# Console form reference

> The exact field labels, conditional fields, and validation messages of the Admin Console's provider and model forms, verbatim as the UI shows them.

Every field label, placeholder, and validation message the Admin Console's provider and model forms display, quoted verbatim so a string seen on screen can be searched here. What a resulting state means afterwards (credential labels, status chips, empty lists) is listed in Console messages and states.

## How to read this page

- Strings are quoted exactly as rendered, including the UI's own punctuation. The surrounding prose follows the documentation's style; the quoted strings do not, and are not corrected.
- A field marked **required** shows the Console's asterisk marker and blocks saving when empty, with the quoted validation message.
- In the edit drawers, a changed field carries a **(modified)** badge, and closing with unsaved work asks **"Discard unsaved changes?"** with **Keep editing** and **Discard changes**. The footer shows **"You have unsaved changes."** while edits are pending.

## Add provider

Opened with **Add provider** on the Providers list. The drawer is titled **Add provider**, described as "Register a provider so models can reference it.", and submits with **Add provider** (**"Saving…"** while in progress).

| Field | Required | Shown | Notes |
| --- | --- | --- | --- |
| **Provider identifier** | Yes | Always (create only) | Placeholder `openai`. Hint: "Lowercase identifier (a-z, 0-9 only). Must start with a letter." Empty: "Provider identifier is required". An identifier already in the catalog is refused on this field with the catalog's message, "catalog: provider "&lt;identifier&gt;" already exists; use UpsertProvider to edit it", and nothing is written |
| **Display name** | No | Always | Placeholder `OpenAI`. "Optional label shown in tables and search filters." |
| **API base URL** | Yes | Always | Placeholder `https://api.example.com/v1`. Empty: "API base URL is required" |
| **Auth method** | No | Always | Options **API Key**, **None**, **AWS**, **Vertex**, **Vertex Anthropic**, **Google AI Key**, plus any server-supplied types as raw values. "Keep this aligned with how models authenticate against the provider." |
| **Region** | Yes | Auth method **AWS** | Placeholder `us-east-1`. "AWS region for the Bedrock service." Empty: "Region is required for AWS" |
| **Region** | Yes | Auth method **Vertex** or **Vertex Anthropic** | Placeholder `us-east5`. "Google Cloud region for Vertex AI." Empty: "Region is required" |
| **GCP Project Name** | Yes | Vertex auth methods | Placeholder `my-gcp-project`. "The GCP project ID where Vertex AI is enabled." Empty: "GCP Project Name is required" |
| **Schema Version** | No | Vertex auth methods | Read-only, pre-filled `vertex-2023-10-16`. "Vertex AI API schema version (readonly)." |
| **Upstream API** | No | Always | Options **Default for auth type**, **OpenAI compatible**, **Anthropic Messages**, **AWS Bedrock**, **Google Vertex AI**, **Vertex AI Anthropic** |
| **Secret type** | No | Non-AWS auth methods | Options **Password** and **Service Account JSON**; forced to Service Account JSON for Vertex auth ("Service Account JSON is required for Vertex auth types.") |
| **Provider secret** | Auth-dependent | Always | See [Provider secret entry](#provider-secret-entry) below |
| **First-party provider** | No | Always | Switch. "Highlights the provider across search results and listings." |
| **Enable provider** | No | Always | Switch. "Disable to keep the provider hidden until it is configured." |

Changing the auth method away from a cloud type while its region or project name is filled asks **"Change Auth Method?"**: "Changing the auth method will remove the current cloud provider configuration fields (region, project name, etc.). This action cannot be undone.", with **Cancel** and **Continue**.

### Provider secret entry

What the secret slot shows depends on the auth method:

- **Non-AWS methods**: a single input or JSON textarea, placeholder "Enter provider secret". A non-JSON value under a Vertex method is rejected with "Invalid JSON format for service account". The hint "Secret values aren't shown. Enter a new secret and Save (or Rotate) to update it." states the write-only contract: no read ever returns a stored secret.
- **AWS**: paired `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` inputs, or the switch **"Use IRSA / EKS Pod Identity (no static keys)"**. With the switch on: "No static keys needed — the data plane authenticates to Bedrock with its pod IAM role (IRSA / EKS Pod Identity)." With it off, both keys are needed; a half-filled pair is rejected with "Enter both AWS keys, or turn on \"Use IRSA / EKS Pod Identity\" above".

## Edit provider

Opened from a provider row. The drawer is titled **Edit** followed by the provider's display name, described as "Update how this provider appears across the Admin Console.", and submits with **Save changes**, disabled until a field changes.

Only the metadata fields render here: **Display name**, **API base URL**, **Upstream API**, **First-party provider**, and **Enable provider**, each behaving as in the table above. The auth method and secret are not edited on this surface; credentials are entered at creation and rotated where the credential status is shown, described under [Credential rotation messages](#credential-rotation-messages).

A stored API base URL cannot be cleared on an edit. An empty field shows "API base URL is required". An edit request that still sends an empty value is refused on the field with "An API base URL cannot be cleared once set. Keep the current value.". The API lets an AWS or None provider be created without a base URL, but this exemption does not apply to an edit.

### Read-only provider detail

Editing the provider catalog needs a platform grant, which is described under [Platform Provider Admin](/agent-router-enterprise/guides/identity-and-access-management/manage-roles-and-permissions/#platform-provider-admin). A user who holds `providers.edit` in the organization but not that platform grant, for example through a custom role, opens the drawer read-only:

- An alert at the top of the drawer reads "Editing the provider catalog needs catalog admin".
- The fields are disabled, and **Save changes** stays disabled.
- The detail is the organization view of the provider, without the key suffix or Agent Router's internal metadata.

The credential rotation dialog shows the same alert in place of its fields. A provider write refused for the same reason, for example from the **Availability** switch on the Providers list, reports the same message.

### Credential rotation messages

The credential half of the provider form appears on the surfaces that manage a stored secret (the onboarding wizard, and rotation reached from the catalog row). Its states, verbatim:

| Message | Shown when |
| --- | --- |
| "A static access key is stored." | AWS provider with a stored key. Beside it, **Remove key (go keyless)** ("Removing…" in progress) |
| "Keyless — the data plane authenticates to Bedrock with the pod's IAM role (e.g. IRSA or EKS Pod Identity). Enter keys below and Save (or Rotate) to switch to a static key." | AWS provider with no stored key |
| "A secret is stored for this provider. Enter a new one and Save (or Rotate) to replace it." | Non-AWS provider with a stored secret; the input placeholder reads "Enter new secret to rotate" and the **Rotate** button ("Rotating…" in progress) stays disabled until a secret is typed |
| "No secret is stored yet — enter one and Save." | Non-AWS provider with no stored secret |
| "Enter a secret to rotate" | **Rotate** clicked with the input empty |
| "Other fields have unsaved edits — Rotate stores only the secret. Use \"Save changes\" to save the edits and the secret together." | **Rotate** clicked while other fields hold edits (the quoted button name is the surface's submit label) |
| "This auth method requires a key. Enter one and save to switch." | The auth method was changed to a credentialed type with no key entered |
| "Changing the auth method requires a key in the new format — the stored key belongs to the previous method. To go keyless, remove the stored key first." | Auth method changed on a provider holding an AWS key, no new key entered (non-AWS stored keys are told "To go keyless, switch to None and save first.") |
| "Unable to rotate provider secret" / "Unable to save provider secret" / "Unable to remove provider secret" | The corresponding write failed and the server supplied no more specific message |

## Add model and Edit model

Opened with **Add model** on the Models list, or **Edit** on a model row. The Add drawer is described as "Register a model for an enabled provider." and submits with **Add model**; the Edit drawer, titled **Edit** plus the model's name, is described as "Update model metadata and pricing details." and submits with **Save changes**, disabled until a field changes.

| Field | Required | Shown | Notes |
| --- | --- | --- | --- |
| **Provider** | Yes | Always | Add: a picker of enabled providers only ("Only providers that are currently enabled are listed."; empty catalog: "No enabled providers available" and "Enable a provider before creating models."). Edit: read-only, "Provider assignments are fixed; create a new model to move it." |
| **Model identifier** | Yes | Always | Placeholder `e.g. gpt-4o`. "Model identifier requested by the client." Empty: "Model identifier is required". Duplicates are refused, see below |
| **Override upstream model identifier** | No | Always | Switch: "Send a different identifier to the provider" on, "Provider receives the model identifier as-is" off |
| **Upstream model identifier** | Yes | Override switch on | Placeholder `e.g. gpt-4o`. "Use the exact identifier expected by the provider." |
| **Mode** | Yes | Always | Options **Audio Speech**, **Audio Transcription**, **Chat**, **Classifier**, **Completion**, **Embedding**, **Image Generation**, **Moderation**, **Prompt Guard**, **Rerank**, **Responses**. Empty: "Select a mode" |
| **Availability** | No | Always | Switch: "Enable immediately" on, "Create as disabled" off |
| **Autofallback** | No | Always | Switch: "Fallback routing enabled" on, "Use single provider" off |
| **Fallback Models** | Yes | Autofallback on | An ordered picker ("Search for a model...", three-character minimum: "Type at least 3 characters to search"). Empty: "At least one fallback model is required when autofallback is enabled"; self-reference: "A model cannot use itself as a fallback model" |
| **Input tokens price (per 1M)** | No | Always | Under the **Pricing** heading. Placeholder `e.g. 15`, "Specify as USD per million input tokens." (output: `e.g. 60`) |
| **Cached tokens price (per 1M)** | No | Always | USD per million **cache-read** tokens: tokens the provider serves from its prompt cache instead of reprocessing. `cache_read_per_million` in the management API. Empty means not applicable |
| **Caching tokens price (per 1M)** | No | Always | USD per million **cache-write** tokens: tokens written into the provider's prompt cache. `caching_per_million` in the management API, a separate rate from the cache-read price above. The model holds one write rate, so a provider that prices cache writes by retention tier (Bedrock prices Anthropic 5-minute and 1-hour cache writes differently) cannot be represented per tier; enter the rate for the retention the workload uses, and treat mixed retentions as an approximation |
| **Context window** | No | Always | Placeholder `e.g. 128000`. "Maximum supported context window for this model." |
| **Capabilities** | No | Always | Twenty checkboxes from **Function Calling** through **Url Context** ("Select all capabilities provided by this model."). The rendered casing, including "Pdf Support" and "Url Context", is the UI's own |
| **Modalities** | No | Always | **Input** and **Output** checkbox columns (Audio, Document, Embedding, Image, Text, Video in; Audio, Code, Embedding, Image, Text, Video out) |
| **Limits (JSON)** | No | Under **Advanced** | Placeholder `e.g. { "rpm": 600, "tpm": 200000 }`. "Model-level limits such as rpm, tpm, or max tokens." |
| **Additional pricing (JSON)** | No | Under **Advanced** | Placeholder `e.g. { "input_per_image": 0.004 }` |
| **Envoy AI Gateway headers** | No | Under **Advanced** | Key/value rows ("Header name" / "Header value", added with **Add Header name**). Duplicate keys are rejected: "Duplicate header names:" followed by the offending names |
| **Metadata (JSON)** | No | Under **Advanced** | Typing `aigw-headers` here warns "Envoy AI Gateway headers should be managed in the dedicated field above, not in the metadata JSON." |

### Model name uniqueness

Model identifiers are unique across every provider, and both drawers enforce it twice:

- **While typing**, a duplicate shows the inline notice: ""&lt;model&gt;" is already registered under" the owning provider, "Model names must be unique across every provider — pick a different identifier (try appending the provider) and use "Override upstream model identifier" to still send" the original name "to the provider." Saving is blocked while the notice shows.
- **On save**, a race that reaches the server anyway returns the toast **Model not created** (or **Model not updated**): the identifier "is already taken. See the highlighted field below."

The override switch is the designed escape: the catalog name must be unique, while the identifier sent upstream need not be.

### Catalog discovery and copying settings

The Add drawer offers two pre-fill paths, both optional:

- **"Tetrate Agent Router public model catalog"**: with a provider selected, **Load catalog** lists the public catalog entries for it ("Agent Router public catalog for" the provider "; not your configured models. Selecting one pre-fills this form."), searchable with "Search catalog...", each row carrying its context size (`128K ctx`) and price (`$N.NN/$N.NN per 1M`, or `Free`). **Use selected model** applies the row and confirms with "Loaded settings for" the model. An empty result reads "No models found for" the provider "in catalog".
- **"Copy settings from an existing model"** (in Edit: "Copy settings from another model"): searches existing models ("Search models...") and applies one with **Copy settings**, confirming "Settings copied from selected model". The section states its boundary: "Provider, model identifier, and enabled state are not copied."

## Guardrail provider drawer

Guardrail providers are created only by cloning a catalog template: the Guardrail Providers page has no template-free add button, by design. **Use this template** on a catalog card opens the drawer, titled **Add provider from** the template's name and described as "Configure an external guardrail provider connection.".

| Field | Shown | Notes |
| --- | --- | --- |
| **Name** | Always | Placeholder `e.g. Azure Content Safety`; pre-filled with the template name plus "(copy)" |
| **Enabled** | Always | Switch |
| **Endpoint** | Azure Content Safety kind | Placeholder `https://tars-cs.cognitiveservices.azure.com`. "The endpoint of your Azure AI Content Safety resource, including the scheme." Empty: "Enter the endpoint of your Azure AI Content Safety resource."; not an absolute URL: "Enter a full URL including the scheme, e.g. https://tars-cs.cognitiveservices.azure.com" |
| **API key** | Azure Content Safety kind | Placeholder "Enter the resource key" (or "Enter a new key to rotate" once stored). "Credentials are never shown. Enter one and save — it is stored encrypted and no read path returns it." |
| **API version (optional)** | Azure Content Safety kind | Placeholder `2024-09-01`. "Leave blank to track the default." |
| **Timeout (optional)** | Azure Content Safety kind | Placeholder `10s`. "How long a single check may take, e.g. 10s." |
| **Groundedness API version (optional)** | Azure Content Safety kind | Placeholder `2024-09-15-preview`. "Used only by the factual-consistency check, which is still in preview on Azure's side." |
| **Region** | Amazon Bedrock Guardrails kind | Required. Placeholder `us-east-1`. "The AWS region your guardrails are in. Every rule on this provider binds a guardrail in this region." Empty: "Enter the AWS region your guardrails are in, e.g. us-east-1."; not a Region code: "Enter an AWS region code such as us-east-1 or eu-central-1." |
| **Endpoint (optional)** | Amazon Bedrock Guardrails kind | Placeholder shows the Regional endpoint for the chosen Region, `https://bedrock-runtime.<region>.amazonaws.com`, which is never stored. "Leave blank for the regional endpoint; set it for a VPC endpoint or FIPS host." For a Region starting with `cn-`, `eusc-`, `us-iso-`, `us-isob-`, `us-isof-`, or `eu-isoe-`, the label reads **Endpoint**, the placeholder is `https://bedrock-runtime.<host>`, and the help reads "Required for this region; enter its Bedrock runtime URL."; a blank one is refused with "Region &lt;r&gt; needs the endpoint set to its Bedrock runtime URL.", and an empty stored value with "Leave the endpoint blank for the regional endpoint, or enter an absolute http(s) URL." A trailing slash is refused with "Remove the trailing slash from the endpoint.", and credentials in the URL with "Remove the credentials from the URL. Store the IAM user credentials below instead." |
| **Timeout (optional)** | Amazon Bedrock Guardrails kind | Placeholder `10s`. "How long one call may take. Leave blank for 10s." Not a duration: "Enter a duration such as 10s or 1500ms. Leave it blank for the default."; zero or less: "Enter a timeout greater than 0." |
| **Access key ID**, **Secret access key** | Amazon Bedrock Guardrails kind | Grouped under **IAM user credentials**; both or neither. "Needs a static IAM-user access key with `bedrock:ApplyGuardrail` on the bound guardrails. IAM roles and temporary credentials aren't supported yet." Half a pair is refused beside the missing half: "Enter the secret access key too. A credential needs both halves." or "Enter the access key ID too. A credential needs both halves." |
| **Configuration** | Other kinds | A key/value grid ("Key" / "Value", added with **Add Entry**) |

The drawer walks a three-step sequence, and the primary button renames per step: **Create provider** ("Creating..."), then **Store credential** ("Storing..."), then **Enable provider** ("Enabling..."). The status box narrates the same: "Cloning" the template "Edit the connection details below." before creating, and afterwards a message stating what remains ("Enabling it is the only thing left" once the credential is stored, or "Its credential is the only thing left to store"). A failed step is recoverable in place: a failed credential write reports the provider "was created, but its credential was not stored", a failed enable says it "could not be enabled. Retry, or enable it from the provider list.", and retrying with an empty key is refused with "Enter the credential. The provider was created without one.".

## Guardrail drawer

**Add guardrail** on the Rules page opens the drawer titled **New Guardrail** (**Edit Guardrail** when editing), described as "Define how this guardrail classifies and enforces policy.". It submits with **Create** or **Save guardrail** ("Saving..." in progress).

| Field | Notes |
| --- | --- |
| **Name** | Placeholder `e.g. PII Protection` |
| **Description** | Free text |
| **Type** | **Compliance**, **Security**, **Policy**, **Custom**, **Evaluator** |
| **Category** | **Data privacy**, **Financial**, **Healthcare**, **Government**, **Compliance**, **Custom** |
| **Severity** | **Low**, **Medium**, **High**, **Critical**, under the **Configuration** heading |
| **Failure mode** | **Fail closed** or **Fail open** |
| **Evaluation timeout (ms)** | Under the **Response** heading, default 5000. "Maximum time to wait for guardrail evaluation before applying the failure mode." |
| **Triggered response** | Seeded for a new guardrail with "This request was blocked by a guardrail policy." |

## Guardrail rule drawer

**Add rule** in a guardrail's expanded rules panel opens the drawer titled **Add Rule** (**Edit Rule** when editing), described as "Rules define which provider check runs and how it is enforced.". It submits with **Add rule** or **Save rule** ("Saving..." in progress).

| Field | Notes |
| --- | --- |
| **Name** | Placeholder `e.g. Detect PII` |
| **Description** | Free text |
| **Active** | Switch; an inactive rule shows an **Inactive** badge in the rules panel |
| **Provider** | "Select provider"; the choice decides which check types and stages are offered |
| **Check type** | The provider's supported checks, rendered as labels such as **PII**, **Toxicity**, **Prompt Injection**, **Jailbreak**, **Secrets**, **Banned Topics**; unsupported checks render disabled |
| **Run on** | **Input**, **Output**, or **Input &amp; Output**; stages a provider does not support for the check are disabled, with a hint naming the constraint (for example "Bias runs on output only for this provider.") |
| **Action** | **Block** or **Redact** |
| **Mode** | **Enforce** or **Monitor** |
| **Configuration** | Per-check fields, summarized below; **Edit as JSON (advanced)** exposes the raw object ("Provider-specific settings as a JSON object."). Invalid JSON is refused with "Configuration must be valid JSON" |
| **Triggered response** | Placeholder "Optional message shown when this rule fires." |

A rule on an Amazon Bedrock Guardrails provider asks for the **Guardrail ID or ARN** (placeholder `gr4ab1cd2ef3`; "Shown on the guardrail's page in the Amazon Bedrock console. An ARN must name a guardrail in this provider's region."; missing or malformed: "Enter the guardrail ID or ARN") and the **Version** (placeholder `e.g. 3`; "A published version number, or DRAFT."; otherwise: "Enter a numbered version (e.g. 3) or DRAFT"). Both fields are trimmed, and `draft` in any case is saved as `DRAFT`. Choosing `DRAFT` shows "DRAFT changes whenever someone edits the guardrail in AWS; use a numbered version in production." Under **Check type** the drawer states "Bedrock decides what this guardrail detects. The check type labels this rule in triggers and metrics."; for `prompt_injection` and `jailbreak`, **Run on** offers input only. A save refused by the data plane version check, including one that turns an inactive rule on, shows the server's message as returned, such as "data plane &lt;id&gt; runs &lt;version&gt;, and Amazon Bedrock Guardrails rules need 0.11.0 or newer: an older build drops them without enforcing them, so upgrade it first", and the drawer stays open.

A check with nothing to configure says so in place: an LLM Guard provider states "Scanners are configured on the LLM Guard server; rules carry no per-check configuration.", and other kinds state "This check uses the provider's built-in detection; no configuration is needed."

### Per-check configuration fields

The **Configuration** block renders fields for the selected provider and check. The recurring shapes:

- **Pattern-based checks** (a regexp provider, or the regexp check): a **Patterns** picker from the pattern library ("Search patterns…"; at least one selection is required: "Select at least one pattern") and a **Redaction format** field, placeholder `[REDACTED]`, whose help documents the `{pattern_name}` placeholder.
- **Threshold-based checks** (ban topics, bias, toxicity): a tag list of categories or topics plus a threshold field, placeholder "Provider default", "Between 0 and 1. Leave empty to use the provider default."
- **Prompt injection**: **Sensitivity**, a **Known injection patterns** regex list ("Regexes matched against the input; any match triggers immediately, before ML detection."), and an **ML-based detection** switch.
- **Ban substrings**: the literal strings, plus a **Case sensitive** switch ("Off matches regardless of casing.").
- **Secrets**: named **Secret types** with clickable suggestions, **Custom patterns**, and an **Entropy analysis** switch ("Also flag long, high-entropy tokens that look like credentials.").
- **Language**: **Allowed languages** as ISO 639-1 codes and a **Block unknown languages** switch ("Trigger when no language can be detected.").
- **Grounding sources** (the factual-consistency check): one reference text per line; "The rule triggers when the response contains claims not grounded in these sources."

## Pattern drawer

**New pattern** on the Patterns page opens the drawer titled **New pattern**, described as "Create a reusable regex pattern for guardrail rules.". It submits with **Create pattern** ("Creating..." in progress).

| Field | Notes |
| --- | --- |
| **Name** | Placeholder `credit_card_number`. "Unique identifier (snake_case). Cannot be changed later."; an invalid value flips the hint to "Must be snake_case: lowercase, starting with a letter." |
| **Display name** | Placeholder `Credit card number` |
| **Category** | Placeholder `financial`, with existing categories suggested. "Pick an existing category or type a new one." |
| **Description** | Placeholder "Optional description of what this pattern matches." |
| **Regex** | Validated live in the browser ("Regex compiles in the browser before it is saved."); an invalid expression shows the browser's own error |

A pattern's detail page carries the same fields in edit mode (the name read-only), plus a **Test pattern** card: paste text under **Sample text** ("Paste sample text to test against this pattern."), **Run**, and the result counts matches with the matches highlighted. Builtin patterns cannot be edited or deleted: "Builtin patterns are managed by the system and cannot be edited or deleted."

## Related

- [Console messages and states](/reference/console-messages/): what a badge, chip, or empty state means once configuration is saved
- [Add providers and models to projects](/agent-router-enterprise/guides/operate-and-govern/manage-models-and-providers/add-providers-and-models-to-projects/): the workflow these forms belong to
- [Configuration propagation](/reference/configuration-propagation/): when a saved change reaches the gateway
