# Services from x402-nvidia.vercel.app on Zero

> x402-nvidia.vercel.app serves 48 paid API services for AI agents, indexed by Zero. Each is callable per call with payment handled by Zero.

Canonical page: https://www.zero.xyz/host/x402-nvidia.vercel.app
Live health (JSON, refreshed every minute): https://www.zero.xyz/host/x402-nvidia.vercel.app/health.json

## Services

- [X402-NVIDIA Nemotron-3-Nano-30B Chat Completions](https://www.zero.xyz/c/x402-nvidia-nemotron-3-nano-30b-chat-completions-b924d770/llms.txt): $0.065331/call via x402. Runs inference on NVIDIA's Nemotron-3-Nano-30B language model via x402 micropayments, returning chat completions
- [X402-NVIDIA GLiNER PII Extraction](https://www.zero.xyz/c/x402-nvidia-gliner-pii-extraction-efbcf86f/llms.txt): $0.088894/call via x402. Extracts and identifies personally identifiable information (PII) from text using NVIDIA's GLiNER model, paid via x402 micropayments.
- [X402-NVIDIA ESMFold Protein Structure Prediction](https://www.zero.xyz/c/x402-nvidia-esmfold-protein-structure-prediction-f35142ba/llms.txt): $0.055091/call via x402. Predicts 3D protein structure from amino acid sequence using NVIDIA NIM's ESMFold model, paid via x402 micropayments
- [X402-NVIDIA StepFun Step-3-7-Flash via Micropayment](https://www.zero.xyz/c/x402-nvidia-stepfun-step-3-7-flash-via-micropayment-b24f8522/llms.txt): $0.157502/call via x402. Run inference on the StepFun Step-3-7-Flash language model via NVIDIA NIM, paying per-call with USDC micropayments using the x402 protocol.
- [X402-NVIDIA PaliGemma Vision API](https://www.zero.xyz/c/x402-nvidia-paligemma-vision-api-f819cc12/llms.txt): $0.060613/call via x402. Run PaliGemma vision-language model inference via x402 micropayments, returning chat-style completions for image understanding tasks
- [X402-NVIDIA GPT-OSS-120B via NIM API](https://www.zero.xyz/c/x402-nvidia-gpt-oss-120b-via-nim-api-efc7cc09/llms.txt): $0.161884/call via x402. Runs inference against NVIDIA's GPT-OSS-120B large language model via NIM, billed per call using x402 USDC micropayments
- [X402-NVIDIA Nemotron-3 Nano Omni via Micropayment](https://www.zero.xyz/c/x402-nvidia-nemotron-3-nano-omni-via-micropayment-648658ee/llms.txt): $0.114268/call via x402. Run NVIDIA's Nemotron-3 Nano Omni model for chat completions via x402 micropayment, returning assistant message choices.
- [X402-NVIDIA Qwen3-5-122B Chat Completions API](https://www.zero.xyz/c/x402-nvidia-qwen3-5-122b-chat-completions-api-53f717b7/llms.txt): $0.172823/call via x402. Runs chat completions using NVIDIA NIM's Qwen3-5 122B model, paid per-call via x402 USDC micropayments
- [X402-NVIDIA Qwen3-Next-80B Chat Completions](https://www.zero.xyz/c/x402-nvidia-qwen3-next-80b-chat-completions-0744e128/llms.txt): $0.136724/call via x402. Run inference on NVIDIA's hosted Qwen3-Next-80B large language model via x402 micropayments, returning chat completion responses.
- [NVIDIA Nemotron-3 Ultra 550B via x402 Micropayments](https://www.zero.xyz/c/nvidia-nemotron-3-ultra-550b-via-x402-micropayments-c2a80acb/llms.txt): $0.129626/call via x402. Run inference on NVIDIA's Nemotron-3 Ultra 550B large language model via pay-per-call USDC micropayments using the x402 protocol
- [X402-NVIDIA Nemotron Nano 9B Chat Completions](https://www.zero.xyz/c/x402-nvidia-nemotron-nano-9b-chat-completions-83edc84f/llms.txt): $0.102729/call via x402. Run inference against NVIDIA's Nemotron Nano 9B language model via x402 micropayment-gated API, returning chat completion responses
- [X402-NVIDIA StepFun Step-3.5 Flash via Micropayment](https://www.zero.xyz/c/x402-nvidia-stepfun-step-3-5-flash-via-micropayment-64dbcab5/llms.txt): $0.105734/call via x402. Run StepFun Step-3.5 Flash chat completions via NVIDIA NIM with per-call USDC micropayment using the x402 protocol
- [NVIDIA NIM Llama 3.1 Safety Guard API (x402)](https://www.zero.xyz/c/nvidia-nim-llama-3-1-safety-guard-api-x402-e7c8d79f/llms.txt): $0.135751/call via x402. Runs NVIDIA's Llama 3.1 safety guard model to classify or filter content for safety via x402 micropayment
- [X402-NVIDIA Gemma-3N-E4B Chat Completions](https://www.zero.xyz/c/x402-nvidia-gemma-3n-e4b-chat-completions-5e98ae4d/llms.txt): $0.106113/call via x402. Run Google Gemma-3N-E4B inference via NVIDIA NIM, billed per-call using x402 USDC micropayments
- [X402-NVIDIA Ministral-14B Chat Completions](https://www.zero.xyz/c/x402-nvidia-ministral-14b-chat-completions-1f3834d6/llms.txt): $0.172128/call via x402. Run inference on NVIDIA's Ministral-14B language model via a pay-per-call x402 micropayment gateway
- [X402-NVIDIA Gemma-4-31B NIM Chat Completions](https://www.zero.xyz/c/x402-nvidia-gemma-4-31b-nim-chat-completions-02983d0c/llms.txt): $0.186144/call via x402. Runs inference on NVIDIA's Gemma-4-31B NIM model via x402 micropayments, returning chat completion responses
- [NVIDIA Nemotron-Nano-12B-VL Vision-Language Model via x402](https://www.zero.xyz/c/nvidia-nemotron-nano-12b-vl-vision-language-model-via-x402-25e43471/llms.txt): $0.086429/call via x402. Run inference on NVIDIA's Nemotron-Nano-12B-VL vision-language model via x402 micropayment-gated chat completions API
- [NVIDIA Nemotron-3 Content Safety API (x402)](https://www.zero.xyz/c/nvidia-nemotron-3-content-safety-api-x402-5f212a12/llms.txt): $0.188236/call via x402. Runs text content through NVIDIA's Nemotron-3 content safety model to classify and flag unsafe or policy-violating content, paid via x402 micropayments.
- [NVIDIA NIM Rerank QA Mistral via X402 Micropayments](https://www.zero.xyz/c/nvidia-nim-rerank-qa-mistral-via-x402-micropayments-f1dfbb4e/llms.txt): $0.109039/call via x402. Reranks a set of candidate passages or model responses for question-answering relevance using NVIDIA's Mistral-based reranking model, paid via x402 micropayment.
- [X402-NVIDIA Mixtral-8x7B Chat Completions](https://www.zero.xyz/c/x402-nvidia-mixtral-8x7b-chat-completions-da86948d/llms.txt): $0.117863/call via x402. Generate chat completions using Mixtral-8x7B via NVIDIA NIM, paid per-call with USDC micropayments over x402
- [X402-NVIDIA Qwen3-235B-A22B via NIM (x402)](https://www.zero.xyz/c/x402-nvidia-qwen3-235b-a22b-via-nim-x402-7c844cd7/llms.txt): $0.189357/call via x402. Runs Qwen3-235B-A22B chat completions through NVIDIA NIM inference, billed per-call via x402 USDC micropayments
- [X402-NVIDIA Mistral Large 3 Chat Completions](https://www.zero.xyz/c/x402-nvidia-mistral-large-3-chat-completions-3e98f303/llms.txt): $0.159201/call via x402. Runs inference on NVIDIA NIM's Mistral Large 3 model via x402 micropayment, returning chat completion responses.
- [X402-NVIDIA Llama-3.3-Nemotron-Super-49B Chat Completions](https://www.zero.xyz/c/x402-nvidia-llama-3-3-nemotron-super-49b-chat-completions-8998a2ed/llms.txt): $0.158628/call via x402. Run chat completions against NVIDIA's Llama-3.3-Nemotron-Super-49B model via x402 micropayment-gated API
- [X402-NVIDIA DeepSeek V4 Pro via NIM](https://www.zero.xyz/c/x402-nvidia-deepseek-v4-pro-via-nim-ec31dfac/llms.txt): $0.142844/call via x402. Run DeepSeek V4 Pro chat completions through NVIDIA NIM infrastructure, paid per-call via x402 micropayments in USDC.
- [X402-NVIDIA Llama Guard 4 Safety Classifier](https://www.zero.xyz/c/x402-nvidia-llama-guard-4-safety-classifier-29f2e158/llms.txt): $0.198816/call via x402. Runs NVIDIA NIM Llama Guard 4 content safety classification on text via x402 micropayment, returning safety assessment of model responses or user inputs.
- [X402-NVIDIA Nemotron-3-Super-120B Chat Completions](https://www.zero.xyz/c/x402-nvidia-nemotron-3-super-120b-chat-completions-a44f604f/llms.txt): $0.104101/call via x402. Runs inference on NVIDIA's Nemotron-3-Super-120B large language model via x402 micropayment-gated API, returning chat completion responses.
- [X402-NVIDIA Mistral Medium 3.5 Chat Completions](https://www.zero.xyz/c/x402-nvidia-mistral-medium-3-5-chat-completions-5aeae3db/llms.txt): $0.18977/call via x402. Runs chat completions via Mistral Medium 3.5 hosted on NVIDIA NIM, paid per-call using x402 USDC micropayments
- [NVIDIA Nemotron-3.5 Content Safety via X402](https://www.zero.xyz/c/nvidia-nemotron-3-5-content-safety-via-x402-b1abcacd/llms.txt): $0.102481/call via x402. Runs NVIDIA's Nemotron-3.5 content safety model to classify and moderate text content, paid per-call via x402 micropayments.
- [X402-NVIDIA Mistral Small 4 Chat Completions](https://www.zero.xyz/c/x402-nvidia-mistral-small-4-chat-completions-f02f7794/llms.txt): $0.069574/call via x402. Run Mistral Small 4 chat completions via NVIDIA NIM, paid per-call with x402 micropayments in USDC
- [X402-NVIDIA Gemma-3N-E2B Chat Completions](https://www.zero.xyz/c/x402-nvidia-gemma-3n-e2b-chat-completions-d4f62d36/llms.txt): $0.156686/call via x402. Run inference on Google's Gemma-3N-E2B model via NVIDIA NIM, paid per-call with USDC micropayments using the x402 protocol
- [NVIDIA Nemotron Safety Reasoning API via x402](https://www.zero.xyz/c/nvidia-nemotron-safety-reasoning-api-via-x402-fb517934/llms.txt): $0.157979/call via x402. Runs NVIDIA's Nemotron safety reasoning model to evaluate content for safety, policy compliance, and reasoning via micropayment-gated API
- [X402-NVIDIA Solar-10-7B Chat Completions](https://www.zero.xyz/c/x402-nvidia-solar-10-7b-chat-completions-5a2fa71d/llms.txt): $0.103606/call via x402. Runs chat completions using NVIDIA NIM's Solar-10-7B model, billed per-call via x402 USDC micropayments
- [X402-NVIDIA DiffusionGemma 26B API](https://www.zero.xyz/c/x402-nvidia-diffusiongemma-26b-api-1ef231e5/llms.txt): $0.097633/call via x402. Run NVIDIA NIM DiffusionGemma 26B inference via x402 micropayments, returning chat-style completions from this diffusion-based language model.
- [X402-NVIDIA NIM AI Models API](https://www.zero.xyz/c/x402-nvidia-nim-ai-models-api-a0521529/llms.txt): $0.110057/call via x402. Access 48+ NVIDIA NIM AI models (chat, vision, safety, translation) via x402 micropayments at $0.11 USDC per call
- [X402-NVIDIA DeepSeek V4 Flash via NIM](https://www.zero.xyz/c/x402-nvidia-deepseek-v4-flash-via-nim-e11c92da/llms.txt): $0.180626/call via x402. Run DeepSeek V4 Flash chat completions via NVIDIA NIM, paid per-call with x402 USDC micropayments
- [X402-NVIDIA Kimi-K2 Chat Completions API](https://www.zero.xyz/c/x402-nvidia-kimi-k2-chat-completions-api-88d3f124/llms.txt): $0.119526/call via x402. Access the Kimi K2 language model via x402 micropayment-gated chat completions, returning assistant message responses.
- [X402-NVIDIA GPT-OSS-20B NIM API](https://www.zero.xyz/c/x402-nvidia-gpt-oss-20b-nim-api-709d79a8/llms.txt): $0.135323/call via x402. Runs inference on the NVIDIA NIM GPT-OSS-20B model via x402 micropayments, returning chat completion responses.
- [X402-NVIDIA SEED-OSS-36B Model API](https://www.zero.xyz/c/x402-nvidia-seed-oss-36b-model-api-4b44d2ff/llms.txt): $0.140517/call via x402. Runs inference on the NVIDIA NIM SEED-OSS-36B model via x402 micropayments, returning chat completion responses.
- [X402-NVIDIA Stockmark-2-100B Chat Completions](https://www.zero.xyz/c/x402-nvidia-stockmark-2-100b-chat-completions-81739c88/llms.txt): $0.152316/call via x402. Runs inference on the Stockmark-2-100B large language model via NVIDIA NIM, billed per call using x402 USDC micropayments
- [X402-NVIDIA Sarvam-M via NIM API](https://www.zero.xyz/c/x402-nvidia-sarvam-m-via-nim-api-eac35d65/llms.txt): $0.132956/call via x402. Run inference on Sarvam-M via NVIDIA NIM, paid per-call with x402 USDC micropayments, returning chat completion responses.
- [NVIDIA NIM Riva Translate API via x402](https://www.zero.xyz/c/nvidia-nim-riva-translate-api-via-x402-806b9081/llms.txt): $0.141604/call via x402. Translates text between languages using NVIDIA's Riva NIM model, billed per-call via x402 micropayments.
- [X402-NVIDIA MiniMax-M3 Chat Completions API](https://www.zero.xyz/c/x402-nvidia-minimax-m3-chat-completions-api-7ac0261d/llms.txt): $0.173231/call via x402. Access the MiniMax-M3 AI model via x402 micropayments for chat completions, returning assistant message responses.
- [X402-NVIDIA Synthetic Video Detector](https://www.zero.xyz/c/x402-nvidia-synthetic-video-detector-18c72df6/llms.txt): $0.10718/call via x402. Detects whether a video was synthetically generated or AI-created using NVIDIA NIM models, paid via x402 micropayments
- [X402-NVIDIA MiniMax-M2 Chat Completions](https://www.zero.xyz/c/x402-nvidia-minimax-m2-chat-completions-308940f5/llms.txt): $0.13657/call via x402. Runs inference on NVIDIA NIM's MiniMax-M2 model via x402 micropayment, returning chat completions.
- [X402-NVIDIA NIM AI Models API – Streaming Chat Completions](https://www.zero.xyz/c/x402-nvidia-nim-ai-models-api-streaming-chat-completions-e3ab9d1d/llms.txt): $0.082553/call via x402. Streams AI chat completion responses from NVIDIA NIM models via x402 micropayment-gated API endpoint
- [X402-NVIDIA GLM-4 Chat Completions via Micropayment](https://www.zero.xyz/c/x402-nvidia-glm-4-chat-completions-via-micropayment-5cc3ce43/llms.txt): $0.159018/call via x402. Access NVIDIA NIM's ZhipuAI GLM-4 language model for chat completions via x402 micropayment at $0.159018 USDC per call
- [X402-NVIDIA Active Speaker Detection API](https://www.zero.xyz/c/x402-nvidia-active-speaker-detection-api-f07aa1fb/llms.txt): $0.131141/call via x402. Detects active speakers in audio or video content using NVIDIA NIM AI models, accessed via x402 micropayments.
- [X402-NVIDIA Ising Calibration via NVIDIA NIM](https://www.zero.xyz/c/x402-nvidia-ising-calibration-via-nvidia-nim-ab4f2648/llms.txt): $0.192562/call via x402. Runs an Ising model calibration job through NVIDIA NIM AI infrastructure, paid via x402 micropayments

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

- [Zero catalog index](https://www.zero.xyz/llms.txt)