Packaging change·Jul 20 → Jul 27, 2026·Week 31, 2026·Cloud & DevOps
Crusoe adds Nemotron 3 Ultra 550B to Serverless Inference at $1/$3.20 per 1M ...
New Nemotron 3 Ultra 550B model added to the Serverless Inference pricing table, priced at $1.00 input / $3.20 output / $0.25 cached per 1M tokens
What changed
New add-on
New Nemotron 3 Ultra 550B model added to the Serverless Inference pricing table, priced at $1.00 input / $3.20 output / $0.25 cached per 1M tokens
Before and after
Jul 20, 2026 vs Jul 27, 2026Pulse.
100%
What changed
New Nemotron 3 Ultra 550B model added to the Serverless Inference pricing table, priced at $1.00 input / $3.20 output / $0.25 cached per 1M tokens
Sign in to view the full comparison
See the before/after screenshots and every marked-up change.
Week 30, 2026 · Crusoe: Launched Serverless Fine-Tuning + Self-Serve DeploymentsCrusoe: GPT-OSS 20B fine-tuning price $0.40->$2.50 + 2 more changes · Week 40, 2026
More from Crusoe
Full history →- Week 41, 2026·packagingCrusoe drops Kimi K2.6 ($0.70/$3.50 per 1M) from Managed Inference lineup
- Week 40, 2026·improvedCrusoe: GPT-OSS 20B fine-tuning price $0.40->$2.50 + 2 more changes
- Week 30, 2026·improvedCrusoe: Launched Serverless Fine-Tuning + Self-Serve Deployments
- Week 27, 2026·improvedCrusoe adds GLM 5.2 and Kimi K2.6 to Managed Inference lineup