Absortio

Email → Summary → Bookmark → Email

bots.so — The AI Inference Model Index

Extracto

Discover and compare AI inference models across providers. Real-time pricing, availability, and performance data for GPT-4, Claude, Llama, Gemini, and 50+ more models.

Resumen

Resumen Principal

El panorama actual de proveedores de inferencia de Modelos de Lenguaje Grandes (LLM) es dinámico y diverso, abarcando 42 entidades clasificadas en tiers como "major" y "community". Un hallazgo central es la prevalencia de la compatibilidad con la API de OpenAI entre la mayoría de los actores, un factor clave que

Contenido

42 Providers Tracked

All LLM Inference Providers

Live tracked count. Showing 42 profiled providers across flagship, major, and community tiers.

Flagship Providers

Major Providers

Together AI logo Live

Together AI
Run leading open-source models with one API

Models Hosted

Frontier Deck Frontier Deck means this provider carries an extensive lineup across many model categories.

API Style
OpenAI-compatible

Compute Location

North America This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Groq logo Live

Groq
Fastest inference on custom LPU hardware

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

NVIDIA logo Live

NVIDIA
AI infrastructure and inference at scale

Models Hosted

Frontier Deck Frontier Deck means this provider carries an extensive lineup across many model categories.

API Style
OpenAI-compatible

Compute Location

US + Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Ollama logo Live

Ollama
Run AI models anywhere

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
Native + OpenAI-compatible

Compute Location

Undisclosed (Contacted 16 Feb 2026) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Fireworks AI logo Live

Fireworks AI
High-performance inference at scale

Models Hosted

Expanded Deck Expanded Deck means this provider offers a broad lineup that covers many common model families.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Mistral AI logo Live

Mistral AI
European AI lab pushing efficiency frontiers

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

EU (France) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Cerebras logo Live

Cerebras
Wafer-scale AI inference at record speeds

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US + Canada + EU This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Baseten logo Live

Baseten
Model APIs for production AI

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Replicate logo Live

Replicate
Run AI models with a cloud API

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
Replicate API

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Cohere logo Live

Cohere
Enterprise AI with RAG specialization

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
Cohere API

Compute Location

US + Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Cloudflare logo Live

Cloudflare Workers AI
AI at the edge, globally distributed

Models Hosted

Expanded Deck Expanded Deck means this provider offers a broad lineup that covers many common model families.

API Style
REST API

Compute Location

Global (Edge) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Crusoe logo Live

Crusoe
The world's favorite AI cloud

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US (Wyoming, Texas) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

DeepInfra logo Live

DeepInfra
Simple, scalable AI inference

Models Hosted

Frontier Deck Frontier Deck means this provider carries an extensive lineup across many model categories.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Nebius logo Live

Nebius
The ultimate cloud for AI explorers

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

EU + US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Hyperstack logo Live

Hyperstack
European GPU cloud powered by renewable energy

Models Hosted

Expanded Deck Expanded Deck means this provider offers a broad lineup that covers many common model families.

API Style
Custom (api_key header)

Compute Location

Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Parasail logo Live

Parasail
No limits. No contracts. Priced right.

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US + Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Scaleway logo Live

Scaleway
Managed Inference with European sovereignty

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

EU (France) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

io.net logo Live

io.net
Decentralized GPU Cloud

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Decentralized This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

OVHcloud logo Live

OVHcloud
AI Endpoints with European data sovereignty

Models Hosted

Expanded Deck Expanded Deck means this provider offers a broad lineup that covers many common model families.

API Style
OpenAI-compatible

Compute Location

Global (46 DCs) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

SiliconFlow logo Live

SiliconFlow
AI Infrastructure for LLMs & Multimodal

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Asia (China) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Weights and Biases logo Live

Weights & Biases Inference
Hosted inference endpoints for open models

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

IONOS logo Live

IONOS
European cloud provider with hosted AI inference

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
Managed AI Model Hub

Compute Location

EU + US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

DigitalOcean logo Live

DigitalOcean
Gradient AI platform at the edge

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Community Providers

Hyperbolic logo Live

Hyperbolic
Decentralized GPU network for AI inference

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

SambaNova logo Live

SambaNova
Enterprise AI with custom RDU chips

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Featherless logo Live

Featherless
Serverless inference for open-source models

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Chutes logo Live

Chutes
Serverless AI Compute

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

GMI Cloud logo Live

GMI Cloud
GPU Cloud for Scalable AI

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Taiwan + Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

CanopyWave logo Live

CanopyWave
Open-source AI inference platform

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Asia-Pacific This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Novita AI logo Live

Novita AI
Open-source LLM API

Models Hosted

Expanded Deck Expanded Deck means this provider offers a broad lineup that covers many common model families.

API Style
OpenAI-compatible

Compute Location

Asia + Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Nscale logo Live

Nscale
The Hyperscaler Engineered for AI

Models Hosted

Expanded Deck Expanded Deck means this provider offers a broad lineup that covers many common model families.

API Style
OpenAI-compatible

Compute Location

EU + Global This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Mancer logo Live

Mancer
Creative AI for roleplay and storytelling

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Public AI logo Live

Public AI
AI as public infrastructure

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

US This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Venice AI logo Live

Venice AI
The Only Private AI API

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Decentralized This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Lilypad Network logo Down

Lilypad Network
Decentralized AI inference

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Decentralized This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Google logo Down

Google (Legacy Key)
Legacy key preserved for historical provider continuity

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
Google Cloud / AI Studio

Compute Location

Global (GCP) This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

WaveSpeed logo Down

WaveSpeed
Platform for faster AI image and video generation

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
Platform API

Compute Location

US + Europe This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Z.ai logo Down

Z.ai
Developer API platform for Z.ai models

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
Model API endpoints

Compute Location

Australia + Germany This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Inceptron logo Soon

Inceptron
Compiler-Optimized AI Inference

Models Hosted

Curated Deck Curated Deck means this provider runs a focused lineup of models, chosen for specific use cases.

API Style
OpenAI-compatible

Compute Location

Europe This is our best guess at where the compute is powered and provided from for this provider, based on the data we could find. May be incorrect.

Newsletter

Get the signal, skip the noise.

Weekly digest of new models and provider updates across 41+ compute providers. Curated for AI builders who ship.

New model releases

Capability updates

Provider status

Fuente: bots.so