Skip to main content
The gateway delegates provider-specific dispatch to bifrost/core, which LangWatch embeds as a Go library. This page lists the providers the gateway can talk to today and the path to configuring each.

​
Configure a provider credential once, use from many VKs

Every provider credential lives in the LangWatch Model Providers table (under Settings → Model Providers). It’s the same surface that powers evaluators and the playground, no separate “gateway providers” store. Gateway-only settings (rate limits, fallback priority, providerConfig overrides) live directly on the ModelProvider itself, on the Advanced (Gateway) tab of the editor. There is no separate binding wrapper. VKs reference ModelProviders by id; the order in the bound routing policy drives primary + fallback selection. 
ModelProvider (raw credential + Advanced/Gateway settings)
  └── RoutingPolicy.modelProviderIds[] (ordered primary + fallback)
       └── VirtualKey.routingPolicyId (or default policy from the org)
This means: rotating the raw OpenAI key rotates it everywhere; changing a rate limit only affects gateway traffic (it’s on the Advanced tab, not the basic credential); changing a VK’s provider mix is one edit to the routing policy it references.

​
Supported providers (v1)

ProviderRoutes supportedAuth methodsCaching passthrough
OpenAIchat, responses, embeddings, images, audio, moderationsAPI keyauto-prefix
Anthropicmessages, chat (translated), streamingAPI keycache_control blocks
Azure OpenAIchat, responses, embeddings, images, audioAPI key, AADauto-prefix
AWS Bedrockmessages, chat, embeddings (Titan)AWS SigV4, IRSAcachePoint
Google Vertex AImessages, chatGCP ADC, SA JSONimplicit context cache
Google GeminichatAPI keyimplicit context cache
Custom OpenAI-compatiblechat, embeddings (depends on upstream)Bearer, custom headeropaque
Behind the scenes bifrost/core also supports Groq, Cohere, Mistral, Ollama, vLLM, SGLang, Perplexity, ElevenLabs, and others. These will light up in the UI as LangWatch ships the per-provider configuration forms.

​
Picking a primary + fallback

Most VKs end up with 1-2 fallback providers. Guidelines:
  • Anthropic-first with Bedrock-Anthropic fallback. Same models on both sides; Bedrock is a warm backup during Anthropic direct outages.
  • OpenAI-first with Anthropic fallback. Different model families but Claude Haiku can serve gpt-5-mini traffic acceptably for coding tasks.
  • Azure-first with OpenAI direct fallback. Pins traffic inside Azure data-residency most of the time but tolerates regional Azure outages.
See Fallback Chains for trigger semantics.

​
Multi-region, multi-account

Each ModelProvider row pins a region (Azure endpoint, Bedrock region, Vertex project). If an organisation spans multiple regions, create sibling ModelProvider rows of the same family with a naming convention (e.g. openai-eu, openai-us) and use VK model_aliases to route gpt-5-mini-eu vs gpt-5-mini-us to the right ModelProvider id.