LLM Providers
大语言模型 · 19 tools
Access GPT-4o, GPT-4, GPT-3.5, embeddings, DALL-E, Whisper, and TTS models via REST API.
Access Claude 3.5 Sonnet, Haiku, and Opus models for chat, analysis, and code generation.
Access Gemini 2.0 Flash, Pro, and Ultra models with native multimodal and tool-use support.
Access DeepSeek-V3 and DeepSeek-R1 reasoning models with competitive pricing.
Access Mistral Large, Small, and Codestral models with efficient architecture.
Access Command-R, Embed, and Rerank models for enterprise NLP and search.
Ultra-fast inference API for open-source LLMs using LPU inference engine.
Cloud platform for open-source LLM inference with 100+ models including Llama, Mixtral, and DeepSeek.
Access Sonar search-grounded LLMs with real-time web search and citations.
AWS managed service for foundation models from Anthropic, Meta, Mistral, Stability AI, and Amazon. Unified API with enterprise security.
Access Grok-2 and Grok-3 models from xAI. Real-time knowledge, long context, and image understanding capabilities.
Access Grok-2 and Grok-3 models with real-time knowledge.
Alibaba Qwen2.5 series - strong multilingual models, competitive China pricing.
Build AI assistants with persistent threads, code interpreter, file search, and function calling.
Fastest LLM inference. Llama 3.1 405B at 969 tokens/second with OpenAI-compatible API.
Run LLMs on Cloudflare's global edge network. Llama, Mistral, and embedding models with zero cold starts.
Open-source model hosting with per-token pricing. Llama, Qwen, Whisper, and Stable Diffusion.
Mistral Large 2, Codestral, and Ministral models. Strong multilingual and coding performance.
Command R+, Embed, and Rerank models. Enterprise-grade RAG and search infrastructure.