ZeroGPU sells to AI agents - no signup

The 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.

    All models

    30 modelsClear all

    Every model on ZeroGPU. Pick an output above to narrow it down.

    ZeroGPU ZLM models (6)

    zlm-v1-signal-extract logo

    Text Classification · ZeroGPU

    TextExtraction

    zlm-v1-signal-extract is a specialized ZeroGPU model for turning unstructured text into structured signals that downstream systems can act on.

    View details
    $0.04 / 1M input$0.10 / 1M output
    zlm-v2-iab-classify-edge-enriched logo

    Text Classification · ZeroGPU

    TextDecisions

    zlm-v2-iab-classify-edge-enriched is a multilingual content classification model built for contextual intelligence, advertising, and agent workflows.

    View details
    $0.05 / 1M input$0.15 / 1M output
    zlm-v1-iab-domain-classifier logo

    Text Classification · ZeroGPU

    TextDecisions

    zlm-v1-iab-domain-classifier is a low-latency domain classification model built for advertising, contextual intelligence, and large-scale enrichment workflows.

    View details
    $0.02 / 1M input$0.05 / 1M output
    zlm-v1-iab-classify-edge logo

    Text Classification · ZeroGPU

    TextDecisions

    ZeroGPU's IAB classifier maps any text to the industry-standard IAB Content Taxonomy in a single, fast inference call.

    View details
    $0.02 / 1M input$0.05 / 1M output
    zlm-v1-tool-decisions logo

    Text Generation · ZeroGPU

    TextText

    zlm-v1-tool-decisions turns user intent into action, combining fast MCP tool selection with high-quality query and argument generation.

    View details
    $0.04 / 1M input

    Small language models (8)

    Chatterbox Nano logo

    Text-to-Speech · Resemble AI

    TextAudio

    Chatterbox Nano is a lightweight text-to-speech model from Resemble AI designed for fast, high-quality speech generation.

    View details
    $0.01 / minute
    GLiNER2.5 Base v1 logo

    Text Classification · Fastino

    TextExtraction

    GLiNER2.5 Base is an English schema-based information extraction model built on DeBERTa-v3-base.

    View details
    $0.02 / 1M input$0.05 / 1M output
    GLiNER2.5 Multi v1 logo

    Text Classification · Fastino

    TextExtraction

    GLiNER2.5 Multi is a 287M-parameter multilingual information extraction model built on mDeBERTa-v3-base.

    View details
    $0.02 / 1M input$0.05 / 1M output
    deberta-v3-small logo

    Text Classification · Microsoft

    TextDecisions

    deberta-v3-small is Microsoft’s lightweight text classification model optimized for fast, low-cost zero-shot classification.

    View details
    $0.02 / 1M input$0.05 / 1M output
    all-minilm-l6-v2 logo

    Text Embedding · Sentence Transformers

    TextEmbeddings

    all-MiniLM-L6-v2 is a lightweight sentence embedding model that converts sentences and short paragraphs into 384-dimensional dense vectors.

    View details
    $0.0040 / 1M input
    GLiNER2.5 Decide v1 logo

    Text Classification · Fastino

    TextDecisions

    GLiNER2.5 Decide is a lightweight, zero-shot decision and classification model built for operational AI workflows.

    View details
    $0.01 / 1M input
    Chatterbox logo

    Text-to-Speech · Resemble AI

    TextAudio

    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 details
    $0.01 / minute
    bge-small-en-v1.5 logo

    Text Embedding · BAAI

    TextEmbeddings

    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 details
    $0.0040 / 1M input

    Open-weight and frontier models (16)

    deepseek-v4.1-flash logo

    Text Generation · DeepSeek

    TextText

    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 details
    $0.30 / 1M input$1.20 / 1M output
    glm-5.3-flash logo

    Text Generation · Z.ai

    TextText

    GLM-5.3-Flash is Z.ai's efficient open-weight model for coding and long-horizon agent tasks.

    View details
    $0.10 / 1M input$0.35 / 1M output
    gpt-5.4-nano logo

    Text Generation · OpenAI

    TextText

    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 details
    $0.20 / 1M input$1.25 / 1M output
    gpt-6-luna logo

    Text Generation · OpenAI

    Text + ImageText

    GPT-6 Luna is the most efficient model of OpenAI's GPT-6 family, built for high-volume, cost-sensitive workloads.

    View details
    $0.10 / 1M input$0.50 / 1M output
    gpt-5.6-luna logo

    Text Generation · OpenAI

    TextText

    GPT-5.6 Luna is the cost-optimized model of OpenAI's GPT-5.6 family, designed for cost-sensitive, high-volume workloads.

    View details
    $0.20 / 1M input$1.20 / 1M output
    gpt-oss-120b logo

    Text Generation · OpenAI

    TextText

    gpt-oss-120b is OpenAI’s open-weight reasoning model built for advanced text generation, coding, research, and agentic workflows.

    View details
    $0.15 / 1M input$0.60 / 1M output
    qwen3-30b-a3b-fp8 logo

    Text Generation · Qwen

    TextText

    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 details
    $0.10 / 1M input$0.45 / 1M output
    llama-3.1-8b-instruct-fast logo

    Summarization · Meta

    TextText

    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 details
    $0.15 / 1M input$0.28 / 1M output
    gpt-oss-20b logo

    Summarization · OpenAI

    TextText

    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 details
    $0.02 / 1M input$0.10 / 1M output
    llama-3.2-3b-instruct-fast logo

    Summarization · Meta

    TextText

    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 details
    $0.05 / 1M input$0.30 / 1M output
    llama-guard-4-12b logo

    Text Generation · Meta

    Text + ImageDecisions

    Llama Guard 4 12B is Meta’s multimodal safety classification model for moderating text, images, and mixed text-image inputs.

    View details
    $0.18 / 1M input$0.18 / 1M output
    LFM2.5-1.2B-Thinking logo

    Text Generation · Liquid AI

    TextText

    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 details
    $0.02 / 1M input$0.05 / 1M output
    LFM2.5-1.2B-Instruct logo

    Text Generation · Liquid AI

    TextText

    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 details
    $0.02 / 1M input$0.05 / 1M output
    Qwen3.6 35B A3B logo

    Text Generation · Qwen

    Text + Image + Video + FileText

    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
    $0.20 / 1M input$1.50 / 1M output