EvolutionaryScale offers ESM API
Service
Hosted inference API for the ESM model families with credit-based metering and a developer console.
- Currently Offered
The ESM API is the access layer for the ESM model families: users install the esm Python package, create an API key in the developer console, and call model-specific inference clients for generation, representation, and structure prediction. Usage is metered with credits and rate limits, additional credits are available on application, and platform guardrails restrict pathogen- and toxin-related sequences with an elevated-access path for legitimate researchers.
The API opened in public beta in January 2025 under the Forge brand with a free limited-time preview for academic and industry scientists. After the company joined Biohub in November 2025 the endpoint migrated to the Biohub Platform while the Forge gateway remained the first-party catalog, and selected models are also provisionable through AWS Marketplace listings.
Hosted inference API for the ESM model families with credit-based metering and a developer console.
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.
Gemini API lets developers build applications with Google's Gemini models and AI capabilities.
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.
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.
Developer API embedding search, entity, narrative, and sentiment analytics into mission systems.
API providing access to 36+ built-in open-source simulators with pre-configured dependencies, from fluid dynamics to molecular dynamics.
Vast.ai Model Library offers one-click deployment templates for open-source models.
OpenAI API lets developers build applications with OpenAI models, tools, and platform services.
Advisory and benchmarking service using automated metrics and MQM-based human audits to validate engine performance and optimize MT/LLM workflows.
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.
A unified AI gateway and LLM router exposing one OpenAI-compatible endpoint across 600+ models.
Developer API providing pay-per-token access to DeepSeek's hosted language models.
Gemini API lets developers build applications with Google's Gemini models and AI capabilities.
Pinecone Inference provides access to embedding and reranking models hosted on Pinecone infrastructure for AI search and retrieval applications.
Holo Models API provides access to H Company multimodal models.
Vast.ai Serverless runs autoscaling GPU inference endpoints on managed capacity.
Managed service for fine-tuning open-source models on dedicated or shared GPU infrastructure for production use.
Quack Backend API is a REST API for guideline management and LLM inference.
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.
Developer API embedding search, entity, narrative, and sentiment analytics into mission systems.
API providing access to 36+ built-in open-source simulators with pre-configured dependencies, from fluid dynamics to molecular dynamics.
Vast.ai Model Library offers one-click deployment templates for open-source models.
Production LLM applications built with LangChain and LangGraph.
OpenAI API lets developers build applications with OpenAI models, tools, and platform services.
Advisory and benchmarking service using automated metrics and MQM-based human audits to validate engine performance and optimize MT/LLM workflows.