reasoningDeepSeek
DeepSeek V4 Pro
State-of-the-art open reasoning model with transparent chain-of-thought. Excels at math, logic and multi-step problem solving.
deepseek-ai/deepseek-v4-proTest it live
Live playgroundDeepSeek V4 Proin-browser demo
DeepSeek V4 Proin-browser demoTest DeepSeek V4 Pro live
Send a message and watch the model respond. Multi-turn — it remembers the conversation.
More reasoning models
Nemotron Super 49B
NVIDIA
NVIDIA's reasoning-tuned Nemotron model — strong math, logic and agentic tool-use at an efficient size.
nvidia/llama-3.3-nemotron-super-49b-v1.5Input / 1M
$0.35
Output / 1M
$0.40
Nemotron Nano 9B
NVIDIA
Compact reasoning model that punches above its weight on math and coding benchmarks. Fast and cheap.
nvidia/nvidia-nemotron-nano-9b-v2Input / 1M
$0.10
Output / 1M
$0.10