This catalog lists the static presets currently bundled with OctaFuse Gateway for direct Admin import. Gateway still lets you create any custom Provider, Model, or compatible endpoint. Not listed does not mean unsupported.
DeepSeek
DeepSeek’s official platform with OpenAI Chat/Responses and Anthropic Messages.
https://api.deepseek.com/chat/completions https://api.deepseek.com/responses https://api.deepseek.com/anthropic ByteDance Volcengine
Standard pay-as-you-go Ark endpoints for OpenAI Chat/Responses, Anthropic Messages, and Seedream image generation.
https://ark.cn-beijing.volces.com/api/v3/chat/completions https://ark.cn-beijing.volces.com/api/v3/responses https://ark.cn-beijing.volces.com/api/v3/embeddings https://ark.cn-beijing.volces.com/api/compatible https://ark.cn-beijing.volces.com/api/v3 ByteDance Volcengine
Coding Plan endpoints for OpenAI Chat, Responses, and Anthropic Messages.
https://ark.cn-beijing.volces.com/api/coding/v3/chat/completions https://ark.cn-beijing.volces.com/api/coding/v3/responses https://ark.cn-beijing.volces.com/api/coding ByteDance Volcengine
Agent Plan endpoints for OpenAI Chat, Responses, and Anthropic Messages.
https://ark.cn-beijing.volces.com/api/plan/v3/chat/completions https://ark.cn-beijing.volces.com/api/plan/v3/responses https://ark.cn-beijing.volces.com/api/plan ByteDance Volcengine
International Volcengine ModelArk endpoints for OpenAI Chat/Responses, Anthropic Messages, and image generation.
https://ark.ap-southeast.bytepluses.com/api/v3/chat/completions https://ark.ap-southeast.bytepluses.com/api/v3/responses https://ark.ap-southeast.bytepluses.com/api/compatible https://ark.ap-southeast.bytepluses.com/api/v3 ByteDance Volcengine
Coding Plan endpoints for OpenAI Chat, Responses, and Anthropic Messages.
https://ark.ap-southeast.bytepluses.com/api/coding/v3/chat/completions https://ark.ap-southeast.bytepluses.com/api/coding/v3/responses https://ark.ap-southeast.bytepluses.com/api/coding Alibaba Cloud
China-region pay-as-you-go endpoints for OpenAI Chat/Responses, Anthropic Messages, and native DashScope audio and image generation.
https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions https://dashscope.aliyuncs.com/compatible-mode/v1/responses https://dashscope.aliyuncs.com/compatible-mode/v1/embeddings https://dashscope.aliyuncs.com/api/v1 https://dashscope.aliyuncs.com/apps/anthropic Alibaba Cloud
Coding Plan endpoints that use plan-specific keys and quota.
https://coding.dashscope.aliyuncs.com/v1/chat/completions https://coding.dashscope.aliyuncs.com/apps/anthropic Alibaba Cloud
International pay-as-you-go endpoints for OpenAI Chat/Responses, Anthropic Messages, and native DashScope audio and image generation.
https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions https://dashscope-intl.aliyuncs.com/compatible-mode/v1/responses https://dashscope-intl.aliyuncs.com/compatible-mode/v1/embeddings https://dashscope-intl.aliyuncs.com/api/v1 https://dashscope-intl.aliyuncs.com/apps/anthropic Alibaba Cloud
International Coding Plan endpoints that use plan-specific keys and quota.
https://coding-intl.dashscope.aliyuncs.com/v1/chat/completions https://coding-intl.dashscope.aliyuncs.com/apps/anthropic Alibaba Cloud
Pay-as-you-go endpoints on maas.qianwenaiapi.com for OpenAI Chat/Responses, Anthropic, and DashScope audio, image, and file transcription. Uses sk- or sk-ws- keys.
https://maas.qianwenaiapi.com/compatible-mode/v1/chat/completions https://maas.qianwenaiapi.com/compatible-mode/v1/responses https://maas.qianwenaiapi.com/api/v1 https://maas.qianwenaiapi.com/apps/anthropic Alibaba Cloud
Personal and team Token Plan endpoints on token-plan.maas.qianwenaiapi.com for OpenAI Chat/Responses, Anthropic, and DashScope TTS/realtime/image. Includes qwen-audio-3.0-asr-flash sync HTTP. Does not include filetrans or video synthesis.
https://token-plan.maas.qianwenaiapi.com/compatible-mode/v1/chat/completions https://token-plan.maas.qianwenaiapi.com/compatible-mode/v1/responses https://token-plan.maas.qianwenaiapi.com/api/v1/services/aigc/multimodal-generation/generation https://token-plan.maas.qianwenaiapi.com/api/v1/services/aigc/multimodal-generation/generation https://token-plan.maas.qianwenaiapi.com/api/v1/services/audio/tts/SpeechSynthesizer wss://token-plan.maas.qianwenaiapi.com/api-ws/v1/inference wss://token-plan.maas.qianwenaiapi.com/api-ws/v1/realtime https://token-plan.maas.qianwenaiapi.com/apps/anthropic Tencent
Hunyuan pay-as-you-go endpoints for OpenAI Chat and Anthropic Messages.
https://api.hunyuan.cloud.tencent.com/v1/chat/completions https://api.hunyuan.cloud.tencent.com/v1/embeddings https://api.hunyuan.cloud.tencent.com/anthropic Tencent
Hunyuan Token Plan endpoints that use the shared sk-tp-* plan key.
https://api.lkeap.cloud.tencent.com/plan/v3/chat/completions https://api.lkeap.cloud.tencent.com/plan/anthropic Baidu
Qianfan V2 endpoints for OpenAI Chat/Responses and Anthropic Messages.
https://qianfan.baidubce.com/v2/chat/completions https://qianfan.baidubce.com/v2/responses https://qianfan.baidubce.com/v2/embeddings https://qianfan.baidubce.com/anthropic Zhipu AI
China-region API for OpenAI Chat, Responses, Anthropic Messages, and GLM image generation.
https://open.bigmodel.cn/api/paas/v4/chat/completions https://open.bigmodel.cn/api/v1/responses https://open.bigmodel.cn/api/paas/v4/images/generations https://open.bigmodel.cn/api/paas/v4/embeddings https://open.bigmodel.cn/api/anthropic Zhipu AI
Coding Plan endpoints for OpenAI Chat/Responses and Anthropic Messages.
https://open.bigmodel.cn/api/coding/paas/v4/chat/completions https://open.bigmodel.cn/api/v1/responses https://open.bigmodel.cn/api/anthropic Zhipu AI
International standard API for chat and GLM image generation.
https://api.z.ai/api/paas/v4/chat/completions https://api.z.ai/api/paas/v4/images/generations Zhipu AI
International Coding Plan endpoints for supported coding tools.
https://api.z.ai/api/coding/paas/v4/chat/completions https://api.z.ai/api/anthropic Meituan LongCat
LongCat endpoints for OpenAI Chat/Responses and Anthropic Messages.
https://api.longcat.chat/openai/v1/chat/completions https://api.longcat.chat/openai/v1/responses https://api.longcat.chat/anthropic Moonshot AI
China-region pay-as-you-go endpoints for OpenAI Chat/Responses and Anthropic Messages.
https://api.moonshot.cn/v1/chat/completions https://api.moonshot.cn/v1/responses https://api.moonshot.cn/anthropic Moonshot AI
Kimi Code endpoints for OpenAI Chat and Anthropic Messages.
https://api.kimi.com/coding/v1/chat/completions https://api.kimi.com/coding MiniMax
China-region MiniMax endpoints for OpenAI Chat/Responses, Anthropic Messages, and native file transcription, speech synthesis, and image generation.
https://api.minimaxi.com/v1/chat/completions https://api.minimaxi.com/v1/responses https://api.minimaxi.com/anthropic https://api.minimaxi.com/v1 MiniMax
International MiniMax endpoints for OpenAI Chat/Responses, Anthropic Messages, and native file transcription, speech synthesis, and image generation.
https://api.minimax.io/v1/chat/completions https://api.minimax.io/v1/responses https://api.minimax.io/anthropic https://api.minimax.io/v1 ElevenLabs
ElevenLabs official API with native file transcription (Scribe) and text-to-speech, plus OpenAI-compatible /v1/audio/* through adapters.
https://api.elevenlabs.io/v1 OpenAI
OpenAI’s official API root for chat, images, and other supported capabilities.
https://api.openai.com/v1 Anthropic
Anthropic’s official Messages API root.
https://api.anthropic.com Meta (Llama)
Meta’s official Model API for Muse Spark, with OpenAI Chat/Responses and Anthropic Messages.
https://api.meta.ai/v1/chat/completions https://api.meta.ai/v1/responses https://api.meta.ai Gemini Developer API with native Gemini and OpenAI-compatible access.
https://generativelanguage.googleapis.com/v1beta/openai/chat/completions https://generativelanguage.googleapis.com/v1beta/openai/images/generations https://generativelanguage.googleapis.com/v1beta/openai/embeddings https://generativelanguage.googleapis.com/v1beta/models Native Gemini endpoint for Vertex AI Express mode with API key authentication.
https://aiplatform.googleapis.com/v1/publishers/google/models Full Vertex: OpenAI Chat Completions plus native Gemini. Replace the project ID; paste a GCP service account JSON as the API key.
https://aiplatform.googleapis.com/v1/projects/YOUR_PROJECT_ID/locations/global/endpoints/openapi/chat/completions https://aiplatform.googleapis.com/v1/projects/YOUR_PROJECT_ID/locations/global/publishers/google/models Mistral AI
Mistral’s official OpenAI-compatible chat API.
https://api.mistral.ai/v1/chat/completions https://api.mistral.ai/v1/embeddings Groq
GroqCloud’s high-speed OpenAI-compatible inference API.
https://api.groq.com/openai/v1/chat/completions Cerebras
Cerebras Inference’s high-speed OpenAI-compatible chat API.
https://api.cerebras.ai/v1/chat/completions SambaNova
SambaNova Cloud inference API with OpenAI Chat/Responses and Anthropic Messages.
https://api.sambanova.ai/v1/chat/completions https://api.sambanova.ai/v1/responses https://api.sambanova.ai/v1/embeddings https://api.sambanova.ai xAI (Grok)
xAI’s OpenAI-compatible API for Grok chat, Responses, and image generation.
https://api.x.ai/v1/chat/completions https://api.x.ai/v1/responses https://api.x.ai/v1/images/generations Together AI
Together AI’s OpenAI-compatible API for chat, images, speech transcription, and speech synthesis.
https://api.together.xyz/v1/chat/completions https://api.together.xyz/v1/images/generations https://api.together.ai/v1/audio/transcriptions https://api.together.ai/v1/audio/speech https://api.together.xyz/v1/embeddings Fireworks AI
Fireworks AI’s OpenAI-compatible inference API.
https://api.fireworks.ai/inference/v1/chat/completions https://api.fireworks.ai/inference/v1/embeddings DeepInfra
DeepInfra’s OpenAI-compatible chat API for hosted open-source models.
https://api.deepinfra.com/v1/openai/chat/completions https://api.deepinfra.com/v1/openai/embeddings Novita AI
Novita’s OpenAI-compatible chat API.
https://api.novita.ai/openai/v1/chat/completions https://api.novita.ai/openai/v1/embeddings Perplexity
OpenAI-compatible chat API for Perplexity’s web-connected Sonar models.
https://api.perplexity.ai/chat/completions Cohere
Cohere’s Compatibility API for integrations using the OpenAI SDK.
https://api.cohere.ai/compatibility/v1/chat/completions https://api.cohere.ai/compatibility/v1/embeddings NVIDIA
NVIDIA Build’s OpenAI-compatible NIM inference endpoint.
https://integrate.api.nvidia.com/v1/chat/completions https://integrate.api.nvidia.com/v1/embeddings Microsoft Azure
Azure OpenAI v1 base URL. Replace the resource name after import. The Foundry host *.services.ai.azure.com/openai/v1 is the same template.
https://YOUR_RESOURCE_NAME.openai.azure.com/openai/v1 StepFun
StepFun pay-as-you-go endpoints for OpenAI Chat/Responses and Anthropic Messages.
https://api.stepfun.com/v1/chat/completions https://api.stepfun.com/v1/responses https://api.stepfun.com Baichuan AI
Baichuan AI’s OpenAI-compatible chat API.
https://api.baichuan-ai.com/v1/chat/completions Xiaomi Mimo
Xiaomi MiMo pay-as-you-go endpoints for OpenAI Chat/Responses and Anthropic Messages.
https://api.xiaomimimo.com/v1/chat/completions https://api.xiaomimimo.com/v1/responses https://api.xiaomimimo.com/anthropic Xiaomi Mimo
China-region Token Plan endpoints for OpenAI Chat/Responses and Anthropic.
https://token-plan-cn.xiaomimimo.com/v1/chat/completions https://token-plan-cn.xiaomimimo.com/v1/responses https://token-plan-cn.xiaomimimo.com/anthropic Qiniu
Qiniu AI Token API with OpenAI Chat, a GPT Responses bypass, Anthropic, and Gemini (Vertex-compatible, Bearer).
https://api.qnaigc.com/v1/chat/completions https://api.qnaigc.com/bypass/openai/v1/responses https://api.qnaigc.com https://api.qnaigc.com/bypass/vertex/v1/models OpenRouter
A unified aggregation platform for chat and image models from many vendors.
https://openrouter.ai/api/v1/chat/completions https://openrouter.ai/api/v1/responses https://openrouter.ai/api/v1/images https://openrouter.ai/api/v1/embeddings OpenCode Zen
OpenCode Zen pay-as-you-go gateway (/zen/v1) with OpenAI, Anthropic, and Gemini; do not mix with Go endpoints.
https://opencode.ai/zen/v1/chat/completions https://opencode.ai/zen https://opencode.ai/zen/v1/models OpenCode Zen
OpenCode Go subscription endpoints (/zen/go/v1) for OpenAI and Anthropic; do not mix with Zen pay-as-you-go.
https://opencode.ai/zen/go/v1/chat/completions https://opencode.ai/zen/go Command Code
Command Code Provider API. OpenAI and open models use Chat Completions and Responses; Claude uses Anthropic Messages.
https://api.commandcode.ai/provider/v1/chat/completions https://api.commandcode.ai/provider/v1/responses https://api.commandcode.ai/provider Hugging Face
Hugging Face’s OpenAI-compatible chat router across many inference providers.
https://router.huggingface.co/v1/chat/completions Vercel
Vercel AI Gateway with OpenAI-compatible and Anthropic Messages endpoints.
https://ai-gateway.vercel.sh/v1/chat/completions https://ai-gateway.vercel.sh/v1/responses https://ai-gateway.vercel.sh/v1/embeddings https://ai-gateway.vercel.sh ZenMux
ZenMux aggregation API (OpenAI, Anthropic, Gemini); Pay As You Go and Builder Plan share endpoints and differ by API key only.
https://zenmux.ai/api/v1 https://zenmux.ai/api/anthropic https://zenmux.ai/api/vertex-ai/v1/publishers/google/models SCNet
National Supercomputing Internet model API with OpenAI- and Anthropic-compatible endpoints.
https://api.scnet.cn/api/llm/v1/chat/completions https://api.scnet.cn/api/llm/anthropic SiliconFlow
SiliconFlow China Model Cloud with OpenAI-compatible APIs and Anthropic Messages.
https://api.siliconflow.cn/v1/chat/completions https://api.siliconflow.cn/v1/images/generations https://api.siliconflow.cn/v1/audio/transcriptions https://api.siliconflow.cn/v1/audio/speech https://api.siliconflow.cn/v1/embeddings https://api.siliconflow.cn SiliconFlow
SiliconFlow’s international Model Cloud OpenAI-compatible API.
https://api.siliconflow.com/v1/chat/completions https://api.siliconflow.com/v1/images/generations https://api.siliconflow.com/v1/audio/transcriptions https://api.siliconflow.com/v1/audio/speech https://api.siliconflow.com/v1/embeddings Ollama
Default local Ollama OpenAI-compatible endpoint; no platform API key is required.
http://127.0.0.1:11434/v1/chat/completions http://127.0.0.1:11434/v1/embeddings Kingsoft Cloud
Kingsoft StarFlow in China, with OpenAI Chat, Responses, and Anthropic Messages.
https://kspmas.ksyun.com/v1/chat/completions https://kspmas.ksyun.com/v1/responses https://kspmas.ksyun.com Kingsoft Cloud
Kingsoft StarFlow international endpoint at global-kspmas.ksyun.com, with OpenAI Chat, Responses, and Anthropic Messages.
https://global-kspmas.ksyun.com/v1/chat/completions https://global-kspmas.ksyun.com/v1/responses https://global-kspmas.ksyun.com Open Design
Open Design Cloud model API with OpenAI Chat, Responses, and Anthropic Messages. Keys are sk-amr- and share Design Plan credits.
https://amr-link.open-design.ai/v1/chat/completions https://amr-link.open-design.ai/v1/responses https://amr-link.open-design.ai Wangsu
Wangsu’s unified gateway. OpenAI, Anthropic, and Gemini all sit under https://api.edgecloudapp.com/v2/llm. Create an sk- token in Token Management; Gemini uses Bearer.
https://api.edgecloudapp.com/v2/llm/openai https://api.edgecloudapp.com/v2/llm/anthropic/messages https://api.edgecloudapp.com/v2/llm/gemini/v1beta/models Try another keyword or clear the current filters.
Data and contributions
Add its name, protocols, and endpoints to the Gateway Provider preset file, then open a PR for the next catalog sync.