Gitee AI offers a comprehensive AI platform with multiple services. Its Serverless API provides on-demand, auto-scaling inference for large language models, supporting text, image, audio, and multimodal models with OpenAI SDK compatibility. The platform includes model fine-tuning services for customization with data preprocessing and training tracking. Reserved GPUs offer flexible GPU compute rental for training and inference, supporting NVIDIA and domestic hardware like Ascend and MetaX. An App Store enables developers to publish and monetize AI applications. Key strengths include support for domestic compute hardware, low-latency inference, and pay-as-you-go pricing. Typical use cases involve AI model deployment, custom model training, and application development.
Gitee AI
ai.gitee.com
Gitee AI provides a platform for AI model hosting, inference, and deployment with access to open-source LLMs.
- Models
- 260 models
- From
- --
- Speed
- 88 tok/s
- Updated
- 6/8/2026
- Latency
- 0.00 s
- Created At
- 12/7/2025
API Endpoints
- Endpoint 1
ai.gitee.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 Gitee AI
Health Check
API Benchmarks & Pricing
Compare 260 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
GLM-5.2 |
happyhorse-1.1 |
ip-location |
Kimi-K2.7-Code |
MOSS-Audio-8B-Thinking |
TeleASR-MultiDialect |
TeleTTS-Bidirectional-Mandarin |
TeleTTS-Mandarin |
TeleTTS-MultiDialect |
ACE-Step-v1-3.5B |
Align-DS-V |
all-mpnet-base-v2 |
AnimeSharp |
AudioFly |
AutoGLM-Phone-9B-Multilingual |
Baichuan-M2-32B |
bce-embedding-base_v1 |
bce-reranker-base_v1 |
bge-large-zh-v1.5 |
bge-m3 |
bge-reranker-large |
bge-reranker-v2-m3 |
bge-small-zh-v1.5 |
ChatTTS |
clip-vit |
Showing 25 of 260 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Aug 22, 01:30 PM | HealthGPT-L14 | 1729.89 tok/s | 9.81s |
| Jun 4, 02:31 AM | MiniMax-M2.7 | 45.49 tok/s | 11.96s |
| Jan 16, 01:53 PM | DeepSeek-V3.2 | 35.11 tok/s | 6.18s |
| Aug 25, 09:52 AM | DeepSeek-R1 | 83.18 tok/s | 16.75s |
| Aug 15, 03:05 AM | DeepSeek-R1 | 13.18 tok/s | 35.97s |
| Jul 23, 05:53 AM | DeepSeek-R1 | 28.70 tok/s | 35.70s |
| Jun 24, 01:43 PM | DeepSeek-R1 | 28.49 tok/s | 26.15s |
| Apr 11, 06:46 AM | DeepSeek-R1 | 22.59 tok/s | 33.60s |
| Apr 9, 06:45 AM | DeepSeek-R1 | 32.76 tok/s | 17.14s |
| Apr 9, 06:45 AM | DeepSeek-R1 | 32.94 tok/s | 23.20s |
Similar API Provider Alternatives to Compare
Compare Gitee AI alternatives against 6 nearby API providers using 310 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| Gitee AI gitee-ai Gitee AI provides a platform for AI model hosting, inference, and deployment with access to open-source LLMs. | Current provider baseline | 260 | 0 | N/A | 88 tok/s | 5330% |
| 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% |
| LLMService llmservice LLMService provides API access to large language models for self-use applications. |
| 425 | 0 | N/A | 139 tok/s | 3450% |
| 阿里云百炼 DashScope dashscope Alibaba Cloud DashScope provides AI model APIs including Qwen LLMs, vision, audio, and embedding models. |
| 291 | 0 | N/A | 76 tok/s | 7640% |
| DeadlySignal API deadlysignal |
| 290 | 0 | N/A | 63 tok/s | 9960% |
| Elysiver API elysiver-api Elysiver API appears to provide an OpenAI-compatible API gateway at elysiver.h-e.top. The public root is protected by a Cloudflare challenge during review. |
| 78 | 0 | $0.014/M | 119 tok/s | 9930% |
| 180txt API 180txt-cn 180txt API provides an OpenAI-compatible API relay for multiple AI models. |
| 77 | 8 | $0.639/M | 42 tok/s | 9940% |
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.