// I want to solve · Developers / Small teams & business / Enterprise IT / Individuals
💸 Control AI costs and usage limits
See what Claude Code, Codex and API calls actually use, set budgets and rate limits for a team, and route requests to cheaper models when it makes sense.
5 steps3 alternatives1 stacks · 2 problemschecked 2026-10-22
How to do it
- 01See where money goes: ccusage for coding-agent subscriptions, vendor consoles or a gateway dashboard for APIs
- 02Individuals: compare your real usage under a subscription versus pay-as-you-go API and pick the cheaper
- 03Teams: deploy LiteLLM or use OpenRouter, issue keys per person/project with budgets and limits
- 04Route simple tasks to cheap models and reserve flagships for hard ones
- 05Turn on prompt caching to avoid paying repeatedly for long context
What it costs
Free start
ccusage, LiteLLM and Portkey open source are free
Pay as you go
Model prices differ by tens of times; see the pricing page
Team / enterprise
Hosted gateway and observability team plans per vendor sites
Prices change; the vendor’s official page wins. Subscriptions compared · API prices
Alternatives: which to pick
| Option | Choose it when |
|---|---|
| LiteLLM | Self-hosted gateway with the fullest budgets and limits |
| OpenRouter | No ops, one key for many vendors |
| ccusage | Track Claude Code usage |
✓ Good fit
- Opaque bills and frequent rate limits
✗ Not a good fit
- Occasional individual users
Ready-made stacks
All stacksSoftware that helps
All software🔀 Model gateways, routing & usage
litellm Model gateways, routing & usagev1.104.2 ★ 62k The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] Open source SDKAPI new-api Model gateways, routing & usagev1.0.0-rc.46 ★ 50k A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. Open source API kong Model gateways, routing & usage3.9.3 ★ 44k 🦍 The API and AI Gateway Open source API claude-code-router Model gateways, routing & usagev3.1.3 ★ 38k One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control. Open source CLI apisix Model gateways, routing & usage3.19.0 ★ 17k The Cloud-Native API Gateway and AI Gateway Open source API Portkey-AI/gateway Model gateways, routing & usagev1.15.2 ★ 13k A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API. Open source API higress Model gateways, routing & usagev2.2.5 ★ 9.5k 🤖 AI Gateway | AI Native API Gateway Open source API bifrost Model gateways, routing & usagev2.2.6 ★ 9.0k Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS. Open source API agentgateway Model gateways, routing & usagev1.6.0 ★ 5.2k Next Generation Agentic Proxy for AI Agents and MCP servers Open source API any-llm Model gateways, routing & usage1.33.0 ★ 2.2k Communicate with an LLM provider using a single interface Open source SDK ai-gateway Model gateways, routing & usagev0.2.0-beta.30 ★ 636 The fastest, lightest, and easiest-to-integrate AI gateway on the market. Fully open-sourced. Open source API Alibaba Cloud Model Studio (Bailian) Model gateways, routing & usage Closed / commercial OpenRouter Model gateways, routing & usage Unified API gateway to hundreds of models with pay-as-you-go billing. Closed / commercial Freemium WebAPI Volcengine Ark / AI Gateway Model gateways, routing & usage Closed / commercial Cloudflare AI Gateway Model gateways, routing & usage Closed / commercial ccusage Model gateways, routing & usage Open spec TrueFoundry Model gateways, routing & usage Closed / commercial rtk Model gateways, routing & usagev1.0.1 ★ 84k CLI proxy that cuts LLM token use 60–90% on common dev commands. Open source CLI OmniRoute Model gateways, routing & usage ★ 77k Free MIT AI gateway to 290+ providers and 500+ models. Open source API headroom Model gateways, routing & usage ★ 77k Compresses tool outputs and RAG chunks before they hit the LLM. Open source CLIproxyMCP free-claude-code Model gateways, routing & usage ★ 61k Routes free model quotas into Claude Code, Codex and other harnesses. Open source proxy CLIProxyAPI Model gateways, routing & usagev8.0.23 ★ 56k Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Series, Claude model through API Open source API freellmapi Model gateways, routing & usagev0.16.7 ★ 39k OpenAI-compatible proxy stacking free tiers of 16 LLM providers. Open source API one-api Model gateways, routing & usagev0.6.10 ★ 37k LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI. Open source API
Problems & solutions
All problems- How-toHow much have Claude Code / Codex used and cost?Usage windows and limits on subscription tools are opaque, and API calls are scattered. Local log analysers and a unified gateway are the two main approaches.
- How-toSet budgets and rate limits for a team’s LLM usageRoute every model call through one gateway, issue virtual keys per person or project, and enforce budgets, rate limits and model allow-lists there.
Needs in this scenario
-
DEV-01Usage limits and costs are invisible and hard to estimate
Developers · People search for: claude code usage limit; track llm token cost; ccusage
-
IND-02Keeping total subscription cost down (self-paying users)
Individual developers & researchers · People search for: cursor vs claude pro worth it; cheapest ai coding setup
-
ENT-04Transparent TCO and residency matrix
Enterprise IT · People search for: llm observability pricing; ai gateway tco
Learn
All tutorials- 阿里云百炼 文档
阿里云 · Using AI tools · Chinese