One endpoint for
every major model, everywhere.
Broad model coverage — DeepSeek, Kimi, GLM, MiniMax and the world's top frontier models — through one drop-in API. Enterprise team management, usage-based billing, balance never expires, Alipay & WeChat Pay supported.
$ curl https://omnirouter-api.cc/v1/messages \ -H "authorization: Bearer $OMNI_KEY" \ -d '{ "model": "deepseek-v4-pro", "max_tokens": 1024, "messages": [{ "role": "user", "content": "Ship it." }] }'
Unified access to
Plug into the tools you already ship with
Drop OmniRouter behind your favourite AI coding agents — one key powers them all.
OpenClaw
A local AI agent that runs on your own machine — executing real tasks through chat, not just conversation.
OPEN SOURCE · LOCAL
Claude Code
Anthropic's official CLI with native Extended Thinking — coding that feels like a conversation.
BY ANTHROPIC
Codex
OpenAI's coding agent — large-scale refactors, bug fixing, and test generation, stable on long tasks.
BY OPENAI
Gemini CLI
Google's open-source terminal agent — invoke Gemini for coding, debugging, and workflow automation.
BY GOOGLE
Broad model coverage, transparent pricing
Every model — from DeepSeek and Kimi to the world's top frontier models — with competitive rates. Billed to the token, balance never expires.
PAYGO
Pay As You Go
No subscription. Top up and spend across every model.
- Top up, spend across every model
- Pay only for what you use
- Balance never expires
RECOMMENDED
Chat On-Demand
Usage-based access tuned for conversational AI workflows.
- Synced with official pricing
- Coverage of the world's top chat models
- Optimized for coding-agent CLIs
RECOMMENDED
Coding On-Demand
Flexible, usage-based billing for AI coding agents.
- Synced with official pricing
- Coverage of the world's top coding models
- Optimized for agent workflows
Daily credits, every model
Monthly or annual plans give you a fixed pool of credits that refills every day at 08:00 (Beijing). Full daily utilization delivers our lowest effective per-token rate.
Lite
10,000 credits / day
Resets daily · fixed daily allowance · all models
Pro
30,000 credits / day
Resets daily · fixed daily allowance · all models
Max
65,000 credits / day
Resets daily · fixed daily allowance · all models
Ultra
135,000 credits / day
Resets daily · fixed daily allowance · all models
Need more on a busy day? Top up with credit packs from $1.
View all plansAI infrastructure built for teams, anywhere
Broad model coverage across regions. Enterprise team management, seat allocation, usage tracking — professional, stable, compliant.
Broad Model Coverage
DeepSeek, Kimi, GLM, MiniMax and the world's top frontier models — every major model behind one endpoint with competitive pricing.
Enterprise Team Management
Seat allocation, member management, invite codes for bulk onboarding — built for enterprise collaboration.
Usage Tracking & Token Billing
Pay only for what you use, down to the request — balance never expires. 30-day summaries, per-member grouping and real-time cost monitoring keep finances under control.
One-Line Integration
Swap the base URL. No rewrites — fully OpenAI & Anthropic wire-compatible out of the box.
Global Edge Acceleration
Stable access worldwide with intelligent routing, automatic failover ensures high availability.
2K / 4K Image Generation
gpt-image-2 generates crisp images up to 2048×2048 and 4096×4096 — the larger the size, the higher the resolution.
Launch your own AI gateway in one click
Own domain, own brand, own pricing — a complete SaaS distribution system out of the box.
One-click launch
Own domain with automatic TLS — spin up your own AI gateway in minutes.
Multi-tier distribution
Main site → distributor → sub-agent — cascade distribution with transparent commission settlement.
Unified control
Top-up, one-click upgrade, disable, and real-time container status — all from the main site.
Frequently asked questions
Broad coverage of frontier and specialist models: DeepSeek V4 Pro/Flash, Kimi K3/K2.7/K2.6, Zhipu GLM 5.3/5.2/5.1, MiniMax M3/M2.7/M2.5, plus the world's top frontier models. New flagships are added once we've validated compatibility.
Every model — regardless of provider or region — is priced at competitive rates below list. All models billed by token in real time. Enterprise customers can contact us for custom pricing. See the pricing page for details.
Complete enterprise team management: seat allocation (configurable by tier), bulk member addition, self-service invite codes, 30-day usage summaries, per-member cost tracking. Enterprise admins can view all member usage and flexibly control seat allocation.
Contact us to set up an enterprise account. After configuring seat tiers, enterprise admins can bulk add members (by user_id) or generate invite codes for distribution. Members are automatically assigned seats upon joining, with usage consolidated to enterprise billing.
Privacy first. Your requests and responses are used solely to relay calls to the upstream models in real time — we never retain your sensitive data, and never resell it or use it for model training. Everything travels through an encrypted tunnel, safeguarding your data at both the technical and policy level.
Never. Top up once and the balance stays until you spend it. Pay only for the tokens you actually use, down to the request.
Ready to accelerate your team's AI?
Join hundreds of teams worldwide managing AI usage with OmniRouter. One key. Every major model. Enterprise-grade management.