A unified API gateway providing access to multiple large language models (LLMs) and AI services through a single interface.
ChatGTP offers 84 LLM API models.
API pricing per token ranges from $0.0041 to $10.27/M (input).
Speed benchmark average: 122 tok/s.
ChatGTP is an API aggregator, offering models from multiple vendors.
https://www.chatgtp.cnPrimary recommendation
https://api.deepseek-r1.shopBackup route
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
| Model | Speed | Latency | Tests |
|---|---|---|---|
20.88 tok/s | 2.51s | 5 | |
45.32 tok/s | 2.13s | 5 | |
| Model | Audit | Input ($/M) | Output ($/M) |
|---|---|---|---|
gemini-3-flash-preview-ci | — | $0.0041 | $0.0041 |
| — | $0.0055 | $0.0055 | |
| — | $0.0055 | $0.0055 | |
| — |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Dec 30, 07:11 AM | deepseek-ai/DeepSeek-V3.2-Exp | 20.88 tok/s | 2.51s |
| Dec 30, 07:00 AM | deepseek-v3-1-terminus | 45.32 tok/s | 2.13s |
| Dec 30, 02:52 AM | gpt-4.1-nano-2025-04-14 | 222.46 tok/s | 0.80s |
| Dec 30, 02:49 AM | gemini-2.0-flash | 181.28 tok/s | 1.02s |
| Nov 27, 04:51 AM | gemini-2.0-flash | 170.98 tok/s | 1.37s |
| Oct 25, 11:53 AM | gemini-2.0-flash | 113.80 tok/s | 6.15s |
| Oct 12, 01:06 AM | gemini-2.0-flash | 151.59 tok/s | 4.46s |
| Oct 9, 04:20 AM | gemini-2.0-flash | 153.26 tok/s | 0.74s |
| Sep 26, 03:11 PM | gemini-2.0-flash | 55.80 tok/s | 32.61s |
| Sep 23, 03:23 PM | gemini-2.0-flash | 84.58 tok/s | 10.45s |
By default, Gemini's thinking model automatically decides whether to think. > Add the suffix -nothinking to the model to force no thinking. > Add the suffix -thinking to force thinking.
Add WeChat: andyliu_xx
222.46 tok/s |
0.80s |
| 5 |
145.40 tok/s | 5.18s | 110 |
46.73 tok/s | 15.23s | 30 |
| $0.0055 |
| $0.0055 |
| — | $0.0068 | $0.0068 |
| — | $0.0082 | $0.0082 |
| — | $0.0082 | $0.0082 |
| — | $0.0082 | $0.0082 |
gemini-3.5-flash-c | — | $0.010 | $0.010 |
| — | $0.011 | $0.011 |
api2.aigcbest.top
Provides AI-generated content APIs for various applications, including text and image generation.
api.holdai.top
毫秒API provides a stable, high-bandwidth API forwarding service for OpenAI-compatible models, including GPT, Claude, and Midjourney, with global server deployment and transparent pricing.
api.linkapi.org
Xiaodoubao API is a Chinese AI API relay platform hosted at api.linkapi.org, advertising low-cost and high-concurrency access to OpenAI, Claude, Gemini, Grok, Flux, and agent workflows.
api.newagiai.com
Provides API access to a wide range of AI models including text, image, and video generation from multiple providers.
api.bltcy.cn
柏拉图AI (api.bltcy.cn) is a multi-dimensional API integration platform providing access to over 600 AI models, serving as an alternate endpoint.
aicanapi.com
AicanAPI provides an enterprise-grade API management platform with high-performance architecture, security compliance, and cost optimization for business digital transformation.
