Skip to main content

Providers

The gateway supports 19 AI providers. A provider becomes active when its required environment variables are set — no code changes or rebuilds needed.

All providers

ProviderVirtual KeyRequired Environment Variables
OpenAIopenaiOPENAI_API_KEY
AnthropicanthropicANTHROPIC_API_KEY
Google GeminigeminiGEMINI_API_KEY
MistralmistralMISTRAL_API_KEY
GroqgroqGROQ_API_KEY
CoherecohereCOHERE_API_KEY
DeepSeekdeepseekDEEPSEEK_API_KEY
Together AItogetherTOGETHER_API_KEY
PerplexityperplexityPERPLEXITY_API_KEY
Fireworks AIfireworksFIREWORKS_API_KEY
AI21ai21AI21_API_KEY
xAI (Grok)xaiXAI_API_KEY
Azure OpenAIazure-openaiAZURE_OPENAI_API_KEY + endpoint + deployment
Azure Foundryazure-foundryAZURE_FOUNDRY_API_KEY + AZURE_FOUNDRY_ENDPOINT
OllamaollamaOLLAMA_HOST (no API key required)
AWS BedrockbedrockAWS_REGION or AWS_ACCESS_KEY_ID
ReplicatereplicateREPLICATE_API_TOKEN
Vertex AIvertex-aiVERTEX_AI_PROJECT_ID
Hugging Facehugging-faceHUGGING_FACE_API_KEY

Provider capabilities

All providers support chat completions and streaming. Capability support varies by provider:

  • Embeddings — OpenAI, Cohere, Mistral, Azure OpenAI, Hugging Face
  • Image generation — OpenAI (DALL·E), Replicate, Fireworks
  • Local / self-hosted — Ollama
  • Managed cloud inference — AWS Bedrock, Vertex AI, Azure Foundry

Provider selection at runtime

The gateway selects a provider using the configured routing strategy. You can also force a specific provider for a single request using the X-Provider request header:

curl http://localhost:8080/v1/chat/completions \
-H "X-Provider: anthropic" \
-H "Content-Type: application/json" \
-d '{"model": "claude-3-5-sonnet-20241022", "messages": [{"role": "user", "content": "Hi"}]}'

If X-Provider is set, the routing strategy is bypassed for that request.

Model catalog

The gateway ships with a built-in catalog of 2,500+ model entries used for cost estimation and the /v1/models response. Run GET /v1/models to see all available models given your configured providers.

Next steps