$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3

Provider details

Crusoe

Learn more about this provider, then browse the models currently listed under it.

crusoecrusoe

Provider docs

Latest news about Crusoe

Crusoe

Official sourceAnnouncement

Crusoe announced on July 7, 2026 that Serverless Fine-Tuning and Self-Serve Deployments are now generally available within Crusoe Intelligence Foundry, the managed AI platform of Crusoe Cloud. The launch is framed as a complete path from proprietary data to production-ready models on purpose-built AI infrastructure, el Self-Serve Deployments are positioned as the inference companion to Fine-Tuning, providing Flexible Inference immediately after training and giving data scientists and ML engineers a unified lifecycle within Crusoe Intelligence Foundry. The announcement describes Crusoe Serverless Fine-Tuning and Self-Serve Deployments

Crusoe

Official sourceRelease Notes

The Crusoe Cloud changelog dated September 6, 2026 (entries through September 12, 2026) records several concrete, dated platform changes within Crusoe Intelligence Foundry. Most notably, on September 12, 2026 a breaking Serverless Inference model deprecation removed Z.ai GLM-5.1, Z.ai GLM-5.2, DeepSeek V3, Qwen3 235B A Beyond model availability, the changelog lists operational platform updates: on September 1, 2026 bug reports became triggerable, trackable, and downloadable programmatically via new `crusoe diagnostics vm` commands and an API; on August 31, 2026 sign-up added six-digit email verification codes; on August 26, 2026 Serv

About Crusoe

What they do

Crusoe builds energy-first AI data centers and cloud infrastructure and offers managed training, fine-tuning, and inference services.

How they were founded

Crusoe was founded in 2018 by Chase Lochmiller and Cully Cavness, initially using otherwise wasted natural gas to power high-performance computing.

Sources

crusoe.ai docs.crusoecloud.com

Quick Info

Organization: Crusoe Energy Systems LLC
Headquarters: Denver, Colorado, United States
SDK package: @ai-sdk/openai-compatible
Synced at: Aug 13, 2026

Models served

11 models available through Crusoe

These model results are sorted newest first so you can quickly see the latest options from this provider.

Crusoeglm

GLM-5.2

zai/GLM-5.2CrusoeReleased Jun 13, 20261,000,000 token context windowIn $1.40 · Out $4.40

Input

Output

Crusoenemotron

Nemotron 3 Nano Omni 30B A3B Reasoning

nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3BCrusoeReleased Apr 28, 2026256,000 token context windowIn $0.30 · Out $1.83

Input

Output

Crusoekimi-k2

Kimi K2.6

moonshotai/Kimi-K2.6CrusoeReleased Apr 21, 2026262,144 token context windowIn $0.70 · Out $3.50

Input

Output

Crusoeglm

GLM-5.1

zai/GLM-5.1CrusoeReleased Apr 7, 2026200,000 token context windowIn $1.20 · Out $4.40

Input

Output

Crusoegemma

Gemma 4 31B IT

google/gemma-4-31b-itCrusoeReleased Apr 2, 2026262,144 token context windowIn $0.14 · Out $0.40

Input

Output

Crusoenemotron

Nemotron 3 Super 120B A12B

nvidia/NVIDIA-Nemotron-3-Super-120B-A12BCrusoeReleased Mar 11, 2026262,144 token context windowIn $0.30 · Out $2.40

Input

Output

Crusoenemotron

Nemotron 3 Nano 30B A3B

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3BCrusoeReleased Dec 15, 2025262,144 token context windowIn $0.05 · Out $0.20

Input

Output

Crusoegpt-oss

GPT OSS 120B

openai/gpt-oss-120bCrusoeReleased Aug 5, 2025131,072 token context windowIn $0.05 · Out $0.20

Input

Output

Crusoeqwen

Qwen3 235B-A22B Instruct 2507

Qwen/Qwen3-235B-A22B-Instruct-2507CrusoeReleased Jul 21, 2025262,144 token context windowIn $0.22 · Out $0.80

Input

Output

Crusoedeepseek

DeepSeek V3 0324

deepseek-ai/DeepSeek-V3-0324CrusoeReleased Mar 24, 2025163,840 token context windowIn $0.50 · Out $1.50

Input

Output

Crusoellama

Llama-3.3-70B-Instruct

meta-llama/Llama-3.3-70B-InstructCrusoeReleased Dec 6, 2024128,000 token context windowIn $0.25 · Out $0.75

Input

Output