83% Cheaper than OpenRouter.
Same models. Same OpenAI-compatible API. Up to 6× more tokens per dollar at the $1,000 top-up. From $10.
Pay-as-you-go from $10 · No subscription · Cancel anytime
/>Used by indie builders & AI startups
/>GET STARTED IN 30 SECONDS
Ship in 3 steps.
No subscription. No setup. Drop your API key into your existing OpenAI client and you are done.
Sign up
Email or Google. No credit card to create your account.
Top up & get a key
One $10 top-up unlocks every model — Opus 4.7, GPT-5.5, Gemini 3 Pro, and 50+ more.
Drop into your code
Point any OpenAI SDK at api.zenn.engineering. Anthropic, Gemini, DeepSeek — same endpoint.
curl https://api.zenn.engineering/v1/chat/completions \
-H "Authorization: Bearer ck_..." \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-4-7",
"messages": [
{ "role": "user", "content": "Hello, Opus." }
]
}'No card required to sign up · 50+ models · OpenAI-compatible
/>Unified API for all models, intelligent routing, and output guardrails — built for teams that need reliability, observability, and cost control.
The Enterprise
LLM Platform.
Unified API
One API key for 60+ models — Claude, GPT-5, Gemini, DeepSeek, Qwen, Veo, and more. Text, image, video. No juggling providers, no fragmented billing.
Intelligent Routing
Automatically route requests to the best model for cost, latency, or quality. Smart fallback ensures zero downtime when a provider goes down.
Output Guardrails
Reduce hallucination risk with built-in output validation and guardrails. Automated checks help catch errors before they reach your users.
/>55+ MODELS LIVE
One API.
Every Model.
Claude, GPT-5, Gemini, DeepSeek, Kimi, GLM, Veo, Fish Audio — text, image, video, and audio.
Official provider list prices. One key. One bill. Pay as you go.
Anthropic
4 models| Model | Input / MTok | Output / MTok |
|---|---|---|
Claude Opus 4.7Latest Flagship claude-opus-4-7 | $5.00 | $25.00 |
Claude Opus 4.6Most Intelligent claude-opus-4-6 | $5.00 | $25.00 |
Claude Sonnet 4.6Best Balance claude-sonnet-4-6 | $3.00 | $15.00 |
Claude Haiku 4.5Fastest claude-haiku-4-5 | $1.00 | $5.00 |
OpenAI
4 models| Model | Input / MTok | Output / MTok |
|---|---|---|
GPT-5.5Flagship gpt-5.5 | $5.00 | $30.00 |
GPT-5.4 gpt-5.4 | $5.00 | $22.50 |
GPT-5.3 CodexCodex Top gpt-5.3-codex | $1.75 | $14.00 |
GPT-5.2 gpt-5.2 | $1.75 | $14.00 |
Google Gemini
3 models| Model | Input / MTok | Output / MTok |
|---|---|---|
Gemini 3.1 Pro PreviewLatest Preview gemini-3.1-pro-preview | $4.00 | $18.00 |
Gemini 3 Pro Preview gemini-3-pro-preview | $4.00 | $18.00 |
Gemini 3 Flash PreviewBest Value gemini-3-flash-preview | $0.50 | $3.00 |
DeepSeek / Moonshot / Zhipu
4 models| Model | Input / MTok | Output / MTok |
|---|---|---|
DeepSeek V4 Pro deepseek-v4-pro | $1.74 | $3.48 |
DeepSeek V4 Flash deepseek-v4-flash | $0.14 | $0.28 |
Kimi K2.6 kimi-k2.6 | $0.95 | $4.00 |
GLM-5.1 glm-5.1 | $1.40 | $4.40 |
All prices per million tokens (LLM) or per generation/request (Image/Video/Audio). 1,000,000 credits = $1 USD.
New models added weekly. One API key for everything.
/>Five Tools, One Key
Every AI coding tool.
Unified.
One Zenn API key works across all five tools. Full API call logs, real-time cost and usage dashboards, and per-model performance analytics.
OpenClaw
The fastest-growing AI agent. Configure Zenn as your provider — Claude Sonnet/Opus, Codex, and Gemini 3.0 Pro through one lobster.
//Models: Claude, GPT-5, Gemini, DeepSeek, Qwen + 60 more
~/.openclaw/openclaw.json
{
"models": {
"providers": {
"zenn-claude": {
"baseUrl": "https://zenn.engineering/api/v1",
"apiKey": "ck_YOUR_KEY",
"api": "anthropic-messages",
"models": [
{ "id": "claude-opus-4-7" },
{ "id": "claude-opus-4-6" },
{ "id": "claude-sonnet-4-6" },
{ "id": "claude-haiku-4-5" }
]
},
"zenn-codex": {
"baseUrl": "https://zenn.engineering/api/v1/codex",
"apiKey": "ck_YOUR_KEY",
"api": "openai-responses"
},
"zenn-gemini": {
"baseUrl": "https://zenn.engineering/api/v1/gemini",
"apiKey": "ck_YOUR_KEY",
"api": "openai-completions"
}
}
}
}Claude Code
Drop-in proxy for Claude Code. Same CLI, same models — official provider pricing.
export ANTHROPIC_BASE_URL=https://zenn.engineering/api/v1//Models: Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5
OpenCode
Multi-provider coding agent. Configure once — access every model through one config file.
~/.config/opencode/opencode.json//Models: Claude, GPT-5, Gemini, and more
Codex CLI
Route Codex CLI through Zenn. Latest GPT-5.x at official provider pricing.
export OPENAI_BASE_URL=https://zenn.engineering/api/v1/codex//Models: GPT-5.5, GPT-5.4, GPT-5.3 Codex, GPT-5.2
Gemini CLI
Full Gemini CLI compatibility — preview channel with massive context windows.
export GEMINI_API_BASE_URL=https://zenn.engineering/api/v1/gemini//Models: Gemini 3.1 Pro, Gemini 3 Pro, Gemini 3 Flash
/>Three plans · Bigger top-ups, more tokens per dollar
Bigger top-ups. More usage.
Top up $100 and get 4× tokens ($400 of OpenRouter API usage). Top up $1,000 and get 6× tokens ($6,000 of OpenRouter API usage). Every model burns at the same per-token list price as OpenRouter — no subscriptions.
10M tokens
Pay-as-you-go. Same per-token prices as OpenRouter on every model.
- 20+ frontier LLMs (Claude, GPT, Gemini, …)
- OpenAI-compatible API key
- Per-key spend limits
- Real-time usage analytics
400M tokens
$100 buys $400 of OpenRouter-equivalent API usage on every model.
- All Pro features
- 4× tokens per dollar at top-up time
- Same list price on every model — Claude, GPT, Gemini
- Priority queue + faster routing
6B tokens
$1,000 buys $6,000 of OpenRouter-equivalent API usage. Best rate.
- All Max features
- 6× tokens per dollar at top-up time
- Priority Anthropic Max channel
- Dedicated support + audit-friendly invoicing
//Multipliers apply per top-up. Mix and match — already on Max? Your existing 4× tokens keep their value until they're spent.
See full pricing & model list/>PRICING SHOWDOWN
Same models. 83% off.
Output price per 1M tokens. We sit at parity with provider list price (Anthropic, OpenAI, Google) on a $10 top-up — and discount via the credit multiplier on bigger top-ups.
| Model | OpenRouter | Zenn 1× ($10) | Zenn 4× ($100) | Zenn 6× ($1,000) |
|---|---|---|---|---|
| Claude Opus 4.7 | $75.00 | $75.00 | $18.75 | $12.50 |
| GPT-5.5 | $30.00 | $30.00 | $7.50 | $5.00 |
| Gemini 3 Pro | $18.00 | $18.00 | $4.50 | $3.00 |
| Effective discount | — | — | −75% | −83% |
OpenAI-compatible. Drop in any OpenAI SDK — Anthropic, Gemini, DeepSeek all run on the same /v1/chat/completions.
No subscription. Pay-as-you-go. Credits never expire.
One key for every model. Switch from Opus to GPT-5.5 by changing one string.
//Provider list prices as of 2026-05. OpenRouter charges list + a small fee. Effective per-MTok cost = list price ÷ multiplier.
/>Enterprise
Built for teams
that ship fast.
From startups to growing teams — unified API access, intelligent routing, output guardrails, and developer analytics with enterprise-grade security.
Contact SalesSSO & Access Control
SAML/OIDC single sign-on, role-based access, and audit logs for your entire engineering org.
Intelligent Routing
Auto-route to the fastest or cheapest model. Smart fallback and load balancing for zero-downtime production.
Developer Analytics
Real-time API call logs, cost breakdowns, usage dashboards, and performance metrics per model and per key.
Output Guardrails
Automated output validation and hallucination detection to help improve response quality.
Ready to Ship Faster?
Claude Code, OpenCode, Codex CLI, Gemini CLI, and OpenClaw — all live. Drop in your API key and start coding in seconds.
//Top up $100 → 4× credits ($400 of usage). $1,000 → 6× credits ($6,000 of usage) + priority Anthropic Max routing.