Ollama Cloud
GlobalOllama Cloud is a cloud model inference subscription service by Ollama, billing per-token from monthly included credits, covering 20+ open-source models including DeepSeek V4, GLM-5.3, Kimi K3, MiniMax M3, Qwen3.5, with unified local+cloud entry point, zero data retention (ZDR), primarily hosted in the United States.
Verified 2026-09-12
Ollama Cloud Plans
FreeStarter usage credits (starter models only)
Free
Starter model subset1 concurrent request
- ✓1 concurrent request
- ✓Starter models only; add credits to unlock all models
- ✓Run models locally, unlimited
- ✓No service fees
- ✓Monthly reset, no rollover
$20USD/month ($200/yr annually)$60 of usage credits per month
Pro
DeepSeek V4-Pro/Flash, GLM-5.3/5.3-Flash/5.2/5.1, Kimi K3/K2.7-Code/K2.6, MiniMax M3/M2.7, Qwen3.5:397b, Gemma4, GPT-OSS, Nemotron-3 series and 20+ models3 concurrent requests
- ✓3 concurrent requests
- ✓$60 monthly usage credits, billed at per-token rates
- ✓Access to larger pro models
- ✓Continue per-token after credits exhausted
- ✓Monthly reset, no rollover; 90% usage alert
$100USD/month$300 of usage credits per month
Max
Same as Pro, with early access to newest models10 concurrent requests
- ✓10 concurrent requests
- ✓$300 monthly usage credits
- ✓Early access to newest models
- ✓Everything in Pro
- ✓DeepSeek V4 off-peak half price (outside UTC 12:00-18:00)
$500USD/month$1,000 shared usage credits per month
Team
Same as Max10 concurrent requests
- ✓Unlimited users
- ✓$1,000 shared credits per month
- ✓10 concurrent requests
- ✓Centralized billing and administration
- ✓Priority support