All free API endpoints
158 results foundMeta Muse Glimmer 30B
Meta's 30B multimodal reasoning model on NVIDIA NIM — text & image input with tool calling and separate thinking.
Nemotron 3.5 Lightning
NVIDIA's 30B-A3B Mamba-2/MoE hybrid architecture with NVFP4 quantization and millisecond latency.
DeepSeek V4 Flash
DeepSeek V4 Flash ultra-fast MoE coding model free tier on OpenCode Zen with sub-second latency.
Kimi K3
Moonshot AI 2.8T Kimi K3 MoE API via NVIDIA NIM — 1M context, native vision, free endpoint with 40 RPM limit.
GLM 5.3 Flash
GLM-5.3-Flash 官方 OpenAI 兼容端点，320B-A18B 混合架构，1M 上下文，免绑卡免费不限量调用。
MiniMax M3
MiniMax M3 1M MSA Sparse Attention model on NVIDIA NIM — 59% SWE-bench Pro for autonomous coding agents.
MiMo TTS 2.5
Upload a 5-second sample to clone and synthesize speech with extreme fidelity.
MiMo TTS 2.5
High-fidelity TTS with dozens of expressive presets across multiple languages and dialects.
GLM 5.3 Flash
Zhipu GLM-5.3-Flash API with 1M context, 320B-A18B MoE architecture, and OpenAI-compatible SDK support.
GLM 5.3 Flash
100% free public endpoint for GLM-5.3-Flash with zero setup and no API key required.
MiniMax Music 3.0
GMI Cloud 官方提供的 MiniMax Music 3.0 端到端音乐生成端点。单 Prompt 即可一键生成人声与立体声伴奏完整全曲。
MiniMax Speech 2.8
GMI Cloud 官方提供的 MiniMax Speech 2.8 自然语音合成端点。支持秒级声音克隆与多语言语音生成。