Ollama Cloud
A cloud-based large model inference service launched by Ollama, supporting access to more than 20 open-source large models—including DeepSeek, GLM, and Kimi—under a single subscription. The service uses transparent per-token pricing and provides an OpenAI-compatible API interface.
Timeline (last 90 days)
Ollama Cloud provides newer models such as GLM and DeepSeek Flash in the cloud, and using cloud models requires registering and logging into an Ollama account.
The Peak hours correspond to midnight to early morning in Beijing time, allowing Chinese users to avoid peak pricing during the day and benefit from the time zone advantage.
There are three ways to connect to Ollama Cloud: running directly in the terminal, connecting via Ollama Launch to an Agent, or using it as a standard API Key.
Ollama Cloud's Peak hours are UTC 12:00 to 18:00 on weekdays, during which some model prices double.
Ollama Cloud uses explicit per-token pricing and has eliminated service fees.
A single Ollama Cloud subscription grants access to more than 20 open-source large models including DeepSeek, GLM, Kimi, and Qianwen.
Ollama Cloud runs native open-source weights directly using dedicated computing resources, hosted in partnership with NVIDIA cloud service providers, rather than reselling official APIs.
All models on Ollama Cloud support tool calling, with context windows ranging from 131K to 1M.
DeepSeek Flash is currently the fastest-growing model on Ollama Cloud.
Since the beginning of the year, overall token consumption on Ollama Cloud has grown 150-fold, with per-user token usage achieving approximately a 5-fold leap.
13 more timeline events
All Facts (10)
Ollama Cloud provides newer models such as GLM and DeepSeek Flash in the cloud, and using cloud models requires registering and logging into an Ollama account.
50%UnverifiedOllama Cloud runs native open-source weights directly using dedicated computing resources, hosted in partnership with NVIDIA cloud service providers, rather than reselling official APIs.
50%UnverifiedAll models on Ollama Cloud support tool calling, with context windows ranging from 131K to 1M.
50%UnverifiedThere are three ways to connect to Ollama Cloud: running directly in the terminal, connecting via Ollama Launch to an Agent, or using it as a standard API Key.
50%UnverifiedThe Peak hours correspond to midnight to early morning in Beijing time, allowing Chinese users to avoid peak pricing during the day and benefit from the time zone advantage.
50%UnverifiedOllama Cloud uses explicit per-token pricing and has eliminated service fees.
50%UnverifiedA single Ollama Cloud subscription grants access to more than 20 open-source large models including DeepSeek, GLM, Kimi, and Qianwen.
50%UnverifiedThe shift in billing model from resource-duration-based to token-usage-based is a process by which service providers refine cost accounting and move toward a predictable subscription revenue model
50%UnverifiedThe old Ollama Cloud plan was essentially billed by GPU runtime duration rather than by token
50%UnverifiedThe low unit price of the old model was premised on users maximally saturating their GPU time quota, while the new model's precise per-token billing eliminates the diminishing marginal cost advantage for heavy users
50%