# Aayat AI – AI Model Picker > Aayat AI – AI Model Picker is a paid API for AI agents from aayatai.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-02). Recommends and ranks AI models from OpenRouter based on task description, required features, token budget, and quality tier ## Facts - Endpoint: POST https://aayatai.com/ai/models/pick?utm_source=zero.xyz - Price: $0.01/call - Payment: x402 - Status: unknown - Last checked: 2026-10-02 - Activations on Zero: 0 - Tags: x402 - Canonical page: https://www.zero.xyz/c/aayat-ai-ai-model-picker-8e5c7411 - Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LX-cqCX7Xl_k2e3wd8c3u 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 aayat-ai-ai-model-picker-8e5c7411 -d '' ``` Example prompt: Find me the best balanced model for a task that reads images and returns structured JSON data — I'm expecting about 3000 input tokens and 400 output tokens per call, and I need vision and JSON support. Return the top 5 options. ## When to prefer this Use this endpoint when an AI agent needs to programmatically select the optimal LLM for a subtask — especially when balancing cost, capability (vision, tools, reasoning, JSON), and context window requirements. Prefer over manually hardcoding a model name, or when the best model may change over time. Ideal for agentic coding assistants, multi-model routing systems, or cost-optimization layers. No API key or account required — pay per call with USDC on Base or Solana. ## Known failure modes - Invalid or unsupported feature name in 'needs' field returns an error - Overly restrictive filters (provider + features + context) may return zero candidates - Payment failure via x402 if insufficient USDC balance on Base or Solana - Task description too vague may result in poor AI-inferred feature matching - minContext value exceeding available model limits returns empty candidate list ## How this service works Cheapest AI model that can do your job. Describe the task (or list needed features: tools, json, reasoning, vision...), expected input/output tokens and a quality level (budget/balanced/best); get the cheapest suitable models across all major providers with estimated USD cost per call and per 1,000 calls, from live prices. POST {task, inputTokens, outputTokens}. ## Output Returns a ranked list of AI models (up to 50) from OpenRouter, each with name, provider, input/output pricing per million tokens, context length, supported features, estimated cost per call, and a top recommended model with a full explanation of how requirements were derived and matched. ## Request schema (JSON Schema) ```json { "type": "object", "properties": { "task": { "type": "string", "maxLength": 1000, "description": "What the model must do, in plain words. An AI reads it to work out the needed features and quality." }, "limit": { "type": "integer", "default": 10, "maximum": 50, "minimum": 1, "description": "How many ranked models to return." }, "needs": { "type": "string", "maxLength": 100, "description": "Comma list of required features (added to any the task implies): tools, json, reasoning, vision, audio, files, web-search." }, "quality": { "enum": [ "budget", "balanced", "best" ], "type": "string", "default": "balanced", "description": "budget, balanced or best. If a task is given, the AI's judgement is used unless you set this to something other than balanced." }, "providers": { "type": "string", "maxLength": 200, "description": "Only these providers, comma separated (e.g. anthropic,openai)." }, "minContext": { "type": "integer", "maximum": 100000000, "minimum": 0, "description": "Minimum context window (default: input + output tokens)." }, "includeFree": { "type": "boolean", "default": false, "description": "Include free, rate-limited variants." }, "inputTokens": { "type": "integer", "default": 2000, "maximum": 10000000, "minimum": 1, "description": "Typical input (prompt) tokens per call." }, "outputTokens": { "type": "integer", "default": 500, "maximum": 1000000, "minimum": 1, "description": "Typical output tokens per call." } } } ``` ## Response schema (JSON Schema) ```json { "type": "json", "example": { "method": "Hard filters (features, context, output limit, provider), a price-based quality floor, then cheapest estimated cost per call.", "source": "OpenRouter", "fetchedAt": "2026-09-28T12:00:00.000Z", "candidates": [ { "id": "google/gemini-2.5-flash", "free": false, "name": "Google: Gemini 2.5 Flash", "created": "2025-06-17", "features": [ "tools", "json", "reasoning", "vision", "audio", "files" ], "provider": "google", "inputPerMTok": 0.3, "contextLength": 1048576, "outputPerMTok": 2.5, "perRequestUsd": 0, "inputModalities": [ "text", "image", "file", "audio" ], "knowledgeCutoff": null, "maxOutputTokens": 65535, "cachedInputPerMTok": 0.075, "estimatedCostPerCallUsd": 0.0019 } ], "considered": 458, "recommended": { "id": "google/gemini-2.5-flash", "free": false, "name": "Google: Gemini 2.5 Flash", "created": "2025-06-17", "features": [ "tools", "json", "reasoning", "vision", "audio", "files" ], "provider": "google", "inputPerMTok": 0.3, "contextLength": 1048576, "outputPerMTok": 2.5, "perRequestUsd": 0, "inputModalities": [ "text", "image", "file", "audio" ], "knowledgeCutoff": null, "maxOutputTokens": 65535, "cachedInputPerMTok": 0.075, "estimatedCostPerCallUsd": 0.0019, "estimatedCostPer1000CallsUsd": 1.9 }, "requirements": { "needs": [ "json", "vision" ], "reason": "Reads images and returns structured data.", "quality": "balanced", "minContext": 3400, "inputTokens": 3000, "outputTokens": 400 } } } ``` ## More - Live health (JSON, refreshed every minute): https://www.zero.xyz/c/aayat-ai-ai-model-picker-8e5c7411/health.json - [Zero catalog index](https://www.zero.xyz/llms.txt) - [Other services from aayatai.com](https://www.zero.xyz/host/aayatai.com/llms.txt)