Requesty is a unified AI gateway and LLM router that gives developers a single OpenAI-compatible endpoint to reach more than 600 models across every major provider. Requests fail over down a fallback chain, route by cost, latency, or capability, and are cached and logged so teams can manage spend per key, group, and user.
As a direct multi-model router, it competes with gateways such as OpenRouter for teams that want to swap model providers and optimize cost and reliability through one endpoint, priced at a small markup on underlying model costs.

A unified AI gateway and LLM router exposing one OpenAI-compatible endpoint across 600+ models.




Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.



Fugu Ultra is Sakana AI's performance-optimized multi-agent orchestration tier for hard, high-stakes reasoning tasks.



Flat-rate monthly subscription giving developers access to curated coding models through compatible endpoints.


A unified OpenAI-compatible API and gateway for accessing hundreds of LLMs from many providers.

8Labs One is an EU-hosted enterprise AI platform consolidating chat, voice, image, video, slides and workflow automation.

Adaptive OpenAI-compatible endpoint coordinating open-weight models for chat and agents.

Open source AI gateway routing every model behind one zero-markup OpenAI-compatible endpoint.

Fugu is a multi-agent orchestration API that routes complex tasks across a pool of frontier language models.

Fugu Ultra is Sakana AI's performance-optimized multi-agent orchestration tier for hard, high-stakes reasoning tasks.

An open-source AI gateway and proxy that calls many large language model APIs in the OpenAI format.

Flat-rate monthly subscription giving developers access to curated coding models through compatible endpoints.

A unified OpenAI-compatible API and gateway for accessing hundreds of LLMs from many providers.

Router is Conifer's routing decision leased on its own to harnesses and companies.



Async inference API for long-horizon AI agents, serving leading open-source models through OpenAI- and Anthropic-compatible endpoints.


RunInfra Model APIs provide hosted open-model inference through compatible APIs for developers and agent teams.


Developer API providing pay-per-token access to DeepSeek's hosted language models.


Together AI is a serverless and dedicated inference API for open-source AI models with OpenAI-compatible endpoints.



Cloudflare's managed gateway for routing, securing, caching, and observing AI applications across many model providers.


One HIPAA-compliant gateway routing all LLM traffic with BAA coverage, audit logging, key management, and cost controls enforced automatically.




Typed Pydantic AI agents with validated outputs and observability.


Managed supervised fine-tuning service for open-source models with on-demand and dedicated deployment options.


Gemini API lets developers build applications with Google's Gemini models and AI capabilities.



Expert-built evaluation services for measuring AI agent quality, model choice, and operating cost.



Hosted inference API for the ESM model families with credit-based metering and a developer console.


Advisory and benchmarking service using automated metrics and MQM-based human audits to validate engine performance and optimize MT/LLM workflows.


Pinecone Inference provides access to embedding and reranking models hosted on Pinecone infrastructure for AI search and retrieval applications.


Managed service for fine-tuning open-source models on dedicated or shared GPU infrastructure for production use.
Async inference API for long-horizon AI agents, serving leading open-source models through OpenAI- and Anthropic-compatible endpoints.

RunInfra Model APIs provide hosted open-model inference through compatible APIs for developers and agent teams.

Developer API providing pay-per-token access to DeepSeek's hosted language models.

Together AI is a serverless and dedicated inference API for open-source AI models with OpenAI-compatible endpoints.

Holo Models API provides access to H Company multimodal models.

Cloudflare's managed gateway for routing, securing, caching, and observing AI applications across many model providers.

One HIPAA-compliant gateway routing all LLM traffic with BAA coverage, audit logging, key management, and cost controls enforced automatically.

Replicate is a cloud API to run, fine-tune, and deploy open-source machine learning models with auto-scaling.

Production LLM applications built with LangChain and LangGraph.

Typed Pydantic AI agents with validated outputs and observability.

Managed supervised fine-tuning service for open-source models with on-demand and dedicated deployment options.

Gemini API lets developers build applications with Google's Gemini models and AI capabilities.

Quack Backend API is a REST API for guideline management and LLM inference.

Expert-built evaluation services for measuring AI agent quality, model choice, and operating cost.

Decisions API evaluates text, images, and JSON and returns typed answers.

Hosted inference API for the ESM model families with credit-based metering and a developer console.

Advisory and benchmarking service using automated metrics and MQM-based human audits to validate engine performance and optimize MT/LLM workflows.

Pinecone Inference provides access to embedding and reranking models hosted on Pinecone infrastructure for AI search and retrieval applications.

Managed service for fine-tuning open-source models on dedicated or shared GPU infrastructure for production use.
