Home › Best AI tools › LLM APIs & Model Providers
Best AI Tools for Building with llm apis (33 options)
33 tools for building with LLM APIs in the directory. Model APIs, inference platforms and gateways for building with large language models.
How to read this page. We do not rank tools or publish scores. This page lists every LLM APIs & Model Providers tool in the directory with its official link and pricing model so you can shortlist, then try the ones that fit. Pricing labels come from each vendor's pricing page when we could confirm them; "See site" means we could not.
At a glance
- 33 tools listed; 0 free to use, 2 with a free tier, 1 paid, 30 where pricing is not confirmed here.
- With a free plan or tier: Modal, Portkey.
What to look for
Compare model choice, context length, rate limits, data-retention terms and how usage is billed, such as per token or per request.
All 33 tools
| Tool | What it does | Pricing | Link |
|---|---|---|---|
| AI21 Labs | AI lab offering the Jamba models and enterprise AI tools. | See site | Official site |
| Alibaba Cloud Model Studio | Alibaba Cloud's platform for accessing and building on Qwen and other models. | See site | Official site |
| Amazon Bedrock | AWS service offering foundation models from multiple providers through one API. | See site | Official site |
| Anthropic API | Anthropic's developer API for the Claude family of models. | See site | Official site |
| Anyscale | Managed platform for running Ray-based AI workloads. | See site | Official site |
| Azure AI Foundry | Microsoft's platform for building and managing AI apps and agents with a catalog of models. | See site | Official site |
| Baseten | Inference platform for deploying and serving AI models. | See site | Official site |
| Cerebras | AI hardware company offering high-speed inference for open models. | See site | Official site |
| Cloudflare Workers AI | Run AI models on Cloudflare's network via serverless APIs. | See site | Official site |
| Cohere | Enterprise AI company offering language models, embeddings and rerank APIs. | See site | Official site |
| Databricks Mosaic AI | Databricks' tools for building, serving and governing AI models and agents. | See site | Official site |
| DeepInfra | Hosted inference for open-source models via API. | See site | Official site |
| DeepSeek API | Developer documentation for the DeepSeek model API. | See site | Official site |
| Fireworks AI | Inference platform for open and fine-tuned generative models. | See site | Official site |
| Google AI Studio | Google's web tool and API gateway for prototyping with Gemini models. | See site | Official site |
| Groq | Fast inference platform that runs open models on custom LPU hardware. | See site | Official site |
| Hugging Face | Hub for open models, datasets and apps, with hosted inference. | See site | Official site |
| LiteLLM | Open-source gateway for calling many LLM providers through one OpenAI-style interface. | See site | Official site |
| Llama | Meta's family of open-weight models with downloads and developer resources. | See site | Official site |
| Modal | Serverless cloud for running AI workloads and model inference. | Freemium | Official site |
| Nebius | AI cloud with GPU infrastructure and managed inference. | See site | Official site |
| Novita AI | Cloud platform offering model APIs and GPU instances. | See site | Official site |
| NVIDIA NIM | NVIDIA's catalog of model endpoints and microservices for inference. | See site | Official site |
| OpenAI API | OpenAI's developer platform for its language, image, audio and agent APIs. | See site | Official site |
| OpenRouter | Unified API that routes requests to many model providers. | See site | Official site |
| Perplexity API | Perplexity's API for search-grounded answers. | See site | Official site |
| Portkey | AI gateway for routing, observing and governing LLM requests. | Freemium | Official site |
| Reka | AI lab offering multimodal models and APIs. | See site | Official site |
| Replicate | Run and deploy machine learning models through a simple API. | See site | Official site |
| SambaNova | AI infrastructure and inference cloud for open and custom models. | See site | Official site |
| Together AI | Cloud for running, fine-tuning and deploying open-source models. | See site | Official site |
| Vertex AI | Google Cloud's platform for building and deploying generative AI and ML models. | See site | Official site |
| xAI API | xAI's developer API for its Grok language, image and voice models, billed by usage. | Paid | Official site |
Browse the LLM APIs & Model Providers category · All best-of guides