Model catalog
One endpoint, every model. Compare context windows, capabilities and real per-token pricing side by side, then swap the model string in your request — nothing else changes.
- 472
- Models
- 48
- Providers
- 4
- Free to try
- $0.0001
- Cheapest input / 1M
8 of 472 models
LanguageNVIDIA Nemotron 3.5 Super VL
nvidia/nemotron-3.5-super-vl
NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, and document understanding. Its hybrid Mamba-2, attention, and Mixture-of-Experts architecture has 120B total parameters with 12B active per token. Baseten serves text and image inputs with up to one million tokens of context for long conversations and agent workflows.
- Context
- 1.0M
- In / 1M
- $0.200
- Out / 1M
- $0.500
- Reasoning
- Tool use
- Vision
- +3
- Language
Nemotron 3.5 Lightning Free
nvidia/nemotron-3.5-lightning-free
Nemotron 3.5 Lightning is an open-weight reasoning and chat model for long-running agents, sub-agent work, chatbots, and RAG systems. The model has 30B parameters with 3B active per token, in a hybrid Mixture-of-Experts design that interleaves Mamba-2 and MoE layers with a few attention layers. It has a 1M token context window and supports tool calling and structured outputs. The provider may retain prompts and responses for model improvement.
- Context
- 1M
- In / 1M
- Free
- Out / 1M
- Free
- Reasoning
- Tool use
- Structured output
- +2
- Language
Nemotron 3.5 Lightning 30B
nvidia/nemotron-3.5-lightning
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA. The model employs a hybrid Mixture-of-Experts architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. The Lightning 3.5 model is released alongside a number of speculative decoding methods for faster text generation. The model has 3B active parameters and 30B parameters in total.
- Context
- 262K
- In / 1M
- $0.050
- Out / 1M
- $0.200
- Reasoning
- Tool use
- Implicit caching
- +2
- Language
Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b
A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.
- Context
- 1M
- In / 1M
- $0.600
- Out / 1M
- $2.40
- Reasoning
- Tool use
- Structured output
- +2
- Language
NVIDIA Nemotron 3 Super 120B A12B
nvidia/nemotron-3-super-120b-a12b
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. It delivers up to 7x higher throughput, providing fast, cost-efficient inference for agentic tasks. Additionally, a long context window gives the model long-term memory, preventing AI agents from losing focus on long, multi-step tasks and ensuring high-accuracy results. Fully open with weights, datasets, and recipes, Super allows easy customization and secure deployment anywhere.
- Context
- 256K
- In / 1M
- $0.150
- Out / 1M
- $0.650
- Reasoning
- Tool use
- Structured output
- +1
- Language
Nvidia Nemotron Nano 12B V2 VL
nvidia/nemotron-nano-12b-v2-vl
The model is an auto-regressive vision language model that uses an optimized transformer architecture. The model enables multi-image reasoning and video understanding, along with strong document intelligence, visual Q&A and summarization capabilities.
- Context
- 131K
- In / 1M
- $0.200
- Out / 1M
- $0.600
- Reasoning
- Tool use
- Vision
- +1
- Language
Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3b
NVIDIA Nemotron 3 Nano is an open reasoning model optimized for fast, cost-efficient inference. Built with a hybrid MoE and Mamba architecture and trained on NVIDIA-curated synthetic reasoning data, it delivers strong multi-step reasoning with stable latency and predictable performance for agentic and production workloads.
- Context
- 262K
- In / 1M
- $0.050
- Out / 1M
- $0.200
- Reasoning
- Tool use
- open weights
- Language
Nvidia Nemotron Nano 9B V2
nvidia/nemotron-nano-9b-v2
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.\
- Context
- 131K
- In / 1M
- $0.060
- Out / 1M
- $0.230
- Reasoning
- Tool use
- open weights