AMD Radeon Cloud

AMD 官方面向开发者推出的 Radeon Cloud Token Factory 算力平台，提供开箱即用的免配置 AI 模型 API（涵盖 DeepSeek V4 Flash 1M、Qwen 3.8 Flash、MiniCPM 等），原生兼容 OpenAI 与 Anthropic 双协议。

Showing 5 of 5 active models
AMD Radeon Cloud

MiniCPM 5 1B

Ultra-fast 1B parameter on-device language model served with high throughput on AMD GPU Cloud.

text-generation
unlimited
AMD Radeon Cloud

MiniCPM-V 4.6

AMD Radeon Cloud endpoint for MiniCPM-V 4.6 edge-multimodal flagship vision model.

text-generation, image-understanding
unlimited
AMD Radeon Cloud

Qwen 3.8 Flash Next

AMD Radeon Cloud high-speed endpoint for Qwen 3.8 Flash Next with 256K context.

text-generation, code-generation
unlimited
AMD Radeon Cloud

DeepSeek V4 Flash Vision (Exp)

Official AMD endpoint for DeepSeek V4 Flash Vision (Exp) multimodal reasoning with 1M context.

text-generation, image-understanding, code-generation
unlimited
AMD Radeon Cloud

DeepSeek V4 Flash

AMD Radeon Cloud Token Factory free API for DeepSeek V4 Flash with 1M context and dual OpenAI/Anthropic protocol support.

text-generation, code-generation
unlimited

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Frequently Asked Questions about AMD Radeon Cloud

Community Feedback

Comments are tied to your GitHub account — sign in to join the discussion.

Explore Other Free AI Providers

NVIDIA NIM
NVIDIA NIM (Inference Microservices) provides optimized cloud and self-hosted API endpoints for enterprise and open-source models with 1,000 free inference credits on registration.
Zhipu AI
智谱 AI 开放平台（BigModel），提供 GLM-5.3-Flash、GLM-4 等全系列前沿大模型与 GLM Coding Plan 开发者订阅。
Empero
Empero is an independent AI research lab based in Germany, dedicated to advancing open-weights models. It provides a 100% free, OpenAI-compatible community endpoint for models like GLM-5.3-Flash with no registration or API key required.
GMI Cloud
GMI Cloud 是专为高性能 AI 与 GPU 算力打造的云服务平台。提供 MiniMax M3、Speech 2.8 与 Music 3.0 等核心旗舰模型的 0 元直接 API 调用，免绑卡、免预充值。
OpenCode Go
OpenCode Go 是专为 Coding Agent 和高频开发者打造的超高性价比订阅计划（Coding Plan）。首月仅 $5（续费 $10/月），提供每月 $60 基础额度池、Hy3 独享 $480/月 算力、GPT-5.6 Sol 5 折以及 Muse Spark 1.2 Contributor 近乎无限额度，量大管饱，可直接生成 API Key 供 Cursor、Claude Code、Aider 等各种工具调用。
DeepSeek
DeepSeek 官方开放平台，提供业内领先的高性价比大模型与代码推理 API，原生支持 OpenAI 接口协议与超低成本 Context Caching。