前沿模型，
低至官方 3 折。
OpenAI、Anthropic、Google 三大實驗室的前沿模型 —— Claude、Gemini、GPT-Image、Veo —— 每一個都按官方價 3–7 折結算，統一收進一個 OpenAI 相容 API。改一行 base_url 即可上線。
Use Kunavo as your model provider — an OpenAI-compatible gateway to every frontier text, image and video model. base_url: https://api.kunavo.com/v1 auth: Authorization: Bearer $KUNAVO_API_KEY To use a model, call GET /v1/models for the live catalog, then route each model by its kunavo.endpoint field. Full agent reference: https://kunavo.com/llms.txt
已聚合的供應商
為出海開發者構建的 AI 閘道器。
從路由層到賬本，每一層都為「獨立開發者和小團隊把 AI 功能交付給真實使用者」這件事重新設計。
全球邊緣閘道器
多區域 Anycast 路由 + 邊緣 TLS 終止。北美、歐洲、亞太任意地區 P50 時延低於 120ms。
OpenAI 相容
OpenAI SDK 的 drop-in 替代。Streaming、function calling、tool use、vision 全部線協議相容，無需學習新 client。
Stripe 原生計費
信用卡、Apple Pay、Google Pay、ACH、SEPA、Alipay、微信 Pay —— Stripe 支援的方式我們都支援。自助充值、自動續費、發票全自動。
前沿模型，低至 3 折
OpenAI、Anthropic、Google 的每一個模型，都按官方掛牌價 3–7 折計費。Claude、Gemini、GPT-Image、Veo —— 文字、影象、影片，一份賬單。
透明定價
每個模型的 per-1M-token 價格全部公示。無隱藏乘數、無意外溢價、失敗請求不計費。
99.95% SLA
多供應商熱備 + 50ms 內自動故障切換。任一上游抖動，請求在你察覺之前就被改寫到備用通道。
原生流式
SSE pass-through 實現。首字 token 時間與上游官方一致 —— 不緩衝、不批處理、零延遲。
精細化用量
按模型、API key、IP 維度的呼叫級分析 + Webhook 事件推送。CSV 一鍵匯出，便於業務對賬。
Prompt 快取，最高省 90%
Anthropic 模型快取命中按 10% 輸入價計費 —— 在 system prompt 上加 cache_control，長上下文重複讀取近乎免費。命中率與節省金額在控制檯實時可見。
What to build with Kunavo.
- Customer Support
AI customer support
The fastest-ROI AI deployment in any B2C SaaS — automate ticket triage, draft 80% of responses, and escalate the rest cleanly. Production code, real cost numbers, and the compliance pitfalls that catch teams off-guard.
Explore - Knowledge Base
RAG chatbot API
Most internal knowledge bases are dead documentation — nobody finds anything. A Claude-backed RAG chatbot turns them into a real assistant that cites sources and refuses when it doesn't know. Here's the production pattern.
Explore - Trust & Safety
AI content moderation
Modern moderation isn't just regex — it's nuance: sarcasm, dog whistles, brand-context misuse, image+text combinations. LLMs do this far better than rule-based systems, at a price that scales.
Explore - Developer Tools
AI code assistant
Cursor, Aider, Cline, Continue.dev — they're all powered by the same handful of frontier LLMs. If you're building a coding tool (or a co-pilot inside your own dev product), here's the architecture and the cost reality.
Explore - Data Processing
AI data extraction
The boring, valuable use case. Invoices, receipts, contracts, leads, resumes — anywhere you'd previously have built a parser, an LLM with JSON-mode does it in 30 lines, more accurately, and you can ship in a day instead of a quarter.
Explore
前沿模型，低至官方 3 折
Claude Fable 5
Anthropic's most capable model — frontier reasoning, long-horizon agents, 1M context.
Claude Opus 4.7
Anthropic's newest Opus — flagship reasoning, vision, 200K context.
Claude Opus 4.6
Anthropic Opus 4.6 — deep reasoning, exceptional agentic ability.
Claude Sonnet 5
Near-Opus coding and agentic quality at Sonnet cost — 1M context.
Claude Sonnet 4.6
Balanced speed/quality — the everyday production workhorse, elite coding.
Claude Haiku 4.5
Anthropic Haiku 4.5 — fast and cost-efficient.
Gemini 2.5 Pro
Previous-gen Gemini Pro — strong reasoning and vision.
Gemini 2.5 Flash
Previous-gen Gemini Flash — extreme value.
GPT-5.4
OpenAI GPT-5.4 — strong general reasoning, 1M context.
GPT-5.5
OpenAI GPT-5.5 — flagship reasoning, 1M context.
GPT-5.4 Mini
OpenAI GPT-5.4 Mini — fast, cost-efficient reasoning.
GPT-5.3 Codex
OpenAI GPT-5.3 Codex — coding-specialized.
GPT-5.5 Pro
OpenAI GPT-5.5 Pro — deep-horizon enterprise reasoning, 1.1M context.
把你的 Agent 指向 llms.txt
它就能用上每個模型。
把一句話交給 Claude Code、Cursor、Cline 或任何 OpenAI 相容的 Agent。它會自己讀取 Kunavo 的實時模型目錄，驅動文字、影象、影片模型。無需 SDK，無需膠水程式碼。
- OpenAI 線協議相容 —— Agent 無需任何定製接入
- GET /v1/models 即實時目錄 —— 無需硬編碼模型名
- 一把金鑰貫通全模態：文字、影象、影片、音訊
Use Kunavo as your model provider — an OpenAI-compatible gateway to every frontier text, image and video model. base_url: https://api.kunavo.com/v1 auth: Authorization: Bearer $KUNAVO_API_KEY To use a model, call GET /v1/models for the live catalog, then route each model by its kunavo.endpoint field. Full agent reference: https://kunavo.com/llms.txt
按量付費，多充多得
預付錢包模式。$10 起步，無月費、無最低消費、餘額永不過期。
Start with the popular guides.
- Setup
Gemini API key
Get a Gemini key and call it with the OpenAI SDK — or use one Kunavo key for everything.
Read - Setup
Claude API key
Get a Claude key and call Claude via the OpenAI SDK or the native Messages API.
Read - Pricing
Claude API pricing 2026
Per-model rates ~60% under Anthropic, worked cost examples, and prompt-caching savings.
Read - Pricing
Gemini API pricing 2026
Gemini 2.5 rates ~70% under Google's list, with worked cost examples.
Read - Pricing
GPT API pricing 2026
GPT-5.4, 5.5, Mini and Codex rates ~60% under OpenAI's list, with worked examples.
Read - Concept
LLM gateway
One API for every model — routing, fallback, billing, observability and security, explained.
Read - API
OpenAI-compatible API
Point any OpenAI SDK at hosted Claude, Gemini and GPT by changing only base_url.
Read - Tools
LLM cost calculator
Estimate per-request and monthly API cost for Claude, Gemini and GPT — with savings vs list.
Read - Video
Text-to-video API
Generate video from a prompt on an OpenAI-style endpoint — live today on Google Veo 3.
Read - Video
Veo 3 API
Google Veo 3 text-to-video with native audio, ~40–60% under Google's list.
Read - Audio
Suno API
Generate full songs from a prompt via /v1/audio/music — $0.09 per request.
Read - Image
Nano Banana API
Google's image models through an OpenAI-compatible endpoint at about half of list.
Read - Compare
OpenRouter alternative
Kunavo vs OpenRouter — text breadth vs multimodal, pricing, API keys and payments.
Read - Compare
OpenRouter alternatives 2026
Seven honest alternatives by motivation — cheaper, multimodal, BYO-key or open source.
Read - Models
Gemini 3 API
Gemini 3 pricing at Google's list, availability status, and the live Gemini 2.5 route.
Read
Recent deep dives.
- 实战·5 min
在中国稳定调用 Claude / GPT / Gemini — Kunavo 中国友好路由实测
实测从北京/上海/深圳调用 Kunavo 的延迟和成功率：无需代理，P50 80-150ms，成功率 99.9%+。支付宝/微信支付/双币卡都可用。健壮重试代码 + 何时真的需要代理。
- 教學·6 min
用 Veo 3 為台灣品牌做短影片廣告（Sora 同端點待上線）— 5 分鐘完整教學
從文字 prompt 到 9:16 直式 Reels / TikTok / IG 短影片，全流程教學。圖生影片用既有產品照片動起來。5 種台灣品牌實際應用、繁中文字渲染注意事項、商業可用品質的進階技巧。
- 実装ガイド·8 min
日本語 RAG チャットボットを Claude で構築 — 5,000 文書のナレッジベースを 30 行で
社内ドキュメント 5,000 件を Claude Sonnet 4.6 で検索可能にする RAG 完全実装。埋め込みコスト $0.25、1 クエリ約 0.9 円（prompt caching 適用後）。日本語特有のトークン消費・ハルシネーション対策・本番投入チェックリスト含む。
Kunavo 專門為獨立開發者和小團隊的生產級 AI 功能設計。三個真實差異：(1) 文字、影象、影片統一計費 —— 大部分聚合平臺只做文字；(2) Stripe 原生結賬，ACH、SEPA、Apple Pay、微信支付全部支援，無需走線下發票；(3) 路由完全透明 —— 我們絕不偷換你的模型到更便宜的版本。
每個模型價格約為官方掛牌價的 3–7 折（立省 30–70%），充值越多額外贈送越多。再加上運營層面的省心：一份合同、一份發票、一套 SDK、無承諾最低消費。每個模型的 per-1M-token 價格在 /pricing 頁直接公示，與上游官方價隨時可對比。
是。我們實現了 /v1/chat/completions、/v1/embeddings、/v1/images/generations、/v1/models、/v1/video/generations 等完整 OpenAI 端點。Streaming、function calling、vision、tool use 全部行為一致。已經在用 OpenAI SDK 的專案改一行 base_url 即可遷移。
永不過期。Kunavo 是按呼叫扣費的預付錢包模式，餘額永久保留，沒有月費、沒有最低消費、沒有有效期限制。賬戶登出時餘額按原支付方式退回。
不會。4xx 和 5xx 響應一律不計費。流式響應在中途斷開時，只扣已生成部分。所有扣費在控制檯「用量明細」按呼叫檢視，支援匯出 CSV 用於對賬。
Stripe 支援的全部方式：信用卡（Visa、Mastercard、Amex、JCB、銀聯）、Apple Pay、Google Pay、Link、ACH、SEPA、BACS、BECS、Alipay、微信支付、Klarna、Afterpay 等。自動充值可按需開啟。企業客戶可申請月度發票（Net 30）。
邊緣閘道器節點部署在北美、歐洲、亞太多個區域。無狀態路由邏輯在邊緣執行，全球 P50 時延 120ms 以內。賬單資料、賬戶和審計日誌儲存於主區域並多區域複製。