# Services from ged-x402-llm.jvalamis.workers.dev on Zero

> ged-x402-llm.jvalamis.workers.dev serves 17 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/ged-x402-llm.jvalamis.workers.dev
Live health (JSON, refreshed every minute): https://www.zero.xyz/host/ged-x402-llm.jvalamis.workers.dev/health.json

## Services

- [GEDX402 Llama 3.1 70B Instruct (x402 Pay-Per-Call)](https://www.zero.xyz/c/gedx402-llama-3-1-70b-instruct-x402-pay-per-call-dae6ba63/llms.txt): $0.06/call via x402. Run Llama 3.1 70B Instruct FP8 Fast inference via a pay-per-call x402 endpoint, paying $0.06 USDC per request with no API key required.
- [Qwen2.5-Coder-32B Instruct via x402 (GEDX402)](https://www.zero.xyz/c/qwen2-5-coder-32b-instruct-via-x402-gedx402-36c500fb/llms.txt): $0.05/call via x402. Runs the Qwen2.5-Coder-32B-Instruct large language model on Cloudflare Workers AI, billed per-call in USDC via the x402 payment protocol — no API keys required.
- [GEDX402 Gemma-4-26B LLM via x402](https://www.zero.xyz/c/gedx402-gemma-4-26b-llm-via-x402-359b059d/llms.txt): $0.015/call via x402. Runs inference on Google's Gemma-4-26B-A4B-IT language model, billed per call in USDC via x402 payment protocol — no API keys required.
- [GEDX402 Qwen3-30B-A3B-FP8 LLM via x402](https://www.zero.xyz/c/gedx402-qwen3-30b-a3b-fp8-llm-via-x402-eab42e19/llms.txt): $0.008/call via x402. Runs inference on the Qwen3-30B-A3B-FP8 large language model, billed per call in USDC via x402 with no API key required
- [GEDX402 Gemma Sea Lion v4 27B Instruct (x402 Pay-per-Call)](https://www.zero.xyz/c/gedx402-gemma-sea-lion-v4-27b-instruct-x402-pay-per-call-02adf5af/llms.txt): $0.04/call via x402. Run inference on the Gemma Sea Lion v4 27B instruction-tuned model via a pay-per-call x402 API using USDC on Base, Polygon, Arbitrum, World, or Solana — no API key required.
- [GEDX402 DeepSeek-R1-Distill-Qwen-32B LLM via x402](https://www.zero.xyz/c/gedx402-deepseek-r1-distill-qwen-32b-llm-via-x402-1cc4267d/llms.txt): $0.08/call via x402. Runs inference on DeepSeek-R1-Distill-Qwen-32B (a 32B parameter reasoning model) via Cloudflare Workers AI, paid per-call with USDC on multiple chains, no API key required.
- [GEDX402 Kimi K2.5 LLM via x402](https://www.zero.xyz/c/gedx402-kimi-k2-5-llm-via-x402-6185e52e/llms.txt): $0.1/call via x402. Runs a Kimi K2.5 large language model inference call, billed per-request in USDC via x402 with no API key required
- [GEDX402 Mistral Small 3.1 24B Instruct LLM](https://www.zero.xyz/c/gedx402-mistral-small-3-1-24b-instruct-llm-03fa1c49/llms.txt): $0.04/call via x402. Runs chat completions using Mistral Small 3.1 24B Instruct via Cloudflare Workers AI, paid per-call with USDC on multiple blockchains, no API key required.
- [Kimi K2.7 Code LLM via x402 (USDC, No API Key)](https://www.zero.xyz/c/kimi-k2-7-code-llm-via-x402-usdc-no-api-key-de4a9cb2/llms.txt): $0.12/call via x402. Calls the Moonshot AI Kimi K2.7 code-focused LLM on Cloudflare Workers AI, billed per-call in USDC via x402 with no API key required
- [GEDX402 Kimi K2.6 LLM via x402](https://www.zero.xyz/c/gedx402-kimi-k2-6-llm-via-x402-817c5a0c/llms.txt): $0.12/call via x402. Calls the Moonshot AI Kimi K2.6 large language model, paid per-request with USDC on-chain — no API key required.
- [GEDX402 Nemotron-3-120B LLM via x402](https://www.zero.xyz/c/gedx402-nemotron-3-120b-llm-via-x402-4c0f4fc0/llms.txt): $0.08/call via x402. Runs inference on NVIDIA Nemotron-3-120B-A12B via Cloudflare Workers AI, paid per-call with USDC over x402 protocol — no API keys required.
- [GEDX402 Llama 3.3 70B Instruct (x402 Pay-Per-Call)](https://www.zero.xyz/c/gedx402-llama-3-3-70b-instruct-x402-pay-per-call-1c6478f4/llms.txt): $0.06/call via x402. Runs inference on Meta's Llama 3.3 70B Instruct FP8 Fast model via Cloudflare Workers AI, billed per-call in USDC with no API key required
- [GEDX402 SQLCoder-7B-2 LLM (x402, no API key)](https://www.zero.xyz/c/gedx402-sqlcoder-7b-2-llm-x402-no-api-key-b8627aa3/llms.txt): $0.016/call via x402. Runs Cloudflare Workers AI's SQLCoder-7B-2 text-to-SQL model, billed per-call in USDC via x402 with no API key required.
- [GEDX402 GPT-OSS-20B LLM (x402 Pay-per-Call)](https://www.zero.xyz/c/gedx402-gpt-oss-20b-llm-x402-pay-per-call-8ff3d0a6/llms.txt): $0.025/call via x402. Runs inference on the @cf/openai/gpt-oss-20b model via Cloudflare Workers AI, billed per-call in USDC over x402 with no API key required.
- [GEDX402 GPT-OSS-120B LLM via x402](https://www.zero.xyz/c/gedx402-gpt-oss-120b-llm-via-x402-f5f2c347/llms.txt): $0.05/call via x402. Runs a 120B open-source GPT-class language model inference call, paid per-request with USDC over x402 protocol — no API keys required.
- [GLM-5.2 LLM via x402 (No API Key, USDC Payment)](https://www.zero.xyz/c/glm-5-2-llm-via-x402-no-api-key-usdc-payment-ca90cd6c/llms.txt): $0.12/call via x402. Runs inference on the GLM-5.2 language model hosted on Cloudflare Workers AI, billed per-call in USDC via x402 with no API key required.
- [GEDX402 QwQ-32B LLM Inference (x402, no API key)](https://www.zero.xyz/c/gedx402-qwq-32b-llm-inference-x402-no-api-key-88a523ac/llms.txt): $0.05/call via x402, rated 1.3/5 (1 review). Runs inference on Qwen QwQ-32B via Cloudflare Workers AI, paid per-call with USDC over x402 — no API key required.

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)