Collection of Free AI API ProvidersCompiled list of free-tier AI routers/APIs — daily resets, free credits, and model access
Note: Providers requiring Telegram should be signed up with a separate Telegram account per provider to avoid cross-linking and spam.
Tier 1 — Best Value (No account gimmicks, high limits)1. Google AI Studio (Gemini)
You do not have permission to view the full content of this post. Log in or register now.
- Models: Gemini 2.5 Flash, Gemini 3 Flash, Gemini 3.5 Flash, Gemini 2.5 Flash Lite, Gemini 3.1 Flash Lite (250k tokens each model)
2. Cloudflare Workers AI
You do not have permission to view the full content of this post. Log in or register now.
- Use on 9router/omnirouter
- Models: OpenAI, Kimi, Qwen, GLM
3. Logfare
You do not have permission to view the full content of this post. Log in or register now.
- Models: DeepSeek, GLM, Kimi, Kiro, MiniMax, Qwen
4. Hcnsec
You do not have permission to view the full content of this post. Log in or register now.
- Models: DeepSeek, Qwen, GLM, Kimi + more
5. OpenRouter
You do not have permission to view the full content of this post. Log in or register now.
- Models: You do not have permission to view the full content of this post. Log in or register now.
Tier 2 — Solid Free Credits (Needs GitHub)6. Bluesmind
You do not have permission to view the full content of this post. Log in or register now.
- Requires GitHub account
- Models: Kimi, GLM, Qwen, Gemini, OpenAI, Anthropic, DeepSeek + more (check model success rate)
7. Helpcoder
You do not have permission to view the full content of this post. Log in or register now.
- Requires GitHub account
- Models: OpenAI
- Note: Errored during testing
8. Agent Router
You do not have permission to view the full content of this post. Log in or register now.
- Requires GitHub account
- Only works with coding agents (You do not have permission to view the full content of this post. Log in or register now.) — cannot be routed
- Models: OpenAI, Claude, GLM, Kimi (better performance at night)
Tier 3 — Free Credits (Needs Telegram — use separate account)9. Conduit
You do not have permission to view the full content of this post. Log in or register now.
- Requires Telegram
- Models: OpenAI, Claude, Meta, Grok, Kimi, Mistral
10. Nara Router
You do not have permission to view the full content of this post. Log in or register now.
- Requires Telegram
- Models: DeepSeek, Laguna, Mistral, Agnes, Nemotron
11. Quickaitool
You do not have permission to view the full content of this post. Log in or register now.
- Requires Telegram
- Models: OpenAI, Claude
Tier 4 — Smaller/Misc Free Credits
12. Free Token Faucet
You do not have permission to view the full content of this post. Log in or register now.
- Models: GLM, Qwen, Kimi, OpenAI, Claude, DeepSeek, MiniMax, Mimo
13. Riftai
You do not have permission to view the full content of this post. Log in or register now.
- Models: GLM, Qwen, Gemini, OpenAI, Claude, DeepSeek
14. Ai-router
You do not have permission to view the full content of this post. Log in or register now.
- Models: Claude, OpenAI
15. Livrouter
You do not have permission to view the full content of this post. Log in or register now.
- Models: DeepSeek, Claude, OpenAI, GLM, Grok
16. Kimchi Dev
You do not have permission to view the full content of this post. Log in or register now.
- Use on 9router
Recommended: Use a Router/AggregatorInstead of juggling separate API keys and endpoints for each provider above, point them all through a self-hosted or third-party router. One OpenAI-compatible endpoint, automatic fallback when a provider's free quota runs out, and unified usage tracking.
Bifrost
You do not have permission to view the full content of this post. Log in or register now.
9router
You do not have permission to view the full content of this post. Log in or register now.
Omnirouter
Similar concept to 9router — aggregates multiple free-tier providers (e.g. Cloudflare Workers AI) behind a single unified endpoint.
Why bother:
- One API key/endpoint in your app instead of N
- Automatic failover when a provider hits its daily free-tier cap
- Centralized logging/metrics (token usage, success rate per provider)
- Easier to swap/rotate providers without touching app code