{"uid":"cap__2VgbrzoDA1hwkytfUd70","slug":"api-vectorway-io-6b45e5b5","name":"VectorWay Chat Completions","description":"Pay-per-call OpenAI-compatible chat completions backed by Gemini 2.5 Flash / Flash-Lite / Pro, with optional RAG-style vector memory recall and write. No account needed — pay USDC over x402 per request. Buyer wallet from the signed payment is the memory namespace, so calls from the same wallet share context. Billed per input + output token. The 402 challenge authorizes an upper bound; settlement drops to actual usage.","url":"https://api.vectorway.io/v1/chat/completions","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"enum":["gemini-2.5-flash","gemini-2.5-flash-lite","gemini-2.5-pro"],"type":"string","description":"Gemini tier — billed by real input/output token counts at a fixed discount off Vertex list. Flash-Lite is the cheapest (~3x under Flash), Flash is the balanced default, Pro is the deep- reasoning tier (~4x Flash on input, ~4x on output)."},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"minItems":1,"description":"OpenAI-style chat transcript. Roles are system, user, assistant. The full transcript is sent to Gemini on every call; persistent recall across calls is handled by the optional vector memory below, not by us replaying past messages."},"memory_read":{"type":"boolean","description":"When true, semantically search the buyer's wallet-scoped vector memory before generation and splice the top-k matches into the prompt as RAG context. Memory is partitioned by payer wallet, so successive x402 calls from the same wallet share the same memory namespace."},"temperature":{"type":"number","maximum":2,"minimum":0,"description":"Gemini sampling temperature."},"memory_write":{"type":"boolean","description":"When true, persist a summary of the request+response into the wallet's vector memory after the call returns. Future calls with memory_read=true will find it via similarity search."}}},"responseSchema":{"type":"json","example":{"usage":{"memory_read":true,"memory_write":true,"memories_used":3},"output_text":"Here are the highlights from the meeting..."}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.101838","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","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":"$0.101838/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.101838","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.101838","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_dJAyg75te3LuFoDlnyey3","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.101838","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"OpenAI-compatible chat completions backed by Gemini 2.5 models with optional vector memory, paid per-request via USDC over x402 with no account required.","exampleAgentPrompt":"Ask the Gemini 2.5 Flash model: 'What are the key differences between transformer and diffusion architectures?' — pay per token from my wallet, and store the conversation in my wallet's memory namespace so future calls can recall it.","exampleUseCases":null,"resultDescription":"Returns an OpenAI-compatible chat completion response object containing one or more assistant message choices, token usage breakdown (input + output tokens billed), finish reason, and model identifier. If vector memory recall was enabled, relevant past context from the same wallet's memory namespace is injected into the response context automatically.","failureModes":["402 payment required if no valid x402 USDC payment header is provided","insufficient USDC balance causes payment failure and request rejection","invalid or malformed messages array returns 400 bad request","unsupported model name returns an error indicating available Gemini model variants","wallet signature verification failure rejects the payment and the request","token limit exceeded on input context returns an appropriate error","vector memory write/recall failure may degrade response quality without hard error"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-compatible LLM chat completions without account registration, want to pay per-token in USDC via x402 (ideal for autonomous agents with crypto wallets), need wallet-scoped persistent vector memory so context carries across sessions, or want access to Gemini 2.5 Flash/Pro quality at pay-as-you-go pricing. Prefer it over API-key-based services when deploying agent workflows that must self-fund requests and maintain memory without a backend.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:38:40.831Z","isFirstParty":false}