# AgentToll Media Model Settings Lookup

> AgentToll Media Model Settings Lookup is a paid API for AI agents from agenttoll.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Returns recommended AI model settings for a given model name and optional task type (coding, writing, or analysis)

## Facts

- Endpoint: POST https://agenttoll.dev/paid/media/model-settings
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agenttoll-media-model-settings-lookup-6ecbde0c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eBY2VdAdV-GMMgNIEkwPz

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 agenttoll-media-model-settings-lookup-6ecbde0c -d '<json body>'
```

Example prompt: What are the recommended settings for claude-3.5-sonnet when doing analysis tasks?

## When to prefer this

Use this endpoint when an AI agent needs to quickly look up recommended configuration parameters for a specific LLM by name, especially when the task context (coding, writing, analysis) is known. Prefer this over hardcoded defaults or trial-and-error when building multi-model agent pipelines or LLM orchestration systems.

## Known failure modes

- Unknown model name returns empty or error response
- Invalid task type string may be ignored or cause an error
- Payment failure in USDC results in 402 response and no data
- Response schema is generic object so fields may vary or be missing
- Unrecognized model may return generic or null settings

## How this service works

108+ receipt-backed x402 work products for AI agents. Clear prices, spend caps, buyer metadata, and structured results over Base USDC.

## Output

Returns a JSON object containing recommended configuration and settings for the specified AI model, optionally tuned for a particular task type (coding, writing, or analysis). May include parameters such as temperature, top-p, max tokens, or other model-specific settings.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "task": {
   "type": "string",
   "description": "optional task e.g. image-to-video, face consistency, LoRA training, fp8, ComfyUI workflow"
  },
  "model": {
   "type": "string",
   "description": "string model family e.g. wan, vace, ltx, flux3, seedance, kling, hunyuan, qwen-image"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttoll-media-model-settings-lookup-6ecbde0c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agenttoll.dev](https://www.zero.xyz/host/agenttoll.dev/llms.txt)