文本生成 APIs
用于文本补全和聊天的语言大模型
MiniCPM 5 1B
AMD 官方 MiniCPM 5 1B 极速轻量模型端点，毫秒级响应，适合实时边缘流水线。
Qwen 3.8 Flash Next
AMD Radeon Cloud 官方 Qwen 3.8 Flash Next 高速推理端点，支持 256K 上下文与双协议。
DeepSeek V4 Flash Vision (Exp)
AMD 官方 DeepSeek V4 Flash Vision (Exp) 多模态端点，支持 100 万 Token 上下文与图文交互。
GPT-OSS 20b
OpenAI's fast 20B open-weights model on NVIDIA NIM for code and agent loops.
GPT-OSS 120b
OpenAI's 120B open-weights model hosted on NVIDIA NIM with 1M context.
QwQ 32b
Free QwQ 32b API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.
Qwen3 30b A3b FP8
Free Qwen3 30b A3b FP8 API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.
Mistral Small 3.1 24b Instruct
Free Mistral Small 3.1 24b Instruct API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.
Mistral 7b Instruct V0.2 LoRA
Free Mistral 7b Instruct V0.2 LoRA API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.
Llama Guard 3 8b
Free Llama Guard 3 8b API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.
Llama 4 Scout 17b 16e Instruct
Free Llama 4 Scout 17b 16e Instruct API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.
Llama 3.3 70b Instruct FP8 Fast
Free Llama 3.3 70b Instruct FP8 Fast API via Cloudflare Workers AI with 10,000 daily free Neurons. Zero setup fee, no credit card required.