Skip to content

Catalogdev-infra

Ollama

situationalBlueshift — gaining momentum

Run open models locally (CLI, app, API) — optional Ollama Cloud Pro/Max for hosted large models.

Visit ollama.com →Add to kitOpen in Noemium

ledger entry · observed by @whysanesanders

The local-model default: one CLI, an OpenAI-shaped API, desktop apps, and you keep weights on disk. Cloud Pro is a separate $20 meter with 5-hour and weekly caps; Max is capacity-paused for new buyers. Local is the product; cloud is overflow. Not a quality claim about any one model.

Strengths

  • Local-model default with one CLI, an OpenAI-shaped API, and desktop apps.
  • You keep model weights on disk and run inference on your own hardware.
  • Free local runtime with no usage caps beyond what your machine can handle.

Known limitations

  • Local quality and speed are your GPU; Ollama is the runner, not the weights.
  • Cloud usage is token-and-model-weighted, not a flat token bucket.
  • New Max subscriptions paused while they add capacity (existing Max kept).
  • Cloud hosts primarily in the US (EU/Singapore overflow); data-residency still a question.

Use it when

  • Offline or private inference where data never leaves the machine.
  • Prototyping with open weights before deciding on cloud spend.

Skip it when

  • Your GPU cannot deliver the quality or speed the use case demands.
  • You need guaranteed data residency from a cloud region.
  • You were planning to sign up for Max while new subscriptions are paused.

Buy-check

  • ·Price — freemium, local runtime $0 unlimited on your hardware; Cloud Free light usage; Pro $20/mo ($200/yr); Max $100/mo (new Max sign-ups paused) as of 2026-08-19. Open the pricing page, not a screenshot.
  • ·Free tier — Free tier exists — burn it first.
  • ·Cancel fallout — What happens to your data/projects on cancel — check the ToS, not the FAQ.
  • ·Seat math — Per-seat pricing multiplies quietly. Count seats before the annual plan.
  • ·Who skips it — Also skipped when: Your GPU cannot deliver the quality or speed the use case demands.; You need guaranteed data residency from a cloud region..

Price trailchangelog →

No price move in this repo yet.

Facts

pricing
freemium1
price note
local runtime $0 unlimited on your hardware; Cloud Free light usage; Pro $20/mo ($200/yr); Max $100/mo (new Max sign-ups paused)
free tier
yes
open source
yes
api
yes
self-host
yes
category
dev-infra
evidence
source-verified
Models
BYOK

Data: trains on inputs unknown · local processing yes

Sources

  1. 1ollama.com/pricing[snapshot]
  2. 2github.com/ollama/ollama[snapshot]

No source, no number.

Edit this page on GitHub

Similar joball alternatives →

Compare:Ollama vs vLLMOllama vs Open WebUI

toolverdictpriceossself-host
Ollamasituationalfreemiumyesyes
Modalshipfreemiumnono
OpenRoutershipfreemiumnono
Replicateshippaidnono

Facts from the catalog files — not scores you can buy. Quality and speed stay in the briefing, not in a fake 1–5 grid.

Modal
dev-infraship

Modal

Serverless GPU and compute platform for running ML and AI workloads.

APIFREE TIER

freemiumfree tier ($30/mo compute); pay-as-you-go beyond

Blueshift — gaining momentum
OpenRouter
dev-infraship

OpenRouteranchor

One API for every major model — unified billing, fallbacks and routing.

APIFREE TIER

freemiumpay-per-token pass-through plus a small fee

Blueshift — gaining momentum
Replicate
dev-infraship

Replicate

Run any community model via API — pay per second, no GPU wrangling.

API

paidpay per run; image models from ~$0.003/image

Steady momentum