# MapleAI Autonomous Agent Execution

> MapleAI Autonomous Agent Execution is a paid API for AI agents from sol.mapleai.shop, paid per call via x402, $0.0065/call, status unknown (last checked 2026-10-22).

Executes multi-step autonomous AI agent tasks with tool access (web search, code execution, URL fetching, data analysis) using either a cheap OSS or premium GPT-6-SOL engine, with optional SSE streaming of step events.

## Facts

- Endpoint: POST https://sol.mapleai.shop/v1/agents/execute?utm_source=zero.xyz
- Price: $0.0065/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/mapleai-autonomous-agent-execution-d0805f96
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_RxD6E32mYe5jVL7buQOM2

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

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability mapleai-autonomous-agent-execution-d0805f96 -d '<json body>'
```

Example prompt: Use the premium gpt-6-sol engine to research the top 5 open-source LLMs released in 2024, write a Python script that scores them by GitHub stars, run that code, and give me a ranked summary — stream the steps as you go, and allow up to 15 reasoning steps with web_search and code_exec tools enabled.

## When to prefer this

Choose this endpoint when the user's request requires multiple sequential reasoning steps, tool use (web search, code execution, URL fetching, data analysis, or calculation), or autonomous decision-making across steps — rather than a single-shot LLM completion. Prefer oss-20b for cost-sensitive tasks and gpt-6-sol for complex, high-accuracy needs. Use stream=true when you need to show progress to a user in real time. This is the right endpoint over a simple chat completion when the task cannot be answered in one inference call and requires tool orchestration.

## Known failure modes

- Task exceeds max_steps limit (20 max) — agent stops and returns partial result
- code_exec quota exceeded — max 3 sandboxed code calls per task; additional calls are blocked
- Invalid tool name in tools array — returns validation error
- Model enum mismatch — only 'agents/oss-20b' or 'agents/gpt-6-sol' accepted
- Payment failure — x402 payment not accepted or insufficient USDC balance
- SSE stream disconnected mid-task — partial steps may be lost
- Task too ambiguous for agent to make progress — returns low-confidence or empty answer
- fetch_url tool blocked by target site — step fails with fetch error

## How this service works

Autonomous agent execution (multi-step reasoning + tools). Engines: cheap agents/oss-20b or premium agents/gpt-6-sol; stream=true streams SSE step events. Ceiling = engine base + max_steps x step + code_exec calls ($0.002 each, max 3 per task) (charged_ceiling_usd).

## Output

Returns a structured payload containing the final answer, all intermediate reasoning and tool-call steps, the model used, total steps taken, and the charged ceiling in USD. When stream=true, delivers Server-Sent Events with 'open', 'step' (per completed reasoning/tool step), and 'done' (with full payload) event types in real time.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "task": {
   "type": "string",
   "description": "Natural language task for the agent"
  },
  "model": {
   "enum": [
    "agents/oss-20b",
    "agents/gpt-6-sol"
   ],
   "type": "string",
   "description": "Execution engine: cheap oss-20b or premium gpt-6-sol"
  },
  "tools": {
   "type": "array",
   "items": {
    "enum": [
     "calculator",
     "fetch_url",
     "web_search",
     "data_analysis",
     "code_exec"
    ],
    "type": "string"
   },
   "description": "Allowed tools, defaults to the enabled set; code_exec runs sandboxed python/javascript/typescript, $0.002 per call, max 3 per task"
  },
  "stream": {
   "type": "boolean",
   "default": false,
   "description": "When true, send SSE events: open, step per completed step, done with the full payload"
  },
  "context": {
   "type": "string",
   "description": "Additional data or constraints"
  },
  "max_steps": {
   "type": "integer",
   "default": 8,
   "maximum": 20,
   "minimum": 1,
   "description": "Charged ceiling of reasoning/tool steps"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mapleai-autonomous-agent-execution-d0805f96/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sol.mapleai.shop](https://www.zero.xyz/host/sol.mapleai.shop/llms.txt)