow it down.
Text Classification · ZeroGPU
zlm-v1-signal-extract is a specialized ZeroGPU model for turning unstructured text into structured signals that downstream systems can act on.
View detailsText Moderation · ZeroGPU
zlm-v1-moderation-edge is a specialized nano model fine-tuned for moderating chat conversations.
View detailsText Classification · ZeroGPU
zlm-v2-iab-classify-edge-enriched is a multilingual content classification model built for contextual intelligence, advertising, and agent workflows.
View detailsText Classification · ZeroGPU
zlm-v1-iab-domain-classifier is a low-latency domain classification model built for advertising, contextual intelligence, and large-scale enrichment workflows.
View detailsText Classification · ZeroGPU
ZeroGPU's IAB classifier maps any text to the industry-standard IAB Content Taxonomy in a single, fast inference call.
View detailsText Generation · ZeroGPU
zlm-v1-tool-decisions turns user intent into action, combining fast MCP tool selection with high-quality query and argument generation.
View detailsSpeech-to-Text · OpenAI
Whisper Tiny is a lightweight automatic speech recognition model from OpenAI designed for fast and efficient speech-to-text transcription.
View detailsText-to-Speech · Resemble AI
Chatterbox Nano is a lightweight text-to-speech model from Resemble AI designed for fast, high-quality speech generation.
View detailsText Classification · Fastino
GLiNER2.5 Base is an English schema-based information extraction model built on DeBERTa-v3-base.
View detailsText Classification · Fastino
GLiNER2.5 Multi is a 287M-parameter multilingual information extraction model built on mDeBERTa-v3-base.
View detailsText Classification · Microsoft
deberta-v3-small is Microsoft’s lightweight text classification model optimized for fast, low-cost zero-shot classification.
View detailsText Embedding · Sentence Transformers
all-MiniLM-L6-v2 is a lightweight sentence embedding model that converts sentences and short paragraphs into 384-dimensional dense vectors.
View detailsText Classification · Fastino
GLiNER2.5 Decide is a lightweight, zero-shot decision and classification model built for operational AI workflows.
View detailsText-to-Speech · Resemble AI
Resemble AI Chatterbox (original ChatterboxTTS, 0.5B) text-to-speech with zero-shot voice cloning and cfg_weight/exaggeration control; billed per second of generated audio, rounded up to the next whole second per request.
View detailsText Embedding · BAAI
bge-small-en-v1.5 is a lightweight English embedding model from BAAI designed for semantic search, retrieval, similarity scoring, ranking, and RAG workflows.
View detailsText Classification
d1.1 is LiquidAI's decision model and the successor to d1.
View detailsText Generation · DeepSeek
DeepSeek V4.1 Flash is an open-weight sparse mixture-of-experts model and the first built on DeepSeek's Causal Encoder-Decoder (CED) architecture, activating 8B parameters on input and 16B on output.
View detailsText Generation · Z.ai
GLM-5.3-Flash is Z.ai's efficient open-weight model for coding and long-horizon agent tasks.
View detailsText Generation · OpenAI
GPT-5.4 nano is the most cost-efficient model in OpenAI's GPT-5.4 family, built for high-volume and latency-sensitive workloads such as classification, extraction, routing and sub-agent tasks.
View detailsText Generation · OpenAI
GPT-6 Luna is the most efficient model of OpenAI's GPT-6 family, built for high-volume, cost-sensitive workloads.
View detailsText Generation · OpenAI
GPT-4.1 mini is OpenAI's fast, cost-efficient GPT-4.1 model.
View detailsText Generation · OpenAI
GPT-5.6 Luna is the cost-optimized model of OpenAI's GPT-5.6 family, designed for cost-sensitive, high-volume workloads.
View detailsText Generation · OpenAI
gpt-oss-120b is OpenAI’s open-weight reasoning model built for advanced text generation, coding, research, and agentic workflows.
View detailsText Generation · Qwen
qwen3-30b-a3b-fp8 is Qwen’s open-weight mixture-of-experts model designed for efficient reasoning, coding, multilingual text generation, and agentic workflows.
View detailsSummarization · Meta
llama-3.1-8b-instruct-fast is Meta’s Llama 3.1 8B Instruct model optimized by ZeroGPU for fast, cost-efficient summarization and text processing at scale.
View detailsSummarization · OpenAI
gpt-oss-20b is OpenAI's open-weight reasoning model for solving problems, writing and debugging code, summarizing complex information, and answering questions from supplied context.
View detailsSummarization · Meta
llama-3.2-3b-instruct-fast is Meta's Llama 3.2 3B Instruct model packaged by ZeroGPU for fast, low-cost summarization on edge GPUs.
View detailsText Generation · Meta
Llama Guard 4 12B is Meta’s multimodal safety classification model for moderating text, images, and mixed text-image inputs.
View detailsText Generation · Liquid AI
LFM2.5-1.2B-Thinking is Liquid AI’s compact 1.2B-parameter reasoning model designed for multi-step problem solving, planning, data extraction, and agentic workflows.
View detailsText Generation · Liquid AI
LFM2.5-1.2B-Instruct is Liquid AI’s compact 1.2B-parameter instruction model built for efficient text generation, conversational AI, and lightweight agent workflows.
View detailsText Generation
Baidu Unlimited-OCR: document parsing and OCR for PDFs, scanned documents and images, returned as clean Markdown (HTML tables, LaTeX formulas).
View detailsContact us for pricing
Text Generation · Qwen
Alibaba Qwen3.6-35B-A3B open-weight multimodal MoE (35B total, ~3B active): text, images, video and PDF documents in, text out, 262K context, tool calling and structured outputs.
View details