Chutes records 250,187 monthly visits with -15.2% month-over-month growth and Paid pricing. RightNow Inference (RunInfra) records 18,110 monthly visits with -22.6% growth and Free Trial, Paid, Contact for Pricing pricing.
Serverless, decentralized inference for open-source AI models
Open models served fast, with warm-cache routing for agents
| Dimension / Metric | | |
|---|---|---|
| Official Domain | chutes.ai | runinfra.ai |
| Pricing Model | Paid | Free Trial, Paid, Contact for Pricing |
| Monthly Visits | 250.19K (250,187) | 18.11K (18,110) |
| MoM Traffic Delta | -44.93K (-15.2%) | -5.28K (-22.6%) |
| Primary Market & Share | 🇺🇸 United States (58.1%) | 🇮🇳 India (48.4%) |
| Direct Visits / mo | 187.04K | 7.78K |
| User Rating | 4.7 | 4.4 |
| Supported Platforms | Website | Website |
Serverless, decentralized inference for open-source AI models
Drop-in compatibility means you change the base URL and key, and your existing OpenAI-style SDK code keeps working.
Run LLMs, image, video, speech, music, embedding, and moderation models, or bring your own code and fintune-style workloads.
Models are held permanently warm, so production traffic does not wait for a container to spin up.
Selected models run inside trusted execution environments for private, isolated inference.
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.
Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
Aggregates hundreds of models behind one API gateway with intelligent routing, but focuses less on dedicated decentralized hosting.
Aggregates hundreds of models behind one API gateway with intelligent routing, but focuses less on dedicated decentralized hosting.
Free / Open-sourceRun and build with open AI models locally or in the cloud
Free / Open-sourceRun and build with open AI models locally or in the cloud
Free / Open-sourceGoogle's family of lightweight, open-weight AI models
Free / Open-sourceGoogle's family of lightweight, open-weight AI models
Ultra-fast AI inference on the LPU and LPX platform
SpecialistSpecializes in high-speed serverless inference for generative media models rather than general text LLMs.
SpecialistSpecializes in high-speed serverless inference for generative media models rather than general text LLMs.
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.
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
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control
Excels at running and fine-tuning diverse machine learning models via API, but uses a distinct serverless architecture.
Excels at running and fine-tuning diverse machine learning models via API, but uses a distinct serverless architecture.
Free / Open-sourceFocuses on memory-efficient model fine-tuning and local execution rather than a hosted decentralized inference cloud.
Free / Open-sourceFocuses on memory-efficient model fine-tuning and local execution rather than a hosted decentralized inference cloud.
Delivers exceptional inference throughput and fine-tuning for open models, though pricing and supported model catalogs vary.
Free / Open-sourceActs as an open-source proxy gateway to unify multiple providers, requiring you to bring your own backend compute.
