You only pay what you use. In euros, no surprises.

DeepSeek V4 Pro

1.6T MoE on 8× B200. Full-power reasoning.

743B NVFP4 on 8× B200. Generalist and coding with tool calling.

DeepSeek V4 Flash

1.6T MoE on 2× B200. High throughput, 524K context.

Qwen3.6 27B

27B dense. Strong at coding and agents, with tool calling.

Qwen3 14B

14B FP8. Reasoning with a configurable thinking budget.

Qwen3.5 9B

9B ultra-light. Fast and cost-effective, with tool calling.

Gemma 4 26B A4B

Multimodal MoE, ~3.8B active. Vision, reasoning and tools.

Nemotron Nano 12B VL

Vision-language model for OCR and document understanding. 128K context, up to 4 images per prompt.

Qwen3-VL 32B OCR

Vision-language model for OCR and document understanding. 64K context, up to 4 images per prompt.

Nemotron 3.5 Lightning 30B

MoE + Mamba-2 hybrid, ~3B active. Reasoning and tool calling, 128K context.