Explore providers 21

Amazon Bedrock

Cloud platform

AWS managed model platform. Access depends on the model, AWS Region, inference profile and account permissions.

Anthropic

Direct developer API

Direct access to Claude models from their developer, Anthropic. Model versions and aliases are tracked separately from other providers.

DeepInfra

Inference platform

Hosted model APIs covering language, images, audio and embeddings. Deployment precision and service tiers can differ between offerings.

DeepSeek

Direct developer API

Direct inference API from DeepSeek. Model aliases can point to specific current model releases.

ElevenLabs

Direct developer API

Developer of speech synthesis, conversational speech, sound-effects and music-generation models.

fal.ai

Model aggregator

API platform for image, video, speech and other generative media from multiple model developers.

Fireworks AI

Inference platform

Inference platform for language, vision and embedding models. This selection refers to its serverless catalog.

Google Cloud Vertex AI

Cloud platform

Google Cloud model platform with Google and partner models. Cloud project, regional endpoint and model access requirements apply.

Google Gemini API

Direct developer API

Google developer API for language, image, video, speech and music models; distinct from Vertex AI deployments.

Groq

Inference platform

GroqCloud model inference for text and audio. Production, preview and enterprise-only models are distinguished in its catalog.

Microsoft Azure AI Foundry

Cloud platform

Microsoft model platform including Azure OpenAI and partner models. Region, deployment type and subscription eligibility affect availability.

Mistral AI

Direct developer API

Mistral model APIs for language, code, audio and document processing. License and weight access vary by model.

Novita AI

Inference platform

Inference platform with language models and image, video, text-to-speech and voice-cloning APIs.

OpenAI

Direct developer API

Direct OpenAI APIs, including image generation and editing, speech synthesis and realtime voice.

OpenRouter

Model aggregator

A unified gateway to models from multiple creators and inference providers. Routing and upstream availability can vary by model.

Replicate

Inference platform

Hosted model APIs with model-specific schemas for image, video, speech and music generation.

Runway

Model aggregator

Developer of Gen-4 and Aleph, with an API offering Runway models alongside partner image, video and audio models.

Segmind

Inference platform

Serverless generative media APIs and workflows, including image editing, video generation and speech.

Together AI

Inference platform

Hosted inference for language and media models. Serverless availability is tracked separately from dedicated deployments.

WaveSpeedAI

Model aggregator

Unified API platform for generative image, video and audio models from multiple developers.

xAI

Direct developer API

Direct Grok APIs for language, image and video workloads. Use the model-specific endpoint and capability documentation.