AI API Router Directory

HyperAgent (hyperagent.com) — fleet-of-AI-agents platform (research, docs, sites, decks, video). Plans convert monthly price 1:1 into spendable credits (up to 45% bonus); agents draw on hosted LLMs (Claude, ChatGPT, Kimi, etc.). Unofficial browser/cookie integration.

Every dollar of plan price returns as credit (1 credit = $1 of model spend); higher tiers add 10-45% bonus. Pay-as-you-go discontinued Aug 2026; top-ups via credit blocks.

GitHub Copilot enterprise plans (Business/Enterprise) - AI coding assistant with AI-credit allowances (1,900 / 3,900 credits per user/mo), model choice across OpenAI, Anthropic, Google and select Moonshot models; Enterprise credits are org-pooled; overage at USD 0.01/credit. Copilot is not currently available for self-hosted GitHub Enterprise Server.

1 AI credit = USD 0.01; overage billed at USD 0.01 per credit.

Cursor is an AI code editor sold on self-serve plans: Hobby is free, the $20/month individual tier (listed as Individual on the pricing page and as Pro in the docs) adds extended Agent limits and frontier models, Pro Plus is $60/month, Ultra is $200/month, and Teams is $40/user/month Standard or $120/user/month Premium with Enterprise as custom. Hobby requires no credit card and lists limited Agent requests and access to Composer. Cursor states there are two usage pools - Cursor Models for Grok 4.6, Grok 4.5 and Composer 2.5, and Other Models for third-party models billed at API price - and that Teams and Enterprise add a $0.25 per million token Cursor Token Rate on third-party model requests.

Cursor Hobby is free with no credit card required, limited Agent requests and access to Composer (cursor.com/pricing, checked 2026-09-16).

Devin, built by Cognition, is an agentic software engineering product spanning Devin Desktop, a CLI, Devin Cloud agents, DeepWiki and the Devin API, aimed at multi-repo engineering work such as migrations, PR review, incident triage and scheduled chores. Its pricing page lists Free at $0 with "a light quota to code with agents", limited model availability, unlimited inline edits and unlimited Tab completions, then Pro at $20/month, Max at $200/month for significantly higher quotas, Teams at $80/month for the team plan plus $40/month per full dev seat, and Enterprise by contact. Paid plans come with a usage allowance that refreshes daily and weekly, and usage beyond the allowance is purchased and consumed at API pricing.

Devin Free is $0 with a light agent quota, limited model availability, unlimited inline edits and unlimited Tab completions (devin.ai/pricing, checked 2026-09-16).

GitHub Copilot is GitHub's AI coding assistant, sold to individuals as Free ($0), Pro ($10/user/month), Pro+ ($39/user/month) and Max ($100/user/month), and to organizations as Business ($19/user/month) and Enterprise ($39/user/month). The Free tier needs no credit card and lists 2,000 completions per month, access to Claude Haiku 4.5 and GPT-5 mini "and more", the Copilot CLI and community support; GitHub's own FAQ on the same page states Free users are limited to 2,000 completions and 50 chat requests per month, including Copilot Edits. Paid individual plans add unlimited code completion and next edit suggestions, cloud agent, code review, delegation to third-party agents (Claude Code and Codex), model selection and monthly GitHub AI Credits of $15 (Pro), $70 (Pro+) and $200 (Max).

GitHub Copilot Free is $0/user/month with 2,000 completions and 50 chat requests per month and no credit card required, stated on github.com/features/copilot/plans and its Free-plan FAQ (checked 2026-09-16).

Open-source local AI router (npm package '9router', MIT license, Next.js, by decolua). Connects CLI coding tools (Claude Code, Codex, Cursor, Gemini CLI, Cline, OpenCode, Antigravity, Copilot and any OpenAI/Claude-compatible client) to 40+ AI providers and 100+ models through a local OpenAI/Claude-compatible endpoint. Features: RTK token compression (20-40% savings on tool results), auto-fallback (subscription -> cheap -> free), multi-account round-robin, web dashboard. Self-hosted; users bring their own upstream accounts/keys. Implementation inspired by CLIProxyAPI.

Software is free (MIT); it routes through user-provided upstream accounts, no credits or prices from the router itself.

Anthropic's Claude API is per-token with no free tier: Fable 5.1 $10/$50, Opus 5 $5/$25, Sonnet 5 $2/$10 and Haiku 4.5 $1/$5 per 1M in/out, with the full 1M-token context at standard pricing on 4.6+, a 50% batch discount, prompt-caching reads at 0.1× input (0.025× on Fable 5.1), 1.1× US-only inference, and itemized server-tool pricing. Consumer plans (Free/Pro/Max) are a separate product.

No free tier on the API (verified 2026-09-16) — first requests bill at per-token rates. The claude.ai Free plan is a separate consumer product with usage limits, not API access.

Open-source Go proxy server (MIT license, router-for-me/CLIProxyAPI) that wraps CLI subscriptions - Google Antigravity/Gemini, OpenAI ChatGPT Codex (GPT series), Anthropic Claude Code, xAI Grok Build, Moonshot Kimi - and exposes them as OpenAI (incl. Responses), Gemini (incl. Interactions), Claude, Codex and Grok compatible API endpoints. OAuth login flows, multi-account round-robin load balancing, streaming/non-streaming/WebSocket, function calling, multimodal input, Management API, and an embeddable Go SDK. Self-hosted; users bring their own upstream accounts/keys. Desktop wrapper: EasyCLIProxyAPI.

Software is free (MIT); access to upstream models depends on user-provided subscriptions/API keys, no credits or prices from the proxy itself.

OAuth access — sign-in with your existing account. Claude Code (Anthropic) 27 models tracked (via OpenRouter catalog).

A free tier is available; the exact credit value is not quantified.

Claude's consumer app is sold on a plan matrix published at anthropic.com/pricing. The Free column includes chat on web, iOS, Android and desktop, Sonnet and Haiku model access, a 200k-token context window, web search, artifacts, memory, skills, connectors, voice mode, incognito chats and file creation and editing through code execution, while Opus, Fable, Claude Code, Projects, Research, Claude in Chrome and the Microsoft 365 and Outlook integrations are all marked as not included. Anthropic states only that usage limits apply and does not publish a numeric message or token cap for the Free plan.

No free tier stated on official pages (checked 2026-09-16) as a credit: the consumer Free plan is a listed plan tier but no allowance or numeric cap is published, and the API docs state only that new API users receive a small amount of free credits without quantifying them.

Juzi AI (api.juziai.cc) is a Chinese commercial-aggregator relay built on the New-API framework. It aggregates high-end models like GPT-5 and Claude Opus by leveraging various upstream account pools, offering pay-as-you-go access to users in mainland China.

Free quota negligible: daily check-in after 10 calls grants 5–20 quota (quota_per_unit=500000 ≈ $1 per 500K quota) → well under $0.01/day; most model_ratio=0 models are pay-per-call. Not quantifiable.

Kiro (AWS) - agentic IDE powered by Amazon Bedrock; credit-based usage: Free (50 credits/mo, rate-limited) plus Pro/Pro+/Pro Max/Power; per-model credit multipliers (e.g. GPT-5.6 Sol 2.4x, Claude Opus 4.5 2.2x, Qwen3 Coder Next 0.05x); USD 20 sign-up bonus on free tier; context windows 200K-1M per model.

Add-on credits approx USD 0.04/credit per third-party (morphllm) - not official AWS pricing; official per-credit USD value not published in fetched sources.

Void AI is an AI API aggregator compatible with the OpenAI SDK. It uses a credit-based billing system where model costs are calculated using multipliers (e.g., GPT-5.1 is 0.75, GPT-4o is 1.25). Offers both flat-rate plans and usage-based top-ups.

No public free-tier information found in the source reference; treat free-tier availability as unverified rather than confirmed absent.