
Optimize finds a cheaper model that scores as well on a team's evals.
It deploys the result as an endpoint, a single model id that a team calls like any other.
Public benchmarks pick the open models to try along the Pareto frontier of benchmark score against price. Model calls bill the team's credits while the search runs. Optimize is paused for now: searches cannot start, continue, or deploy, though past results stay available, and a deployed endpoint answers only while every model it calls remains in the catalog.


Conifer Gateway is one OpenAI- and Anthropic-compatible endpoint for more than 200 models.



A unified OpenAI-compatible API and gateway for accessing hundreds of LLMs from many providers.
Conifer Gateway is one OpenAI- and Anthropic-compatible endpoint for more than 200 models.

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

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





Portkey AI provides a gateway platform for managing and observing large language model deployments.


KrakenD AI Gateway is a self-hosted gateway routing requests across models with fallback and load balancing, filtering prompts before 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.



Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.


Secure enterprise portal for multiple large language model platforms with reusable language skills and usage-based pricing.



Developer API for Anthropic's Claude family of frontier language models including Opus, Sonnet, and Haiku.


Unified web API exposing multilingual AI capabilities including machine translation, sentiment analysis, intent detection, and speech transcription.


Baseten Dedicated Inference is a high-performance inference platform for deploying, serving, and scaling custom and open-source AI models in production.


Gemini Enterprise Agent Platform supports building, deploying, and governing enterprise AI agents and machine learning models.
Zen provides handpicked, benchmarked AI models optimized for coding agents in OpenCode.

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

Portkey AI provides a gateway platform for managing and observing large language model deployments.

KrakenD AI Gateway is a self-hosted gateway routing requests across models with fallback and load balancing, filtering prompts before models.

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

Console is Conifer's observability surface for a team's AI spending and routing.

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

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.

TrustGate connects agents to models and tools securely as part of NeuralTrust.

Hosted gateway for routing and governing traffic across hosted and self-hosted AI models.

Secure enterprise portal for multiple large language model platforms with reusable language skills and usage-based pricing.

Riften is an LLM request-routing gateway that sends each request to the lowest-cost capable model.

Developer API for Anthropic's Claude family of frontier language models including Opus, Sonnet, and Haiku.

Unified web API exposing multilingual AI capabilities including machine translation, sentiment analysis, intent detection, and speech transcription.

Baseten Dedicated Inference is a high-performance inference platform for deploying, serving, and scaling custom and open-source AI models in production.

Gemini Enterprise Agent Platform supports building, deploying, and governing enterprise AI agents and machine learning models.
