Provides API services with official pricing and discounted recharge rates for cost-effective access.
ChatST API offers 76 LLM API models.
API pricing per token ranges from $0.0000 to $6.99/M (input).
Speed benchmark average: 535 tok/s.

https://api.chatst.orgMost Recommended
https://api.st0722.topDomestic Transit, Ultra-Low Latency
https://api.662793.xyzOverseas User Friendly
https://api.chatst.us.kgEdgeOne Overseas Acceleration
https://chatst.orgRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
| Model | Speed | Latency | Tests |
|---|---|---|---|
625.49 tok/s | 0.37s | 5 | |
444.26 tok/s | 0.63s | 5 |
| Model | Audit | Input ($/M) | Output ($/M) |
|---|---|---|---|
| — | $0.0000 | $0.0000 | |
| — | $0.0000 | $0.0000 | |
| — | $0.0000 | $0.0000 | |
| — | $0.0001 | $0.0001 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jul 30, 04:12 AM | qwen-3-235b-2507 | 625.49 tok/s | 0.37s |
| Jul 30, 04:12 AM | meta-llama/llama-4-scout-17b-16e-instruct | 444.26 tok/s | 0.63s |
Large top-up channel is now available: Purchase address for large discount redemption codes above 100: https://shop.st0722.top/item?id=99
| — | $0.0001 | $0.0001 |
| — | $0.0001 | $0.0001 |
sarvam-105b | — | $0.0001 | $0.0001 |
| — | $0.0001 | $0.0001 |
QA | — | $0.0014 | $0.0014 |
| — | $0.0070 | $0.0070 |
api2.aigcbest.top
Provides AI-generated content APIs for various applications, including text and image generation.
napi.seaya.link
Seamee API provides an AI model relay for accessing multiple LLMs through OpenAI-compatible endpoints.
openrouter.fans
A third-party OpenRouter-compatible API relay providing access to multiple AI models.
api.gpt.ge
Provides access to over 500 AI models via OpenAI protocol with pay-as-you-go pricing, fast response times, and transparent billing.
api.aaai.vip
API provider for AI services accessible via dedicated endpoints.
newapi.exynos.top:8443
Synapse is an OpenAI-compatible API relay service providing access to multiple AI models with unified endpoints.