{"uid":"cap_146ylqMCiuevO0JL3w44Q","slug":"intel-memoryapi-org-478fb681","name":"AgentIntel LLM Provider Recommender","description":"x402-powered LLM provider intelligence API. Get recommendations, capability data, and status for AI agent routing decisions. Pay per query in USDC on Base mainnet.","url":"https://intel.memoryapi.org/x402/intel/recommend","method":"GET","headers":{},"bodySchema":{"properties":{"input":{"required":["method"],"properties":{"method":{"enum":["GET"],"type":"string"}}}}},"responseSchema":{"example":{"task":"tool_calling","success":true,"priority":"quality","recommendations":[{"why":"top agent score (91/100), excellent tool calling (92/100)","name":"Claude 3.5 Sonnet","rank":1,"slug":"anthropic-claude35-sonnet","recommendation_score":89}]}},"example":{"request":{"best_for":"tool_calling","max_price":0.5,"min_context":32000,"tool_calling":"true"},"response":{"task":"general","source":"AgentIntel — LLM Intelligence for AI Agents","success":true,"priority":"balanced","recommendations":[{"why":"low cost ($0.075/M tokens), large context (1000K tokens)","name":"Gemini 1.5 Flash","rank":1,"slug":"google-gemini15-flash","model":"gemini-1.5-flash","company":"Google","pricing":{"input_per_million":0.075,"output_per_million":0.3},"performance":{"context_window":1000000,"first_token_ms":200},"capabilities":{"json_mode":true,"x402_native":false,"tool_calling":true},"recommendation_score":78},{"why":"low cost ($0.15/M tokens)","name":"GPT-4o mini","rank":2,"slug":"openai-gpt4o-mini","model":"gpt-4o-mini","company":"OpenAI","pricing":{"input_per_million":0.15,"output_per_million":0.6},"performance":{"context_window":128000,"first_token_ms":300},"capabilities":{"json_mode":true,"x402_native":false,"tool_calling":true},"recommendation_score":76},{"why":"large context (200K tokens)","name":"Claude 3 Haiku","rank":3,"slug":"anthropic-claude3-haiku","model":"claude-3-haiku-20240307","company":"Anthropic","pricing":{"input_per_million":0.25,"output_per_million":1.25},"performance":{"context_window":200000,"first_token_ms":350},"capabilities":{"json_mode":true,"x402_native":false,"tool_calling":true},"recommendation_score":71}]}},"exampleRequest":{"best_for":"tool_calling","max_price":0.5,"min_context":32000,"tool_calling":"true"},"tags":["x402"],"displayCostAmount":"0.005","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_J01nBoZDb-XPjR_q2Ygs-","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns ranked LLM provider recommendations tailored to a specific agent task, capability requirements, and pricing constraints","exampleAgentPrompt":"Which LLM should I use for my tool-calling agent — I need at least 32k context, support for tool calling, and want to keep costs under $0.50 per million tokens; give me a ranked recommendation with scores and reasoning.","exampleUseCases":[{"title":"Cost-optimized model selection for high-volume","prompt":"I'm running an agent that processes thousands of customer support requests daily and I need the cheapest possible LLM that still supports tool calling and can handle our average 8k token conversations — what should I pick?"},{"title":"JSON mode with affordable latency requirements","prompt":"My agent needs to extract structured data from documents and format responses as JSON, but our users expect sub-second first-token latency — which LLM provider gives me the best speed-to-cost tradeoff?"},{"title":"Extended context for document analysis agents","prompt":"I'm building an agent that summarizes and analyzes entire contract documents up to 100k tokens — what's the most economical LLM I can use that won't break the budget while handling that context size?"}],"resultDescription":"An ordered list of LLM recommendations, each with model name, provider company, input/output pricing per million tokens, context window, first-token latency, supported capabilities (tool calling, JSON mode, x402 native), a numeric recommendation score, and a human-readable explanation of why each model was chosen.","failureModes":["No models match the specified constraints (e.g. max_price too low or min_context too high) — returns empty recommendations list","Invalid parameter types (e.g. non-numeric max_price) — likely 400 Bad Request","Payment not completed via x402 — endpoint returns 402 Payment Required","Service unavailable or provider data stale — may return 503 or partial data"],"whenToPreferThis":"Use this endpoint when an AI agent needs to dynamically select or switch LLMs based on task requirements, budget, or capability needs — especially for tool-calling agents, cost-sensitive deployments, or when building routing logic across multiple model providers. Prefer this over static model lists when you need scored, ranked recommendations with reasoning.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:36:36.751Z","isFirstParty":false}