LLM APIs
API providers for large language models, including free tiers and local options.
20 tools · updated
20 tools
| Visit | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
 Google Gemini API3 plans | Free – Usage | Lab API | |||||||||
 OpenAI2 plans | Usage | Lab API | |||||||||
 Anthropic Claude CodeNew2 plans | Usage | Lab API | |||||||||
 OpenRouter4 plans | Free – Usage | Router | |||||||||
 Groq3 plans | Free – Usage | Inference host | |||||||||
 Mistral3 plans | Free – Usage | Lab API | |||||||||
 DeepSeek API | Usage | Lab API | |||||||||
 Cloudflare3 plans | Free – $5 | Inference host | |||||||||
 Vercel3 plans | Free – $20/seat | Router | |||||||||
 Cerebras Inference3 plans | Free – Usage | Inference host | |||||||||
 Fireworks AI2 plans | Usage | Inference host | |||||||||
 Hugging Face | Usage | Router | |||||||||
 xAI Grok APINew2 plans | Usage | Lab API | |||||||||
 Together AI2 plans | Usage | Inference host | |||||||||
 SambaNova CloudNew3 plans | Free – Usage | Inference host | |||||||||
 DeepInfraNew2 plans | Usage | Inference host | |||||||||
 SiliconFlowNew2 plans | Free – Usage | Inference host | |||||||||
 MiniMax / HailuoNew | Usage | Lab API | |||||||||
 Novita AINew2 plans | Usage | Inference host | |||||||||
 Z.AI APINew2 plans | Free – Usage | Lab API |
- Google Gemini APIFree – UsageGoogle developer API for Veo text- and image-to-video generation
- OpenAIUsageOpenAI SDK for building tool-using agents with handoffs and guardrails
- Anthropic Claude CodeUsageNewFirst-party API for Claude models with tools, vision and caching
- OpenRouterFree – UsageRouter for hundreds of LLMs through one OpenAI-compatible API
- GroqFree – UsageFast inference cloud offering hosted Whisper speech-to-text
- MistralFree – UsageMistral API that converts PDFs and images into structured Markdown and JSON
- DeepSeek APIUsageLow-cost first-party API for DeepSeek reasoning and chat models
- CloudflareFree – $5Free, privacy-first web analytics built into Cloudflare infrastructure.
- VercelFree – $20/seatVercel's deployable starter templates for web, AI, and commerce apps
- Cerebras InferenceFree – UsageUltra-fast inference API for selected open models
- Fireworks AIUsageHigh-speed serverless and on-demand GPU inference platform for open-weight mode…
- Hugging FaceUsageModel hub and API router for hosted open-model inference
- xAI Grok APIUsageNewFirst-party lab API for Grok reasoning, coding, and multimodal models
- Together AIUsageInference and fine-tuning platform for open-source models
- SambaNova CloudFree – UsageNewHigh-speed RDU chip inference API for Llama, DeepSeek, and open-weight models
- DeepInfraUsageNewLow-cost serverless inference API for open-source LLMs, vision, and embeddings
- SiliconFlowFree – UsageNewHigh-throughput inference platform for DeepSeek, Qwen, GLM, and multimodal mode…
- MiniMax / HailuoUsageNewHailuo 2.3 and H3 video generation models with subscription and API options
- Novita AIUsageNewLow-cost open-model LLM API and serverless GPU cloud for DeepSeek, GLM, and Qwen
- Z.AI APIFree – UsageNewFirst-party developer API for GLM-5.3, GLM-5v Vision, and AutoGLM agent models