Anthropic API Featured
Claude models through the Anthropic developer platform
Google Gemini API Featured
Gemini models via Google AI Studio and the Gemini API
Llama Featured
Meta's open-weight model family
Ollama Featured
Run open models locally with one command
OpenAI API Featured
GPT and reasoning models behind one developer API
OpenRouter Featured
One API and one bill for hundreds of models
Alibaba Cloud Model Studio
Qwen models and a model service on Alibaba Cloud
Amazon Bedrock
Managed access to many foundation models on AWS
Amazon Nova
Amazon's own foundation models on Bedrock
Arize Phoenix
AI observability and evaluation you can self-host
Axolotl
Config-driven fine-tuning for open LLMs
Azure AI Foundry
Microsoft's platform for building with models and agents
Baseten
Production inference for open and custom models
BGE (FlagEmbedding)
Open BGE embedding and reranker models
Bifrost
Fast open-source LLM gateway from Maxim
Braintrust
Evals, logging and prompt tooling for AI products
Cerebras
Inference on wafer-scale chips
Cloudflare AI Gateway
Proxy for AI traffic with caching and rate limits
Cloudflare Workers AI
Run models on Cloudflare's network
Cohere
Enterprise language models for search and agents
Cohere Embed
Multilingual and multimodal embeddings
Cohere Rerank
Rerank search results with a hosted model
Datadog LLM Observability
LLM traces inside Datadog
DeepInfra
Pay-per-token API for open models
DeepSeek API
Low-cost reasoning and chat models, OpenAI-compatible
DeepSeek-V3
Open weights for DeepSeek's V3 mixture-of-experts model
Eden AI
European AI gateway with one API for many models
Fireworks AI
Fast inference for open and custom models
Gemini embeddings
Embedding models in the Gemini API
Gemma
Google's lightweight open models
GLM-4.5
Z.ai's open GLM model series
Google Vertex AI
Google Cloud's platform for models and ML
gpt-oss
OpenAI's open-weight reasoning models
Groq
Inference on custom LPU chips
Helicone
Open-source LLM observability through a proxy or SDK
Hugging Face Inference Providers
One API across many inference partners
Hugging Face TRL
Train language models with SFT, DPO and RL
IBM Granite
IBM's open enterprise language models
Jina AI
Embeddings, rerankers and web reader APIs
Kimi K2
Moonshot AI's open mixture-of-experts model
Kong AI Gateway
AI traffic management on the Kong API gateway
Langfuse
Open-source LLM observability, evals and prompt management
LangSmith
Tracing, evals and deployment from the LangChain team
LiteLLM
Open-source proxy and SDK for 100+ LLM providers
LLaMA-Factory
Unified fine-tuning for 100+ language models
llama.cpp
C/C++ inference for GGUF models on everyday hardware
Mistral AI
French lab with hosted APIs and open models
Mixedbread
Search, embedding and rerank models and APIs
Modal
Serverless GPUs defined in Python
NVIDIA Nemotron
Open NVIDIA models with open data and recipes
OLMo
Fully open language models from Ai2
OpenAI embeddings
Text embedding models from OpenAI
OpenAI fine-tuning
Fine-tune OpenAI models on your own examples
OpenLLMetry
OpenTelemetry instrumentation for LLM apps
Opik
Open-source LLM tracing and evals from Comet
Oumi
Open platform to train, evaluate and deploy models
Perplexity API
Search-grounded answers and a web search API
Phi
Microsoft's small language models
Portkey
AI gateway with guardrails, caching and observability
PostHog LLM analytics
LLM traces next to product analytics
Pydantic Logfire
OpenTelemetry observability from the Pydantic team
Qwen3
Alibaba's open Qwen3 language models
Qwen3 Embedding
Open embedding and reranking models from the Qwen team
Replicate
Run models through an API without managing servers
Requesty
LLM router with failover and governance
SambaNova
Inference cloud on custom RDUs
Sentence Transformers
Python library for embedding and rerank models
TensorZero
Open-source LLM gateway, evals and optimization
Text Embeddings Inference
Hugging Face server for embedding and rerank models
Tinker
Fine-tuning API for open-weight models
Together AI
Serverless and dedicated inference for open models
torchtune
PyTorch-native library for fine-tuning LLMs
Unsloth
Faster, lower-memory fine-tuning of open models
Vercel AI Gateway
One endpoint for models from many providers
vLLM
High-throughput open-source LLM serving engine
Voyage AI
Embedding and reranking models for retrieval
Weights & Biases Weave
Tracing and evaluation for AI applications
xAI API
Grok models for developers