Photon

Photon

Moondream
+
+

Related Products

  • Runpod
    230 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Gemini Enterprise Agent Platform
    1,161 Ratings
    Visit Website
  • Google AI Studio
    41 Ratings
    Visit Website
  • CredentialStream
    190 Ratings
    Visit Website
  • FAMCare Human Services
    32 Ratings
    Visit Website
  • Cloudflare
    2,048 Ratings
    Visit Website
  • KrakenD
    76 Ratings
    Visit Website
  • Admin By Request Endpoint Privilege Management
    105 Ratings
    Visit Website
  • Chainstack
    34 Ratings
    Visit Website

About

Cheaper Inference is an OpenAI-compatible API gateway that provides access to AI models from multiple providers through a single API key, without requiring users to change their request format. Developers can switch by replacing the provider base URL and API key while keeping the same model, messages, tools, streaming settings, and response handling. It supports text and image models, vision-capable chat requests, streaming, prompt caching, reasoning controls, and temporary image uploads for larger vision payloads. Models are selected per request, and the catalog can be filtered by type, vision, reasoning, streaming, or provider. Automatic retries handle network and provider failures, while eligible fallback routes can be tried before a request fails. Every request is visible in History, giving teams a record of request volume, token usage, and operational activity.

About

Photon is Moondream’s official high-performance inference engine, designed to run vision-language models efficiently across cloud, desktop, and edge environments while delivering real-time performance for production AI systems. It is built as a custom inference layer tightly integrated with the Moondream model architecture, using optimized scheduling, native image processing, and purpose-built CUDA kernels to maximize speed and efficiency. This co-designed approach allows Photon to significantly reduce latency compared to traditional VLM setups, enabling responsive interactions on edge devices and real-time throughput on server-grade hardware. It supports deployment across a wide range of NVIDIA GPUs, from embedded systems like Jetson devices to high-end multi-GPU servers, making it adaptable for diverse operational needs. It includes production-ready features such as automatic batching, prefix caching, and memory-efficient attention mechanisms.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Audience

AI teams and developers in need of a tool to access and route requests across multiple AI models and providers through one OpenAI-compatible API

Audience

AI engineers and computer vision teams who need to deploy real-time, high-performance vision-language models across cloud, edge, and on-prem environments

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

Pricing

$0.48 per output
Free Version Not Supported
Free Trial Not Supported

Pricing

$300 per month
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Supported
In Person Not Supported

Company Information

Keak
United States
cheaperinference.com

Company Information

Moondream
Founded: 2024
United States
moondream.ai/p/photon

Alternatives

Alternatives

OptoCompiler

OptoCompiler

Synopsys

Categories

AI Gateways Supported
AI Inference Supported

Categories

AI Inference Supported

Integrations

Claude Fable 5 Supported
Claude Mythos 5.1 Supported
Claude Opus 4.6 Supported
Claude Sonnet 5 Supported
DeepSeek-V4-Flash Supported
DeepSeek-V4.1-Flash Supported
GLM-5 Supported
GLM-5.2 Supported
GLM-5.3-Flash Supported
GPT-5 mini Supported
GPT-5.4 Pro Supported
GPT-5.4 mini Supported
Gemini 3 Flash Supported
Gemini 3.1 Flash-Lite Supported
Gemini 3.7 Flash Supported
Gemini 3.8 Flash Supported
MiniMax M2.7 Supported
Muse Spark 1.2 Supported
NVIDIA Jetson Not Supported
Seedance 2.0 Supported

Integrations

Claude Fable 5 Not Supported
Claude Mythos 5.1 Not Supported
Claude Opus 4.6 Not Supported
Claude Sonnet 5 Not Supported
DeepSeek-V4-Flash Not Supported
DeepSeek-V4.1-Flash Not Supported
GLM-5 Not Supported
GLM-5.2 Not Supported
GLM-5.3-Flash Not Supported
GPT-5 mini Not Supported
GPT-5.4 Pro Not Supported
GPT-5.4 mini Not Supported
Gemini 3 Flash Not Supported
Gemini 3.1 Flash-Lite Not Supported
Gemini 3.7 Flash Not Supported
Gemini 3.8 Flash Not Supported
MiniMax M2.7 Not Supported
Muse Spark 1.2 Not Supported
NVIDIA Jetson Supported
Seedance 2.0 Not Supported
Claim Cheaper Inference and update features and information
Claim Cheaper Inference and update features and information
Claim Photon and update features and information
Claim Photon and update features and information