Choose a Provider Upstream
A provider upstream is the model service an AISIX gateway calls after resolving a caller-facing model alias. AISIX stores the upstream credential in a provider key and uses an adapter to send requests in the format that the upstream expects.
Choose the setup path for the endpoint and account you use, not only for the model family. Configure Gemini through Google AI Studio when you have an AI Studio API key. Use Google Vertex AI when the model is hosted in a Google Cloud project.
Every setup below supports both AISIX Cloud and the open-source AISIX gateway. Each provider guide contains complete configuration sections for both products followed by one shared verification procedure.
Setup Paths
Choose among the direct provider and managed-platform setups:
| Setup | Use When | Adapter |
|---|---|---|
| OpenAI | You call models through an OpenAI API account. | openai |
| Azure OpenAI | An Azure OpenAI deployment hosts the model. | azure-openai |
| Anthropic | You call Claude through the Anthropic API. | anthropic |
| AWS Bedrock | AWS Bedrock hosts the model or inference profile. | bedrock |
| Gemini (Google AI Studio) | You call Gemini with a Google AI Studio API key. | openai |
| Google Vertex AI | A Google Cloud project hosts Gemini or another Vertex publisher model. | vertex |
| Qwen (Alibaba Cloud) | You call Qwen through Alibaba Cloud Model Studio. | openai |
| DeepSeek | You call models through the DeepSeek API. | openai |
| Groq | You call Groq-hosted models. | openai |
| Mistral AI | You call models through the Mistral API. | openai |
| Together AI | You call models from the Together AI catalog. | openai |
| OpenRouter | You call models from many vendors through one OpenRouter account. | openai |
| Fireworks AI | You call Fireworks-hosted models. | openai |
| Perplexity | You call the search-grounded Sonar models. | openai |
| Cohere | You call Cohere Command models, embeddings, or rerank. | openai |
| Cerebras | You call open-weight models on Cerebras inference hardware. | openai |
| Moonshot AI (Kimi) | You call Kimi models through the Moonshot AI platform. | openai |
| Zhipu AI (GLM) | You call GLM chat models or CogVideoX video generation. | openai |
| Hugging Face | You call open-weight models through the Hugging Face Inference Providers router. | openai |
| Baseten | You call Baseten Model APIs or a dedicated Baseten deployment. | openai |
Three more setups target providers whose video or rerank wire the gateway implements natively. The openai adapter shapes their chat-style and embeddings traffic, while the video-generation and rerank routes dispatch on the provider value itself. These providers are not listed on the models.dev catalog, so the dashboard suggests no model IDs for them, and cost metadata for budgets and usage reports is operator-supplied on the model alias — see each page's cost metadata section:
| Setup | Use When | Adapter |
|---|---|---|
| Jina | You call Jina embedding models, or reranker models through the rerank route. | openai |
| RunwayML | You run Runway Gen or Runway-hosted Veo video tasks through the video route. | openai |
| Volcengine Ark (Doubao) | You call Doubao chat models or Seedance video generation through Volcengine Ark. | openai |
AISIX Cloud can also create provider keys for community catalog providers from models.dev. These providers use the openai adapter by default, but AISIX does not curate provider-specific request rewrites, response rewrites, or base URL quirks for them. The open-source gateway can use the same provider identifiers as labels, but you must set the adapter and base URL explicitly in resources.yaml. Use these pages when the provider is available in the catalog and you want a provider-specific setup guide:
| Setup | Use When | Adapter |
|---|---|---|
| Amazon Nova API | You call Nova models through the direct API-key-based Nova endpoint rather than Bedrock. | openai |
| Cloudflare Workers AI | You call account-scoped Cloudflare Workers AI model IDs such as @cf/openai/gpt-oss-120b. | openai |
| Databricks | You call Databricks Model Serving endpoints in your workspace. | openai |
| DeepInfra | You call DeepInfra-hosted open-weight models through its OpenAI-compatible API. | openai |
| DigitalOcean Gradient AI | You call foundation models through DigitalOcean Serverless Inference. | openai |
| Meta Llama API | You call Llama models through Meta's direct OpenAI-compatible API. | openai |
| MiniMax | You call MiniMax models through the OpenAI-compatible API root. | openai |
| ModelScope | You call ModelScope API-Inference model IDs. | openai |
| Nebius Token Factory | You call open models hosted by Nebius Token Factory. | openai |
| NVIDIA NIM | You call the NVIDIA hosted NIM API or NVIDIA-published model IDs. | openai |
| Novita AI | You call Novita-hosted open models through its LLM API. | openai |
| OVHcloud AI Endpoints | You call models through the OpenAI-compatible endpoint from OVHcloud. | openai |
| SiliconFlow | You call SiliconFlow-hosted org-namespaced model IDs. | openai |
| Snowflake Cortex | You call models available in a Snowflake account through the Cortex REST API. | openai |
| Weights & Biases Inference | You call open models through W&B Inference. | openai |
| xAI | You call Grok models through the OpenAI-compatible API from xAI. | openai |
For another public or private endpoint that accepts OpenAI-compatible chat-completions requests, choose the corresponding general setup:
| Setup | Use When | Adapter |
|---|---|---|
| Other OpenAI-Compatible Providers | A public provider exposes an OpenAI-compatible API and does not have a dedicated setup guide. | openai |
| Ollama | You run models on a local or private Ollama server. | openai |
| vLLM | You serve a private model with the OpenAI-compatible server provided by vLLM. | openai |
| Bring Your Own Endpoint | You operate another private OpenAI-compatible endpoint, such as SGLang or an internal proxy. | openai |
Each setup creates the same gateway resources: a provider key, a model alias, and a caller API key. The setup page provides the credential, upstream model identifier, base URL, and adapter details for that provider. Compare route support in Provider Compatibility, or review the upstream request formats in Adapter Protocol Families.