速创API https://api.suchuang.vip offers a platform for accessing multiple AI models via a single API. It supports text generation models like GPT-5.1, Claude Opus 4.5, and Grok 4.1; image generation models such as Nano-Banana-2, Doubao Seedream 4.5, and Qwen Image Edit 2509; and video generation models including Sora 2, Veo 3.1, Kling Omni-Video V1, and Wan 2.5. The API provides both official and reverse-engineered formats, with features like OSS storage preferences for image speed optimization and asynchronous task support for video and image models. Use cases include chatbots, creative content generation, and multimedia applications.
Suchuang API provides access to various AI models including text generation, image creation, and video generation through a unified API.
- Models
- 510 models
- From
- $0.0020/M
- Speed
- 74 tok/s
- Updated
- 7/29/2026
- Latency
- 0.00 s
- Created At
- 8/13/2025
- Recharge Rate
- ¥1.00 per $1 quota
Features
DrawingTaskData ExportCheck-in
Login Methods
Passkey
API Endpoints
- Hong Kong Route
https://api.suchuang.vipUse this normally
Claim this provider
速Verified by 速创API
Leaderboard Rankings
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
About 速创API
Health Check
100%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 903 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
gpt-5.2-pro | - | - | - | - | ||||||||||
claude-haiku-4-5 | - | - | - | - | ||||||||||
deepseek-v4-flash-0731 | - | - | - | - | ||||||||||
deepseek-v4-pro-0813 | - | - | - | - | ||||||||||
gemini-3.1-flash-lite | - | - | - | - | ||||||||||
gemini-3.5-flash-lite | - | - | - | - | ||||||||||
glm-5.1 | - | - | - | - | ||||||||||
grok-4.20-0309-non-reasoning | - | - | - | - | ||||||||||
grok-4.20-0309-reasoning | - | - | - | - | ||||||||||
grok-4.20-multi-agent-0309 | - | - | - | - | ||||||||||
grok-build-0.1 | - | - | - | - | ||||||||||
kimi-k2.6 | - | - | - | - | ||||||||||
kimi-k2.7-code | - | - | - | - | ||||||||||
kimi-k3 | - | - | - | - | ||||||||||
qwen3.8-max | - | - | - | - | ||||||||||
| - | - | 97.1 t/s | 10.46 s | |||||||||||
grok-imagine-imagedefault | $0.100/request | - | - | - | ||||||||||
grok-imagine-image-prodefault | $0.300/request | - | - | - | ||||||||||
claude-opus-5default | $5.25/M | $26.25/M | - | - | ||||||||||
claude-opus-5优惠官转 | $18.38/M | $91.88/M | - | - | ||||||||||
| $34.65/M | $173.25/M | - | - | |||||||||||
gemini-3.6-flashdefault | $1.59/M | $7.96/M | - | - | ||||||||||
gemini-3.6-flash优惠官转 | $5.57/M | $27.84/M | - | - | ||||||||||
| $10.49/M | $52.50/M | - | - | |||||||||||
gpt-5.6-lunadefault | $1.00/M | $6.00/M | - | - |
Showing 25 of 903 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Aug 14, 10:24 AM | grok-4.6 | 97.09 tok/s | 10.46s |
| Jun 10, 01:44 AM | claude-fable-5 | 45.62 tok/s | 3.69s |
| Apr 22, 03:16 AM | gemini-3.1-pro-preview | 105.41 tok/s | 12.72s |
| Apr 22, 03:15 AM | claude-sonnet-4-6 | 19.71 tok/s | 8.43s |
| Apr 22, 03:12 AM | gpt-5.4 | 50.06 tok/s | 1.42s |
| Mar 31, 12:28 AM | gpt-4o-2024-11-20 | 84.77 tok/s | 3.24s |
| Mar 18, 10:40 AM | gpt-4o-2024-11-20 | 61.38 tok/s | 1.52s |
| Feb 23, 02:49 AM | gpt-4o-2024-11-20 | 127.81 tok/s | 0.91s |
| Feb 19, 05:31 AM | gpt-4o-2024-11-20 | 78.18 tok/s | 0.70s |
Similar API Provider Alternatives to Compare
Compare 速创API alternatives against 6 nearby API providers using 886 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| 速创API suchuang Suchuang API provides access to various AI models including text generation, image creation, and video generation through a unified API. | Current provider baseline | 510 | 0 | $0.0020/M | 74 tok/s | 9970% |
| 初叶🍂Furry API ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users. |
| 1,021 | 152 | $18.00/M | 171 tok/s | 4960% |
| CatClaw API www-catclawai-top CatClaw API provides an AI model relay with access to GPT, Claude, and other large language models. |
| 129 | 2 | N/A | 83 tok/s | 9990% |
| 天絮 API tianxu-api Tianxu API provides an AI model relay service with multiple access points and stable connectivity. |
| 759 | 0 | $0.014/M | 93 tok/s | 9920% |
| 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 | 1330% |
| 钠 API naapi-cc Na API (naapi.cc) is an OpenAI-compatible LLM API gateway with competitive pricing and stable access to 100+ models from OpenAI, Anthropic, Google, and more. |
| 566 | 0 | $0.0031/M | 649 tok/s | 9970% |
| 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 | 9880% |
Announcements
warning8/5/2026
Recent model adjustments: dear users, please switch to the new models. For details, join the group.
warning8/2/2026
Price reductions and group adjustments are coming soon. Please stay tuned for announcements.
default8/1/2026
gpt-5.6 has been synchronized with the official price reduction.
warning7/31/2026
The auto group in newapi had billing issues, so it has been removed. Existing auto groups have been changed to default.
success7/25/2026
VIP recharge discount details: ≥ 200 yuan: upgrade to VIP group, subsequent recharges at 5% off ≥ 600 yuan: upgrade to SVIP group, subsequent recharges at 10% off First recharge meets the threshold? If your first recharge is 200 or 600 yuan, contact me to get the same discount (5% or 10% off) for this recharge.
Users who have met the threshold have been upgraded in batches. Future upgrades will be done periodically; we recommend contacting me directly for faster processing.
success7/25/2026
claude-opus-5 is now available.
error7/24/2026
Dear users:
Due to unexpected circumstances, we have restored the database to the state from early this morning.
Users who recharged today: your recharge records have been lost. Please contact us as soon as possible to restore your balance.
Other users: usage records and quota deductions before the restoration will not be restored. Services during the outage are considered free.
We apologize for the inconvenience. If you have any questions, please contact us.
success7/23/2026
gemini-3.6-flash is now available.
success7/9/2026
grok-4.5 is now available, with very fast output.
default6/23/2026
Due to frequent price changes for domestic models, the default group for domestic models has been adjusted to official domestic prices. New groups 0.8 domestic and 0.53 domestic have been added. Gemini models have also restored the original default pricing.
FAQ
Why does the model give an inconsistent model name when asked 'What model are you'?
The model's self-description isn't reliable; it lacks self-identification and depends on its training data.
Why does the official website model know its own model name, and are you providing fake models?
The official website uses system prompts to inform the model of its identity; you can try it, and it might say it's the GPT-999 model.
Why does the model fabricate content that doesn't exist?
The model might generate plausible but incorrect answers when lacking information; for critical data, provide sources or request citations.
Why does the model ignore earlier parts of a long context I provided?
This could be due to context length limits causing truncation; try shortening input, breaking questions into parts, or summarizing first.
Why does the token count or cost differ from my estimation?
Billing covers input and output tokens, including system prompts, tool calls, and retries; check the usage or billing details in the response.
What should I do if an API request fails?
1. Authentication error: Verify your API key. 2. Insufficient balance: Recharge your account. 3. Parameter error: Check request parameters against the documentation. 4. Model unavailable: Switch to another available model. 5. Request timeout: Could be network issues or high load; retry later. If unresolved, contact support with logs; avoid saying it's not working without details.
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.