Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
#1Ollama records 9,421,973 monthly visits with +4.3% month-over-month growth and Free, Freemium, Paid pricing. RightNow Inference (RunInfra) records 18,110 monthly visits with -22.6% growth and Free Trial, Paid, Contact for Pricing pricing.

Open models served fast, with warm-cache routing for agents
| Dimension / Metric | ![]() | |
|---|---|---|
| Official Domain | ollama.com | runinfra.ai |
| Pricing Model | Free, Freemium, Paid | Free Trial, Paid, Contact for Pricing |
| Monthly Visits | 9.42M (9,421,973) | 18.11K (18,110) |
| MoM Traffic Delta |
| +389.71K (+4.3%) |
| -5.28K (-22.6%) |
| Primary Market & Share | 🇨🇳 China (15.9%) | 🇮🇳 India (48.4%) |
|---|
| Direct Visits / mo | 4.02M | 7.78K |
|---|
| User Rating | 4.8 | 4.4 |
|---|
| Supported Platforms | app, open-source, website | Website |
|---|
Run and build with open AI models locally or in the cloud
Install once and pull open-weight models by name; Ollama handles weights, quantization and versioning for you.
A built-in server exposes a straightforward REST API, so scripts, editors and agents can talk to local models with minimal setup.
Route requests to hosted open models when your laptop cannot hold the checkpoint you need, with per-token pricing and concurrency tiers.
Access families such as Llama, Qwen, DeepSeek, Gemma, Mistral and gpt-oss from a single interface.

Open models served fast, with warm-cache routing for agents
Automatically keeps repeated calls from one agent session on the replica that already holds its context, reaching reported cache-hit rates around 99% and cutting effective input costs.
One API key works with both the OpenAI and Anthropic SDKs, so existing agent code can switch providers with minimal changes.
Serves open-weight models with published pricing, tool calling, JSON mode, streaming and image-input capabilities, plus live output-speed and cache metrics.
Cache hits appear in usage and are billed at the cached rate, with a published measurement methodology and per-model effective input rates.
Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
#1SpecialistCloud API gateway providing instant access to thousands of models, trading local hardware privacy for cloud compute.
#2
Free / Open-sourceGoogle's family of lightweight, open-weight AI models


Ultra-fast AI inference on the LPU and LPX platform

Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control

Free / Open-sourceOpen-source platform for building visual agentic workflows and RAG pipelines using local or cloud models.


Free / Open-sourceFeature-rich self-hosted web chat interface designed to manage and query local models like Ollama.
Free / Open-sourcePrivacy-first desktop app focused specifically on local document chat and RAG, unlike Ollama's general-purpose CLI runtime.

Low-cost serverless inference APIs for 200+ open models

Free / Open-sourceDevelopment framework for connecting local models to external document stores and structured data sources.

Free / Open-sourceOpen-source desktop app for running models locally with a graphical interface, but heavier than Ollama's lightweight CLI.
Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
SpecialistCloud API gateway providing instant access to thousands of models, trading local hardware privacy for cloud compute.
Free / Open-sourceGoogle's family of lightweight, open-weight AI models
Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control
Free / Open-sourceOpen-source platform for building visual agentic workflows and RAG pipelines using local or cloud models.
Free / Open-sourceFeature-rich self-hosted web chat interface designed to manage and query local models like Ollama.
Free / Open-sourcePrivacy-first desktop app focused specifically on local document chat and RAG, unlike Ollama's general-purpose CLI runtime.
Free / Open-sourceDevelopment framework for connecting local models to external document stores and structured data sources.
Free / Open-sourceOpen-source desktop app for running models locally with a graphical interface, but heavier than Ollama's lightweight CLI.