Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
#1DeepInfra records 457,810 monthly visits with -8.9% 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.

Open models served fast, with warm-cache routing for agents
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | deepinfra.com | runinfra.ai |
| Pricing Model | Paid | Free Trial, Paid, Contact for Pricing |
| Monthly Visits | 457.81K (457,810) | 18.11K (18,110) |
| MoM Traffic Delta |
|---|
| -44.51K (-8.9%) |
| -5.28K (-22.6%) |
| Primary Market & Share | 🇺🇸 United States (15.3%) | 🇮🇳 India (48.4%) |
|---|
| Direct Visits / mo | 237.82K | 7.78K |
|---|
| User Rating | 4.6 | 4.4 |
|---|
| Supported Platforms | Website | Website |
|---|

Low-cost serverless inference APIs for 200+ open models
Access text, image, speech, music and video models from multiple families through one consistent API, with task- and family-based browsing.
Per-million-token rates with input, output and cached-input breakdowns shown up front, including current discounts on many models.
Rent data-center GPUs by the instance-hour when you need raw compute for fine-tuning, custom serving or burst workloads.
Inputs and outputs are not retained, and the platform holds SOC 2 and ISO 27001 certifications for information security.

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.
#1
SpecialistProvides direct developer API access to Google's proprietary Gemini models rather than community open-weight models.
#2Acts as an API router across multiple hosting providers rather than hosting models directly like DeepInfra.
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


Ultra-fast AI inference on the LPU and LPX platform

SpecialistOptimized specifically for ultra-fast generative media and vision model inference rather than general-purpose 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.
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control

Stronger ecosystem for deploying custom machine learning models and fine-weights, but generally higher inference pricing.
Provides a unified AI inference platform across multiple modalities via an OpenAI-compatible API.

Focuses on lightning-fast serverless inference for generative media and text models with developer-first pricing.
Free / Open-sourceHigh-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs.
SpecialistProvides direct developer API access to Google's proprietary Gemini models rather than community open-weight models.
Acts as an API router across multiple hosting providers rather than hosting models directly like DeepInfra.
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
SpecialistOptimized specifically for ultra-fast generative media and vision model inference rather than general-purpose 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.
One OpenAI-compatible gateway for adaptive LLM routing, guardrails, and spend control
Stronger ecosystem for deploying custom machine learning models and fine-weights, but generally higher inference pricing.
Provides a unified AI inference platform across multiple modalities via an OpenAI-compatible API.