zeabur API at new-api.abrdns.com is a LinuxDO community LLM relay by user qq1244. Rate limit 30. Models: DeepSeek, Gemini, K2. Daily sign-in rewards credits. Supports LDC, NSFW. No immersive translate.
zeabur API
new-api.abrdns.com
zeabur API (new-api.abrdns.com) is a LinuxDO LLM relay by user qq1244. Rate 30. DeepSeek, Gemini, K2. Daily sign-in credits. Supports LDC, NSFW.
- Models
- 132 models
- From
- $0.050/M
- Speed
- --
- Updated
- 6/8/2026
- Latency
- --
- Created At
- 4/20/2026
- Recharge Rate
- ¥7.30 per $1 quota
Features
Login Methods
API Endpoints
- Endpoint 1Historical / Unverified
https://abrdns.com - Endpoint 2Historical / Unverified
https://new-api.abrdns.com
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 zeabur API
Health Check
API Benchmarks & Pricing
Compare 32 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
| $1.88/M | $4.50/M | |
DeepSeek-V4-Pro-think国产模型 | $0.435/M | $0.870/M |
GLM-5.2-1M国产模型 | $1.80/M | $6.30/M |
MiniMax-M3-highspeed国产模型 | $0.600/M | $2.40/M |
Qwen/Qwen3.6-27B-FP8国产模型 | $0.290/M | $3.20/M |
Qwen/Qwen3.6-35B-A3B-FP8国产模型 | $0.345/M | $1.38/M |
Qwen3-Embedding-0.6B嵌入模型 | $0.0020/request | - |
Qwen3-Reranker-0.6B嵌入模型 | $0.0020/request | - |
| $0.600/M | $2.40/M | |
Kimi-K3国产模型 | $4.50/M | $22.50/M |
gpt-image-2生图分组 | $0.050/request | - |
GLM-5.2-think国产模型 | $1.50/M | $4.50/M |
GLM-5.2国产模型 | $1.20/M | $4.10/M |
Kimi-K2.7-Code国产模型 | $0.950/M | $4.00/M |
qwen3.7-max国产模型 | $5.00/M | $15.00/M |
DeepSeek-V3国产模型 | $0.250/M | $1.00/M |
| $0.500/M | $1.50/M | |
DeepSeek-V4-Pro国产模型 | $0.435/M | $0.870/M |
| $0.170/M | $0.350/M | |
Kimi-K2.6国产模型 | $0.680/M | $3.15/M |
GLM-5.1国产模型 | $1.00/M | $3.20/M |
| $0.390/M | $0.970/M | |
qwen3.6-plus国产模型 | $0.280/M | $1.69/M |
MiniMax-M2.7国产模型 | $0.300/M | $1.20/M |
GLM-5-Turbo国产模型 | $1.20/M | $4.00/M |
Showing 25 of 32 model rows
Recent Test Records
Similar API Provider Alternatives to Compare
Compare zeabur API alternatives against 6 nearby API providers using 436 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| zeabur API new-api-abrdns-com zeabur API (new-api.abrdns.com) is a LinuxDO LLM relay by user qq1244. Rate 30. DeepSeek, Gemini, K2. Daily sign-in credits. Supports LDC, NSFW. | Current provider baseline | 132 | 0 | $0.150/M | N/A | 9660% |
| 钱多多 API api2-aigcbest-top Provides AI-generated content APIs for various applications, including text and image generation. |
| 1,418 | 2 | $0.0025/M | 101 tok/s | 9940% |
| Koyeb AI Gateway new-api-koyeb-app An OpenAI-compatible API gateway deployed on Koyeb, providing access to multiple AI models. |
| 578 | 420 | N/A | 33 tok/s | 9960% |
| Yun API api-zyai-online Yun API is a high-speed, stable, and high-concurrency API relay service based on official APIs, offering access to over 100 AI models including text, image, and video generation. |
| 431 | 0 | $0.00000342/M | 32 tok/s | 9930% |
| TommyLam API new-api-tommylam-me TommyLam API offers an OpenAI-compatible API gateway for accessing multiple AI models at competitive rates. |
| 231 | 100 | N/A | 61 tok/s | 9990% |
| F2API api-f2api-com F2API is an enterprise AI gateway providing a unified OpenAI-compatible interface for accessing multiple large language models. |
| 1,262 | 0 | N/A | 272 tok/s | 9990% |
| 哈基米API站 api-gemai-cc 哈基米API站 offers a unified API gateway for large language models with competitive pricing and stable service. |
| 323 | 0 | $0.930/M | 119 tok/s | 9990% |
Announcements
Update content:
All users' public welfare station quota halved
All users' welfare station level reset, need to re-authenticate to use welfare station functions
Check-in adds random check-in, based on original check-in with random multiplier
Check-in adds consecutive check-in extra multiplier
Public station 8.17 adjustment: kimi-k3 quota exhausted, taken offline today
Public station 8.17 adjustment: Due to excessive deepseek usage, upstream exploded, DeepSeek-V4-Flash (preview version corresponding id) replaced with correct preview version model upstream
Public station 8.17 adjustment: Due to excessive deepseek usage, upstream exploded, DeepSeek-V4-Pro (preview version corresponding id) temporarily taken offline
Public station 8.17 update: level3 launches GLM-5.3-1M
Public station 8.17 adjustment: deepseek-v4 official series models synchronized with official price increase
Public station 8.16 adjustment: Adjusted some model IDs and prices
Public welfare site / image generation site adjustment on 8.7: Due to high GPT risk control at night and low user usage, the image-2-1k and gpt-image-2 models on the image generation site will be inaccessible from 23:00 to 8:00 the next day.
The public welfare site now supports the /v1/responses interface, which can be used directly in Codex. As it is still in testing, please understand if there are issues.
Due to the database expiring at the end of the month, migration is required. The public welfare site / image generation site / welfare site are expected to enter downtime maintenance at 22:00 tonight.
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.

