Train and scale AI on NVIDIA VR200 NVL 72, GB300 NVL 72, B300, B200, H200, H100, and and more GPUs. Launch on-demand instances or reserve a cluster. Get started. Inference platform · OpenAI-compatible API · Gpu Cloud · Open Source · Serverless · Training

Intelligence vs Price

Best value among Lambda models on this chart: DeepSeek V3 324 · Qwen3 32B · Llama 3.1 8B Instruct (and 1 more on the dashed frontier). Prices use each model's lowest available Lambda price across regions. Hover any dot for full pricing, or click a creator in the legend to isolate.

Language Models
Intelligence
Blended Price, $
Log X

Lambda models

20 models in Global, 20 with pricing
All Model Types
All Creators
US Dollar ($)
Per 1M tokens
Input/1M
to
Output/1M
to
Select
Model
Creator
Input Price, $
Output Price, $
Context
Max Output
Inference Providers
Intelligence
Coding
DeepSeek V3 324DeepSeek logoDeepSeek0.20.6164K66K#1#1
Qwen3 32BAlibaba logoAlibaba0.050.1131K41K#2#2
Llama 3.3 70B InstructMeta logoMeta0.120.3131K120K#3#3
Llama 3.1 405B InstructMeta logoMeta0.80.8131K16K#4N/A
Llama 3.1 Nemotron 70B InstructNVIDIA logoNVIDIA0.120.3131K16K#6N/A
Llama 3.1 8B InstructMeta logoMeta0.0250.04200K128K#5#4
Qwen2.5 Coder 32B InstructAlibaba logoAlibaba0.050.1131K29K#7N/A
Llama 3.1 70B InstructMeta logoMeta0.120.3131K16K#8N/A
Llama 3.2 3B InstructMeta logoMeta0.0150.025131K118K#9N/A
LFM 40BLiquid AI logoLiquid AI0.10.2131KN/A#10N/A
DeepSeek Llama3.3 70BDeepSeek logoDeepSeek0.20.6131KN/AN/AN/A
DeepSeek R1 528DeepSeek logoDeepSeek0.20.6164K33KN/AN/A
DeepSeek R1 671BDeepSeek logoDeepSeek0.80.8131KN/AN/AN/A
Hermes 3 405BNous Research logoNous Research0.80.8131KN/AN/AN/A
Hermes 3 70BNous Research logoNous Research0.120.3131KN/AN/AN/A
Hermes 3 8BNous Research logoNous Research0.0250.04131KN/AN/AN/A
LFM 7BLiquid AI logoLiquid AI0.0250.04131KN/AN/AN/A
Llama 3.2 11B Vision InstructMeta logoMeta0.0150.025131K16KN/AN/A
Llama 4 17B Maverick InstructMeta logoMeta0.050.11.0M16KN/AN/A
Llama 4 17B Scout InstructMeta logoMeta0.050.110.0M16KN/AN/A