Chat Completions

OpenAI-compatible chat completion, one paid call per answer.

Overview

OpenAI-compatible chat completion, one paid call per answer. POST JSON {model, messages, max_tokens?, temperature?, tools?}: model gpt-oss-120b (default), gpt-oss-20b, llama-3.3-70b, llama-3.1-8b or qwen3-30b; up to about 4,000 input tokens and 1,024 output tokens; no streaming. Returns the standard chat.completion object (choices, usage). OpenAI SDKs work with baseURL upstream/api/x402/v1 and an x402-paying fetch. Models run on Cloudflare Workers AI. Bad input, an unknown model, stream:true or a full daily capacity is refused before payment; a paid call the model fails to answer is recorded and refunded. Llama models: Built with Llama.

Endpoint

Method	Endpoint	Price	Description
POST	/v1/marketplace/api/chat-completions-44091	$0.0023	Invoke Chat Completions (Llm) and return the upstream response.

How to call it

Requests are paid per call over the x402 protocol. Call the endpoint, receive a 402 Payment Required quote, then repeat the request with the signed payment header. The SDKs do both steps for you.

# 1. Ask for a quote
curl -i -X POST https://api.jarvisclaw.ai/v1/marketplace/api/chat-completions-44091 \
  -H 'Content-Type: application/json' \
  -d '{}'

# 2. Pay it (the SDK signs and retries for you)
curl -X POST https://api.jarvisclaw.ai/v1/marketplace/api/chat-completions-44091 \
  -H 'Content-Type: application/json' \
  -H 'X-PAYMENT: <signed-payload>' \
  -d '{}'

Open in the marketplace