> ## Documentation Index > Fetch the complete documentation index at: https://docs.loongclaw.ai/llms.txt > Use this file to discover all available pages before exploring further. # Provider Guides > One setup page per built-in Loong provider kind. # Provider Guides Loong currently ships 41 built-in provider kinds. This hub exists so the README and chooser pages can stay compact while every built-in provider still has a truthful setup page. Use [Providers And Models](/use-loong/providers-and-models) when you are still choosing a lane. Use this hub when you already know the provider family and want the exact built-in contract, minimal config, and verification path. ## Quick Picks Use this short list when you want a fast starting point before scanning the full matrix below. | If you want... | Start here | Why | | --------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | | the shortest common hosted path | [Volcengine](/use-loong/provider-guides/volcengine) | the platform-first hosted lane stays explicit and well-supported in the public docs | | another common hosted path with the same shape | [BytePlus](/use-loong/provider-guides/byteplus) | it keeps the hosted setup path short without hiding the broader provider inventory | | a named direct hosted vendor your team already uses | [OpenAI](/use-loong/provider-guides/openai) | the built-in direct hosted contract stays explicit instead of being flattened into one generic story | | a coding-dedicated lane | [BytePlus Coding](/use-loong/provider-guides/byteplus-coding) or [Kimi Coding](/use-loong/provider-guides/kimi-coding) | coding quota and model choice can stay separate from the main assistant lane | | a local or self-hosted model server | [Ollama](/use-loong/provider-guides/ollama) | the operator-owned server boundary stays visible from the start | | a gateway or compatibility endpoint | [OpenRouter](/use-loong/provider-guides/openrouter) or [Bedrock](/use-loong/provider-guides/bedrock) | route ownership stays explicit when another layer sits in front of the model vendor | ## Platform-First Hosted Common hosted first-run lanes when you want a short reviewed path without hiding the provider family. | Provider | Kind | Default auth env | Model note | | --------------------------------------------------- | ------------ | ------------------ | ------------------------------- | | [Volcengine](/use-loong/provider-guides/volcengine) | `volcengine` | `ARK_API_KEY` | operator chooses model strategy | | [BytePlus](/use-loong/provider-guides/byteplus) | `byteplus` | `BYTEPLUS_API_KEY` | operator chooses model strategy | ## Direct Hosted Providers Direct hosted provider families when your team already has a vendor choice and wants it to stay explicit in config. | Provider | Kind | Default auth env | Model note | | ----------------------------------------------------- | ------------- | --------------------- | --------------------------------- | | [OpenAI](/use-loong/provider-guides/openai) | `openai` | `OPENAI_API_KEY` | operator chooses model strategy | | [Anthropic](/use-loong/provider-guides/anthropic) | `anthropic` | `ANTHROPIC_API_KEY` | operator chooses model strategy | | [Gemini](/use-loong/provider-guides/gemini) | `gemini` | `GEMINI_API_KEY` | operator chooses model strategy | | [DeepSeek](/use-loong/provider-guides/deepseek) | `deepseek` | `DEEPSEEK_API_KEY` | reviewed fallback `deepseek-chat` | | [MiniMax](/use-loong/provider-guides/minimax) | `minimax` | `MINIMAX_API_KEY` | reviewed fallback `MiniMax-M2.7` | | [Mistral](/use-loong/provider-guides/mistral) | `mistral` | `MISTRAL_API_KEY` | operator chooses model strategy | | [Cohere](/use-loong/provider-guides/cohere) | `cohere` | `COHERE_API_KEY` | operator chooses model strategy | | [xAI](/use-loong/provider-guides/xai) | `xai` | `XAI_API_KEY` | operator chooses model strategy | | [Z.ai](/use-loong/provider-guides/zai) | `zai` | `ZAI_API_KEY` | operator chooses model strategy | | [Zhipu](/use-loong/provider-guides/zhipu) | `zhipu` | `ZHIPUAI_API_KEY` | operator chooses model strategy | | [Qwen](/use-loong/provider-guides/qwen) | `qwen` | `DASHSCOPE_API_KEY` | operator chooses model strategy | | [Kimi](/use-loong/provider-guides/kimi) | `kimi` | `MOONSHOT_API_KEY` | operator chooses model strategy | | [Groq](/use-loong/provider-guides/groq) | `groq` | `GROQ_API_KEY` | operator chooses model strategy | | [Fireworks](/use-loong/provider-guides/fireworks) | `fireworks` | `FIREWORKS_API_KEY` | operator chooses model strategy | | [Together](/use-loong/provider-guides/together) | `together` | `TOGETHER_API_KEY` | operator chooses model strategy | | [Perplexity](/use-loong/provider-guides/perplexity) | `perplexity` | `PERPLEXITY_API_KEY` | operator chooses model strategy | | [Qianfan](/use-loong/provider-guides/qianfan) | `qianfan` | `QIANFAN_API_KEY` | operator chooses model strategy | | [Cerebras](/use-loong/provider-guides/cerebras) | `cerebras` | `CEREBRAS_API_KEY` | operator chooses model strategy | | [NVIDIA](/use-loong/provider-guides/nvidia) | `nvidia` | `NVIDIA_API_KEY` | operator chooses model strategy | | [SambaNova](/use-loong/provider-guides/sambanova) | `sambanova` | `SAMBANOVA_API_KEY` | operator chooses model strategy | | [Novita](/use-loong/provider-guides/novita) | `novita` | `NOVITA_API_KEY` | operator chooses model strategy | | [SiliconFlow](/use-loong/provider-guides/siliconflow) | `siliconflow` | `SILICONFLOW_API_KEY` | operator chooses model strategy | | [StepFun](/use-loong/provider-guides/stepfun) | `stepfun` | `STEP_API_KEY` | operator chooses model strategy | | [Venice](/use-loong/provider-guides/venice) | `venice` | `VENICE_API_KEY` | operator chooses model strategy | ## Coding-Specialized Providers Dedicated coding lanes that keep coding quota, pricing, or route ownership separate from the general assistant lane. | Provider | Kind | Default auth env | Model note | | ----------------------------------------------------------------- | ------------------- | --------------------- | ------------------------------- | | [Volcengine Coding](/use-loong/provider-guides/volcengine-coding) | `volcengine_coding` | `ARK_API_KEY` | operator chooses model strategy | | [BytePlus Coding](/use-loong/provider-guides/byteplus-coding) | `byteplus_coding` | `BYTEPLUS_API_KEY` | operator chooses model strategy | | [Kimi Coding](/use-loong/provider-guides/kimi-coding) | `kimi_coding` | `KIMI_CODING_API_KEY` | default model `kimi-for-coding` | | [Step Plan](/use-loong/provider-guides/step-plan) | `step_plan` | `STEP_API_KEY` | operator chooses model strategy | | [Bailian Coding](/use-loong/provider-guides/bailian-coding) | `bailian_coding` | `BAILIAN_API_KEY` | operator chooses model strategy | ## Gateway And Compatibility Providers Gateway, proxy, or compatibility endpoints that sit between Loong and upstream model vendors. | Provider | Kind | Default auth env | Model note | | ------------------------------------------------------------------------- | ----------------------- | -------------------------- | ------------------------------- | | [OpenRouter](/use-loong/provider-guides/openrouter) | `openrouter` | `OPENROUTER_API_KEY` | operator chooses model strategy | | [Cloudflare AI Gateway](/use-loong/provider-guides/cloudflare-ai-gateway) | `cloudflare_ai_gateway` | `CLOUDFLARE_API_KEY` | operator chooses model strategy | | [Vercel AI Gateway](/use-loong/provider-guides/vercel-ai-gateway) | `vercel_ai_gateway` | `AI_GATEWAY_API_KEY` | operator chooses model strategy | | [Bedrock](/use-loong/provider-guides/bedrock) | `bedrock` | `AWS_BEARER_TOKEN_BEDROCK` | operator chooses model strategy | | [Custom](/use-loong/provider-guides/custom) | `custom` | `CUSTOM_PROVIDER_API_KEY` | operator chooses model strategy | ## Local And Self-Hosted Providers Local or self-hosted servers where the model boundary stays operator-owned. | Provider | Kind | Default auth env | Model note | | ------------------------------------------------- | ----------- | ---------------------- | ------------------------------- | | [Ollama](/use-loong/provider-guides/ollama) | `ollama` | local or explicit auth | operator chooses model strategy | | [LM Studio](/use-loong/provider-guides/lm-studio) | `lm_studio` | local or explicit auth | operator chooses model strategy | | [llama.cpp](/use-loong/provider-guides/llamacpp) | `llamacpp` | local or explicit auth | operator chooses model strategy | | [vLLM](/use-loong/provider-guides/vllm) | `vllm` | local or explicit auth | operator chooses model strategy | | [SGLang](/use-loong/provider-guides/sglang) | `sglang` | local or explicit auth | operator chooses model strategy | ## Reading Rule * Start with [Providers And Models](/use-loong/providers-and-models) when the provider choice is still open. * Use the individual guide page when one provider kind is already decided. * Keep [Provider Recipes](/use-loong/provider-recipes) for representative rollout paths rather than the full provider inventory. * Keep [Configuration Patterns](/use-loong/configuration-patterns) open when you need the shared `active_provider` plus `providers.` shape.