AI Tools
Ollama
Ollama: precios, capacidades, actualizaciones y alternativas, leídos en las páginas del propio desarrollador.

En inglés
Key facts
- Price
- Free plan · paid plans from $20/mo · $16.67/mo billed yearly Read on ollama.com
- Free plan
- Yes Read on ollama.com
- Platforms
- macOS · Windows · Linux · CLI · API Read on ollama.com
- API
- Yes Read on ollama.com
- Open source
- Yes · MIT Read on github.com
- Latest version
- v0.40.17
- Last update
- 16 Nov 2026 Read on github.com
- Prices checked
- 26 Oct 2026 Read on ollama.com
Ollama lets developers download and run open models on macOS, Windows, or Linux, or use hosted models through Ollama’s cloud. Its CLI connects models to coding agents and other tools, and its REST API lets applications run and manage models.
Running models on your own hardware is unlimited; cloud model use is billed per token. Paid plans include monthly usage credits, and local performance depends on the computer’s hardware. Ollama is infrastructure for running models, not a single fixed AI model.
- Category
- Developer Tools
- Read from the maker’s pages
- 2026-11-18
Company
Features
- Download and run open models on your own computer.
- Use hosted cloud models without downloading them.
- Connect coding tools through the ollama launch command.
- Run and manage models through a REST API.
- Use OpenAI- and Anthropic-compatible API integrations.
- Run models that support image understanding and tool calling.
- Generate speech with supported models.
- Ollama's source repository is available under the MIT license.
Use cases
- Run an open model locally for private development or testing.
- Connect a model to a coding agent such as Claude Code or Codex.
- Add model inference to an application through the REST API.
- Use cloud models when a local computer cannot run a chosen model.
- Generate spoken output with a supported speech model.
Pricing
Free plan · paid plans from $20/mo · $16.67/mo billed yearly
- Prices checked
- 2026-10-26
Free
free
- Run models locally
- Starter usage credits included
- Includes access to starter models
- Add credits to unlock all models
- No service fees
- 1 concurrent request
Pro
$20/mo
- $20 / mo.
- $200/yr billed annually
- $16.67 / mo. billed annually
- For shorter, well-defined day-to-day tasks
- $60 of usage credits per month
- Access to larger pro models
- Run multiple models concurrently
- Fast mode (coming soon)
- 3 concurrent requests
Max
$100/mo
- $100 / mo.
- For power users who run multiple agents simultaneously
- $300 of usage credits per month
- Early access to the newest models
- 10 concurrent requests
Team
from $500/mo
- $500 / mo.
- Unlimited users
- $1,000 of usage credits per month, shared across the team
- Centralized billing and administration
- Priority support
- Shared projects, skills, and instructions (coming soon)
- 10 concurrent requests
Enterprise
price on request
- Model access controls
- Limit team access to specific models
- Set cost budgets for users and API keys
- Private Slack channel with dedicated support
- Custom security questionnaires
Capabilities
- Choice of models — “Use any cloud model with pay-as-you-go usage credits.” source
- Self-hosted — “Run models locally” source
- No code retained — “When Ollama partners with providers, we require no logging, no training, and zero data retention policies in place.” source
- API — “Works with popular coding agents, including Claude Code and Codex, plus an API for your own tools” source
- Runs models for you — “Ollama hosts models and compute resources primarily in the United States.” source
Latest updates
- Version 0.40.17
Improved ChatGPT CLI restore/restart, OpenCode thinking settings, Vulkan GPU mmap, and concurrent MLX generation; updated llama.cpp and MLX.
- Version 0.40.17
Improved ChatGPT CLI restore and restart, OpenCode settings, Vulkan mmap, concurrent MLX generation, and updated llama.cpp and MLX.
- Version 0.40.16
Added Ripple Preview; reduced Qwen3.8 Flash Next memory use on Apple silicon; updated CLI, API, and Windows on ARM CUDA support.
- Version 0.40.15
Added support for MiMo V2.6 and AutoTrust decision models, plus Kimi Code CLI launch and kimi-cli migration.
- Version 0.40.15
Loads bundled CUDA libraries in-process on Linux and adds MiMo V2.6 model support.
Where it works
macOS · Windows · Linux · CLI · API
Alternatives to Ollama
- LM Studio
LM Studio downloads and runs language models on your computer, with chat, document queries, and local APIs.
- Unsloth
Free, open-source desktop software for running and training AI models locally, with tools for image generation, web search and coding agents.
- LocalAI
LocalAI runs open AI models on your own hardware, with a web interface and APIs for chat, images, speech, video, and more.
- Jan
Jan is an open-source desktop app for running AI models locally or connecting to cloud providers, with tools for research, files and coding.
- Open WebUI
Self-hosted AI interface for chatting with local or cloud models, searching documents, and connecting tools.
- Liquid Foundation Models
Liquid Foundation Models are open-weight AI models for text, vision, audio, and decision tasks, usable locally or through Liquid's API.
Questions about Ollama
Is Ollama free?
Yes. Ollama has a free plan. Paid plans start at $20/mo. Prices checked on 26 Oct 2026.
How much does Ollama cost?
The plans on the maker’s pricing page: Free (free), Pro ($20/mo), Max ($100/mo), Team (from $500/mo) and Enterprise (price on request). Prices checked on 26 Oct 2026.
Does Ollama have an API?
Yes. The maker’s pages state that Ollama has an API. Read on the maker’s pages on 18 Nov 2026.
Which platforms does Ollama run on?
Ollama runs on macOS, Windows, Linux, CLI and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.
Is Ollama open source?
Yes. The code of Ollama is published at github.com/ollama/ollama under the MIT licence. Read on the maker’s pages on 18 Nov 2026.
Is Ollama still available?
Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Ollama has ended.
What changed recently in Ollama?
The latest entry in its maker’s changelog: 16 Nov 2026, “Version 0.40.17”. Before it: 10 Nov 2026, “Version 0.40.17”. Changelog checked on 19 Nov 2026.
Sources
- https://ollama.com/pricing — Official pricing tiers, prices, usage credits, and cloud model billing.
- https://ollama.com/ — Product overview describing local and cloud access to open models.
- https://ollama.com/download — Official downloads and local, cloud, CLI, and API usage information.
- https://ollama.com/blog/open-models-long-horizon-agents — Latest dated blog post read; discusses prefix caching and agent workflows.
- https://github.com/ollama/ollama/releases — Official repository release listing identifies v0.40.17 as a pre-release.
- https://github.com/ollama/ollama — Official repository identifies the MIT license and documents the REST API.