统一的大模型接口网关，提供聊天、嵌入、图像和音频等多种端点，支持超过30个供应商。
Astrdark 目前提供 2 个大模型 API。
API 按 token 计费价格为 $0.010/M（输入）。
速度基准测试平均吞吐 48 tok/s。
api.astrdark.cyou| 模型 | 速度 | 延迟 | 测试数 |
|---|---|---|---|
longcat-flash-lite | 66.16 tok/s | 9.82s | 5 |
longcat-flash-thinking-2601 | 30.73 tok/s | 44.12s | 5 |
| 模型 | 输入 ($/M) | 输出 ($/M) |
|---|---|---|
openrouter/free | $0.0000 | $0.0000 |
nemotron-nano-12b-v2-vl | $0.0000 | $0.0000 |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
google/gemma-3-12b-it:free | $0.010 | $0.010 |
google/gemma-3n-e4b-it:free | $0.010 | $0.010 |
| $0.010 | $0.010 | |
google/gemma-4-31b-it:free | $0.010 | $0.010 |
liquid/lfm-2.5-1.2b-thinking:free | $0.010 | $0.010 |
| 时间 | 模型 | 速度 | 延迟 |
|---|---|---|---|
| 04/13/2026, 08:32 | longcat-flash-lite | 66.16 tok/s | 9.82s |
| 04/13/2026, 08:20 | longcat-flash-thinking-2601 | 30.73 tok/s | 44.12s |
Seamee API provides an AI model relay for accessing multiple LLMs through OpenAI-compatible endpoints.
9 个共享模型A non-profit API provider offering access to various AI models including Codex, Claude Code, and Open Code through multiple endpoints.
8 个共享模型A non-profit API service providing access to various AI models including Codex, Claude Code, and Open Code, with specific unlimited-use groups.
8 个共享模型A non-profit AI infrastructure offering free access to integrated large language models with privacy-focused, no-logging policies.
8 个共享模型SWT-API provides access to various AI models including Claude, Kimi, GLM, and Gemini for chat and completion tasks.
7 个共享模型
A unified gateway API for large language models, offering access to multiple providers with competitive pricing and stability.
6 个共享模型