Try NVIDIA NIM APIs

moonshotai kimi-k2-thinking

Open reasoning model with 256K context window, native INT4 quantization and enhanced tool use

Conversational Reasoning chat Long Context Function Calling

qwen qwen3-next-80b-a3b-thinking

80B parameter AI model with hybrid reasoning, MoE architecture, support for 119 languages.

Reasoning chat Text-to-Text

bytedance seed-oss-36b-instruct

ByteDance open-source LLM with long-context, reasoning, and agentic intelligence.

thinking budget chat reasoning text-generation

nvidia nvidia-nemotron-nano-9b-v2

High‑efficiency LLM with hybrid Transformer‑Mamba design, excelling in reasoning and agentic tasks.

thinking budget chat reasoning

qwen qwq-32b

Powerful reasoning model capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems.

coding chat math advanced reasoning

moonshotaikimi-k2-thinking

qwenqwen3-next-80b-a3b-thinking

bytedanceseed-oss-36b-instruct

nvidianvidia-nemotron-nano-9b-v2

qwenqwq-32b

moonshotai kimi-k2-thinking

qwen qwen3-next-80b-a3b-thinking

bytedance seed-oss-36b-instruct

nvidia nvidia-nemotron-nano-9b-v2

qwen qwq-32b