天宫造物 is an API proxy service that aggregates multiple AI models through a unified interface. It supports models including GPT-5.4, Claude 4.6, Nano Banana, and Gemini 3.1. The service is optimized for Chinese developers with domestic direct connections and low-latency architecture, claiming average response times of 50ms. It offers pay-as-you-go pricing based on token consumption and maintains 99.9% uptime with automatic failover mechanisms. The API is fully compatible with OpenAI's SDK specifications, requiring only base URL and API key changes for integration. Key features include stream output support, comprehensive error handling, and detailed usage monitoring through an automated console.
cpa.tgzw.shop
天宫造物 (cpa.tgzw.shop) is an API proxy service providing low-latency access to multiple AI models including Claude, GPT, and Gemini.
- Models
- 61 models
- From
- --
- Speed
- 45 tok/s
- Updated
- 6/8/2026
- Latency
- 0.00 s
- Created At
- 3/24/2026
- Recharge Rate
- ¥1.00 per $1 quota
Features
DrawingTaskData Export
Login Methods
LinuxDOPasskey
API Endpoints
- Endpoint 1Historical / Unverified
https://one.vipui.cn - Endpoint 2Historical / Unverified
https://tgzw.shop - Endpoint 3Historical / Unverified
https://cpa.tgzw.shop - Endpoint 4Historical / Unverified
https://c2api.tgzw.shop
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.
About 天宫造物
Health Check
100%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 23 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
gpt-image-2default | $0.100/M | $0.100/M | - | - |
claude-3-5-haiku-20241022default | $0.800/M | $4.00/M | - | - |
claude-3-5-sonnet-20240620default | $3.00/M | $15.00/M | - | - |
claude-3-5-sonnet-20241022default | $3.00/M | $15.00/M | - | - |
claude-3-7-sonnet-20250219default | $3.00/M | $15.00/M | - | - |
claude-opus-4-7default | $5.00/M | $25.00/M | - | - |
gpt-5.5default | $5.00/M | $40.00/M | - | - |
gpt-5.4-minidefault | $0.750/M | $4.50/M | - | - |
gpt-5.4default | $2.50/M | $15.00/M | 50.0 t/s | 7.31 s |
gpt-5.3-codexdefault | $1.75/M | $14.00/M | - | - |
| - | - | 39.8 t/s | 3.15 s | |
claude-sonnet-4-6default | $3.00/M | $15.00/M | - | - |
claude-opus-4-6default | $5.00/M | $25.00/M | - | - |
| - | - | 12.3 t/s | 2.61 s | |
| - | - | 12.2 t/s | 2.62 s | |
gpt-5.2default | $0.250/M | $2.00/M | - | - |
claude-opus-4-5-20251101default | $5.00/M | $25.00/M | - | - |
| - | - | 82.0 t/s | 13.94 s | |
claude-haiku-4-5-20251001default | $1.00/M | $5.00/M | - | - |
claude-sonnet-4-5-20250929default | $3.00/M | $15.00/M | 45.4 t/s | 3.17 s |
claude-opus-4-1-20250805default | $15.00/M | $75.00/M | - | - |
claude-opus-4-20250514default | $15.00/M | $75.00/M | - | - |
claude-sonnet-4-20250514default | $3.00/M | $15.00/M | - | - |
Showing 23 of 23 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Apr 1, 02:08 PM | gpt-5.1-codex-mini | 81.97 tok/s | 13.94s |
| Apr 1, 07:19 AM | gemini-3-flash | 12.25 tok/s | 2.61s |
| Apr 1, 07:19 AM | google/gemini-3-flash | 12.21 tok/s | 2.62s |
| Apr 1, 07:16 AM | anthropic/claude-sonnet-4.6 | 12.33 tok/s | 2.59s |
| Mar 29, 10:28 AM | anthropic/claude-sonnet-4.6 | 45.90 tok/s | 3.40s |
| Mar 29, 10:10 AM | claude-sonnet-4-5-20250929 | 44.12 tok/s | 3.14s |
| Mar 29, 09:01 AM | claude-sonnet-4-5-20250929 | 46.68 tok/s | 3.20s |
| Mar 29, 08:49 AM | anthropic/claude-sonnet-4.6 | 46.59 tok/s | 2.83s |
| Mar 29, 08:35 AM | gpt-5.4 | 67.73 tok/s | 3.25s |
| Mar 29, 08:33 AM | gpt-5.4 | 65.44 tok/s | 3.88s |
Similar API Provider Alternatives to Compare
Compare 天宫造物 alternatives against 6 nearby API providers using 377 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| 天宫造物 cpa-tgzw-shop 天宫造物 (cpa.tgzw.shop) is an API proxy service providing low-latency access to multiple AI models including Claude, GPT, and Gemini. | Current provider baseline | 61 | 19 | N/A | 45 tok/s | 9910% |
| 鲨鱼魔法 openai-sharkmagic-top 鲨鱼魔法 (sharkmagic.top) provides access to official paid AI models like Gemini, Claude, and GPT through a unified proxy with OpenAI-compatible API. |
| 1,577 | 15 | $7.20/M | 81 tok/s | 9980% |
| OpenRouter openrouter A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google. |
| 614 | 0 | N/A | 93 tok/s | 10000% |
| NVIDIA NIM nvidia-nim NVIDIA NIM provides optimized AI model inference APIs for LLMs, vision, and embedding models through NVIDIA cloud infrastructure. |
| 168 | 0 | N/A | 82 tok/s | 9960% |
| WONG公益站 wzw-pp-ua WONG公益站 is a free, community-driven OpenAI-compatible API relay. It aggregates 70+ AI models from providers like OpenAI, Anthropic, DeepSeek, xAI, Moonshot, and Zhipu AI, offering free API quotas for developers and researchers. |
| 155 | 0 | $0.0055/M | 46 tok/s | 9990% |
| HotaruAPI api-hotaruapi-top HotaruAPI provides API access to AI models for developers, including a model marketplace and self-service options. |
| 378 | 4 | N/A | 59 tok/s | 0% |
| Kilo kilo-ai Kilo provides an open-source coding agent and AI assistant platform for developers, supporting 500+ models and integrations across IDEs and tools. |
| 350 | 0 | N/A | 69 tok/s | 9650% |
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.