default8/6/2026
Notice: The gpt-5.6-luna model has been removed. Please switch to another model.
Lumin AI is an AI API relay service for developers, providing unified access to multiple AI models.
- Models
- 32 models
- From
- $0.060/M
- Speed
- --
- Updated
- 8/3/2026
- Latency
- --
- Created At
- 5/29/2026
- Recharge Rate
- ¥1.00 per $1 quota
Features
TaskData Export
Billing
Payment methods
AlipayWeChat Pay
- Refunds
- Supported
API Endpoints
- Default Route
https://api.luminai.cc/For use in Hong Kong and overseas
- Endpoint 2Historical / Unverified
https://api.luminai.cc - Accelerated Route B
https://vip.luminai.ccAccelerated access for Asia-Pacific and Hong Kong
- Channel Status Monitor
https://status.luminai.ccReal-time channel status
- Endpoint 5Historical / Unverified
https://ai.luminai.cc - Endpoint 6Historical / Unverified
https://js1.luminai.cc
Claim this provider
Verify ownership to unlock provider management features:
- Edit provider name, content, and links
- Get featured with priority traffic and visibility boost
- Display a verified badge to build user trust
Leaderboard Rankings
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
Health Check
0%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 98 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
claude-opus-4-6-thinkingZ-测试分组请勿选择 | $75.00/M | $375.00/M |
codex-auto-review0-Codex-限时福利 | $0.400/M | $2.40/M |
codex-auto-reviewA-Codex-Sale | $0.750/M | $4.50/M |
codex-auto-reviewB-Codex-Plus | $2.00/M | $12.00/M |
codex-auto-review套餐-Codex-套餐专用 | $5.00/M | $30.00/M |
gemini-3-flash-agentZ-测试分组请勿选择 | $75.00/M | $300.00/M |
gemini-3.5-flash-extra-lowZ-测试分组请勿选择 | $75.00/M | $300.00/M |
gemini-pro-agentZ-测试分组请勿选择 | $75.00/M | $300.00/M |
grok-imagineG-Grok-Super | $37.50/M | $37.50/M |
grok-imagine-imageG-Grok-Super | $37.50/M | $37.50/M |
claude-opus-5E-Claude-Main | $2.00/M | $10.00/M |
claude-opus-5E-Claude-Main-Backup | $2.00/M | $10.00/M |
claude-opus-5套餐-Main专用分组 | $5.00/M | $25.00/M |
claude-opus-5H-Claude-混合满血 | $7.50/M | $37.50/M |
claude-opus-5H-Claude-Max | $10.00/M | $50.00/M |
gemini-3.6-flash-highZ-测试分组请勿选择 | $1.50/M | $7.50/M |
gpt-5.6-lunaB-Codex-Plus | $0.400/M | $2.40/M |
gpt-5.6-terra0-Codex-限时福利 | $0.200/M | $1.20/M |
gpt-5.6-terraA-Codex-Sale | $0.375/M | $2.25/M |
gpt-5.6-terraB-Codex-Plus | $1.00/M | $6.00/M |
gpt-5.6-terra套餐-Codex-套餐专用 | $2.50/M | $15.00/M |
gpt-5.6-terra-openai-compactA-Codex-Sale | $0.750/M | $4.50/M |
gpt-5.6-terra-openai-compactB-Codex-Plus | $2.00/M | $12.00/M |
gpt-5.6-terra-openai-compact套餐-Codex-套餐专用 | $5.00/M | $30.00/M |
gpt-5.6-sol0-Codex-限时福利 | $0.400/M | $2.40/M |
Showing 25 of 98 model rows
Recent Test Records
No test records available
Similar API Provider Alternatives to Compare
Compare Lumin AI alternatives against 6 nearby API providers using 225 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| Lumin AI ai-luminai-cc Lumin AI is an AI API relay service for developers, providing unified access to multiple AI models. | Current provider baseline | 32 | 0 | $0.210/M | N/A | 0% |
| Dext API ai-dext-top Dext API is an OpenAI-compatible API relay offering access to 500+ LLM models at competitive prices, with multi-channel routing and broad model coverage. |
| 667 | 219 | $0.017/M | 19 tok/s | 1380% |
| 小水管 API edge-pieixan-icu Pie-Xian (小水管) provides an OpenAI-compatible API relay with multiple endpoints including api.pie-xian.com and edge nodes. |
| 495 | 2 | $0.054/M | 260 tok/s | 9870% |
| ChooseC API ipv4-beta-lm-studio ChooseC API is a unified AI model aggregation gateway supporting 260+ mainstream models including Claude, GPT, Qwen, DeepSeek, Kimi, and GLM with OpenAI, Claude, and Gemini compatibility. |
| 335 | 9 | $0.095/M | 138 tok/s | 9950% |
| VSLLM vsllm-com VSLLM runs a New API-powered AI gateway on vsllm.com for aggregated model access through a single endpoint. |
| 209 | 2 | $0.056/M | 174 tok/s | 9970% |
| Leonhard API codexe-top Leonhard API provides an OpenAI-compatible API gateway at codexe.top for accessing multiple LLM models. |
| 89 | 3 | $0.112/M | 46 tok/s | 6540% |
| Tokeness.io tokeness-cn Tokeness.io is an OpenAI-compatible API relay hub that connects developers to mainstream LLMs including GPT, Claude, and DeepSeek through a single endpoint. |
| 47 | 1 | $0.079/M | 62 tok/s | 10000% |
Announcements
default8/2/2026
Please update your primary domain to: api.luminai.cc and re-bookmark it. The AI primary domain can only be accessed via VPN.
default7/26/2026
Codex limited-time offer: accounts replenished, hurry up and use them. codex-plus group cannot bypass limits. G-Grok-Super is now live, no restrictions, no need to bypass limits, low moral constraints by default.
ongoing7/25/2026
Self-operated grokSuper is now live.
success7/24/2026
Claude full group now includes opus-5.
ongoing7/24/2026
The low-price gpt group is down across all providers. We've just replenished accounts—use them while they last! If they don't work, switch groups.
default7/22/2026
Codex limited-time offer: accounts replenished, you can continue using them.
ongoing7/21/2026
Codex limited-time offer is out of accounts. For urgent use, switch to the sale group. ccmax is down across all providers, high latency.
default7/20/2026
Codex limited-time offer: another batch of accounts added, hurry up and use them. codex-sale and codex-plus groups remain stable. Codex special packages: same as codex-plus group, pure Pro 20x account pool, minimum 0.2x rate. Choose for stability, purity, and value.
default7/16/2026
Today's codex limited-time offer at 0.08x has been replenished. If accounts are exhausted, remember to switch groups.
default7/16/2026
Codex limited-time offer accounts replenished. OpenAI is banning accounts aggressively—if they don't work, don't wait, switch groups.
default7/16/2026
All accounts in the codex limited-time offer group have been banned. Please switch groups promptly to avoid disruption. Codex package special: minimum 0.2x rate, dedicated codex-plus group, pure Pro 20x account pool, limited-time purchase.
ongoing7/15/2026
Codex packages are here! Pure Pro account pool, as low as 0.2x, available for a limited time, then discontinued. Check the subscription packages if interested.
success7/12/2026
To improve speed, we've migrated to high-performance, high-bandwidth servers. Providing stable service is LuminAi's goal.
default7/5/2026
Node offline: vip2.luminai.cc is officially offline. Please switch to other nodes.
ongoing6/30/2026
Claude full group weekend special: E-Claude-Max-F at 0.8x rate. No client restrictions, supports integration. Codex limited-time offer group at 0.08x and Codex-Plus group have both been replenished and are stable—use with confidence.
ongoing6/30/2026
The Claude-Main exclusive package is temporarily offline. Sales are paused to ensure stable service. Existing users are unaffected.
FAQ
Frequently Asked Questions
Answers to common questions
Notes
- Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 20-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.
- Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.
- Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.