Model providers

A model provider entry gives the gateway somewhere to send inference, and the credential to send it with. Catalog providers know their own connection details; an OpenAI-compatible endpoint needs a base URL as well.

What a provider needs

Most take a name and an API key. The name is not cosmetic — it is what appears in routes and in every trace, so openai-prod will serve you better than OpenAI the first time two entries exist. Some providers do not authenticate with a single key:

Provider	What it needs
Azure OpenAI	The Azure endpoint and API version, then either an API key or a service principal (tenant, client ID, client secret).
Amazon Bedrock	Access key ID, secret access key and region — plus a session token for temporary credentials.
Vertex AI	A GCP service-account JSON, uploaded or pasted. Project ID is read from the file.
OpenAI-compatible	A base URL, and whatever that endpoint expects, including nothing.

Keys are stored encrypted and never shown again. On an existing entry, leaving the key blank keeps the stored one; typing a new one replaces it. Rotating a credential is therefore an edit on the entry, and nothing downstream has to change — applications, policies and access all point at the entry, never at the secret.

Contract pricing

Cost in Analytics, on every trace, and in any budget policy is only as true as the rates behind it. By default TrustGate prices traffic at list rates. If you negotiated something else, the reporting is wrong until you say so here.

Setting	Meaning
List discount	A percentage off list, applied to every model on this provider.
Model override	A model slug with explicit input and output rates, in USD per million tokens. A trailing `` covers a family, so `gpt-4o-mini` catches the variants.

Overrides win wherever they match; the discount covers everything else. A flat contract needs only the discount. Add overrides for the models priced outside it. This matters beyond reporting: a budget policy that stops spend at a threshold is counting with these numbers.

Instances

A provider entry holds as many instances as you need — production and staging keys, two Azure deployments, one key per cost centre. Each is configured and tested on its own, and each is selectable independently when routing or an application picks a destination.

Every provider

These are the providers the gateway knows how to talk to. Anything not listed connects through OpenAI Compatible, which is the entry for self-hosted models and vendors that expose an OpenAI-shaped API. The format column is the wire protocol the gateway translates to. It matters in exactly one situation: a provider speaking the openai format accepts an OpenAI-shaped request unchanged, so moving traffic between two of them is a routing change and nothing else.

Provider	Code	Format	What it needs
OpenAI	`openai`	openai	API key. Optional base URL for a proxy or regional endpoint.
OpenAI Compatible	`openai_compatible`	openai	Base URL, plus whatever that endpoint expects — including nothing. This is the entry for self-hosted and unlisted vendors.
Google AI Studio	`google`	google	API key.
Google Vertex AI	`vertex`	google	A GCP service-account JSON, uploaded or pasted, and a location. Project ID is read from the file.
Anthropic	`anthropic`	anthropic	API key.
AWS Bedrock	`bedrock`	anthropic	Access key ID, secret access key and region; a session token for temporary credentials.
Azure OpenAI	`azure`	openai	Azure endpoint and API version, then either an API key or a service principal (tenant, client ID, client secret).
Mistral	`mistral`	openai	API key.
Groq	`groq`	openai	API key.
DeepSeek	`deepseek`	openai	API key.
xAI	`xai`	openai	API key.
Cerebras	`cerebras`	openai	API key.
OpenRouter	`openrouter`	openai	API key.
Cohere	`cohere`	cohere	API key.