List LLM Providers

Endpoint

GET /apiops/projects/{projectName}/llm-providers/

Authentication

Requires a Personal API Access Token.

Header

Authorization: Bearer YOUR_TOKEN

Request

Headers

Header	Value	Required
Authorization	Bearer {token}	Yes

Path Parameters

Parameter	Type	Required	Description
projectName	string	Yes	Project name

Query Parameters

None

Response

Success Response (200 OK)

{
  "status": "SUCCESS",
  "resultList": [
    {
      "id": "6712a3f4e1b2c3d4e5f60011",
      "projectId": "660f1e2a9c4b5a6d7e8f9012",
      "projectName": "MyProject",
      "name": "deepseek-primary",
      "description": "DeepSeek production provider",
      "enabled": true,
      "providerType": "DEEPSEEK",
      "endpoint": "https://api.deepseek.com/v1",
      "apiVersion": "v1",
      "organizationId": null,
      "authScheme": "BEARER",
      "authHeaderName": "Authorization",
      "credentialSource": "GATEWAY",
      "apiKeyLocation": "HEADER",
      "apiKeyPrefix": null,
      "allowClientOverride": false,
      "apiKeySet": true,
      "apiSecretSet": false,
      "serviceAccountJsonSet": false,
      "supportedModels": [
        {
          "modelId": "deepseek-chat",
          "displayName": "DeepSeek Chat",
          "contextWindow": 64000,
          "maxOutputTokens": 8192,
          "pricePerMillionInput": 0.27,
          "pricePerMillionOutput": 1.10,
          "capabilities": ["function_calling"],
          "modality": "TEXT",
          "isDeprecated": false
        }
      ],
      "providerRpmLimit": 500,
      "providerTpmLimit": 100000,
      "coldStartRetryEnabled": false,
      "lastHealthCheckAt": "2026-07-13T09:15:00Z",
      "healthStatus": "HEALTHY",
      "lastLatencyMs": 240,
      "providerDefinitionId": null,
      "allowedModelIds": ["deepseek-chat"],
      "deploymentType": "CLOUD",
      "builtIn": false,
      "metadata": []
    }
  ],
  "resultCount": 1
}

Response Fields

Field	Type	Description
status	string	Response status: SUCCESS or FAILURE
resultList	array	List of LLM provider objects
resultCount	integer	Total number of providers returned

LLM Provider Object Fields

Field	Type	Description
id	string	Internal identifier (read-only)
projectId	string	Project identifier (read-only)
projectName	string	Project name (read-only)
name	string	Provider name (unique within the project)
description	string	Free-text description
enabled	boolean	Whether the provider is active
providerType	string	Provider type enum constant (e.g. OPENAI, ANTHROPIC, AZURE_OPENAI, BEDROCK, VERTEX, DEEPSEEK, GROQ, VLLM, OLLAMA)
endpoint	string	Base API URL (e.g. https://api.deepseek.com/v1)
wireProtocol	string	Wire protocol the adapter speaks (OPENAI_COMPATIBLE, ANTHROPIC, BEDROCK, VERTEX, COHERE). Snapshot taken at save time from the built-in template or custom connection settings — read-only here. See note below.
defaultChatCompletionPath	string	Chat-completion path appended to endpoint. Snapshot; read-only.
defaultEmbeddingPath	string	Embedding path. Snapshot; read-only.
defaultAudioTranscriptionPath	string	Audio-transcription path. Snapshot; read-only.
defaultAudioSpeechPath	string	Text-to-speech path. Snapshot; read-only.
defaultImageGenerationPath	string	Image-generation path. Snapshot; read-only.
defaultResponsesPath	string	Responses-API path. Snapshot; read-only.
apiVersion	string	Provider API version (e.g. v1, 2024-02-15-preview)
organizationId	string	Organization identifier (OpenAI org-...; optional)
authScheme	string	Auth scheme enum constant (BEARER, API_KEY_HEADER, BASIC, AWS_SIGV4, OAUTH2, NONE, CUSTOM) — see Credential Type by authScheme
authHeaderName	string	Header used to carry the credential (e.g. Authorization, x-api-key, api-key)
credentialSource	string	Who supplies the credential: GATEWAY or CLIENT. Never null in the response — legacy records default to GATEWAY
apiKeyLocation	string	Where the API key travels: HEADER or QUERY. Never null in the response — legacy records default to HEADER
apiKeyPrefix	string	Stored value prefix; null means the auth scheme's own prefix is used, "" means the raw key with no prefix
allowClientOverride	boolean	true if an incoming request's own auth header is kept instead of the stored credential (GATEWAY mode only); null/false otherwise
apiKeySet	boolean	true if an apiKey is configured (secret value never returned)
apiSecretSet	boolean	true if an apiSecret is configured (secret value never returned)
serviceAccountJsonSet	boolean	true if a GCP Vertex service-account JSON is configured (secret value never returned via APIops)
supportedModels	array	Per-provider model snapshots (see fields below)
providerRpmLimit	integer	Organization-level requests-per-minute limit
providerTpmLimit	integer	Organization-level tokens-per-minute limit
coldStartRetryEnabled	boolean	Retry on 503 for self-hosted providers (vLLM/Ollama cold start)
lastHealthCheckAt	string	ISO-8601 timestamp of the last health probe (read-only)
healthStatus	string	Last probe result enum constant (UNKNOWN, HEALTHY, DOWN) (read-only)
lastLatencyMs	integer	Last probe round-trip time in milliseconds (read-only)
providerDefinitionId	string	Optional catalog provider definition reference
allowedModelIds	array[string]	Integration-level model filter; empty/null = all models allowed
deploymentType	string	Deployment type enum constant (CLOUD, ON_PREM)
builtIn	boolean	true for system-provided built-in templates (read-only).
metadata	array	Custom key/value metadata entries; secret values are nulled

Endpoint path snapshots

wireProtocol and the six default*Path fields are snapshots: the manager copies them from the built-in provider template (or custom connection settings) when the connection is saved, and the gateway reads only this copy. They are returned for visibility and are not writable through this API — send them and they are ignored; omit them and the stored values are preserved.

The effective request URL is endpoint + the path for the modality being called. Both halves support Apinizer variable resolution (${env.name} and #{contextVar}), resolved at request time, so one connection definition can point at different paths per environment. A path left empty falls back to the provider type's built-in default.

Supported Model (LlmModelDef) Fields

Field	Type	Description
modelId	string	Model identifier (e.g. deepseek-chat)
displayName	string	Human-readable model name
contextWindow	integer	Maximum context window in tokens
maxOutputTokens	integer	Maximum output tokens
pricePerMillionInput	number	USD per 1M input tokens
pricePerMillionOutput	number	USD per 1M output tokens
pricePerMillionCached	number	USD per 1M cached tokens (optional)
pricePerMillionCacheWrite	number	USD per 1M cache-write tokens (flat rate; optional)
cacheWritePricesByTtl	array	Cache-write price per TTL — see Cache-Write Price Fields
contextTierPrices	array	Long-context price tiers — see Context-Tier Price Fields
serviceTierPrices	array	Provider service-tier price multipliers — see Service-Tier Price Fields
capabilities	array[string]	Capability tags, normalized on save — see Capabilities Normalization
modality	string	Modality enum constant (TEXT, VISION, AUDIO, EMBEDDING, RERANK, MULTIMODAL, IMAGE)
isDeprecated	boolean	Whether the model is deprecated

EnumStatus

• SUCCESS - Operation successful
• FAILURE - Operation failed

Error Response (400 Bad Request)

{
  "status": "FAILURE",
  "resultMessage": "Project (name: MyProject) was not found!"
}

Error Response (401 Unauthorized)

{
  "status": "FAILURE",
  "resultMessage": "Token is not valid!"
}

cURL Example

curl -X GET \
  "https://demo.apinizer.com/apiops/projects/MyProject/llm-providers/" \
  -H "Authorization: Bearer YOUR_TOKEN"

Notes and Warnings

• Secret Masking (INV-06):
  • apiKey, apiSecret and serviceAccountJson are never returned in plaintext
  • Presence is exposed via apiKeySet / apiSecretSet / serviceAccountJsonSet boolean flags
  • Secret metadata values are returned as null
• Enum Serialization:
  • providerType, authScheme, credentialSource, apiKeyLocation, deploymentType and model modality serialize as the enum constant name (e.g. DEEPSEEK, BEARER, GATEWAY, HEADER, CLOUD, TEXT), not lowercase
• Empty List:
  • If no providers exist, an empty resultList with resultCount: 0 is returned
• Usage References:
  • The usedByRefs field (API proxies referencing the provider) is only populated by the single-provider Get LLM Provider endpoint, not by this list endpoint

Related Documentation

• Get LLM Provider - Retrieve a single provider by name
• Create LLM Provider - Create or upsert a provider
• LLM Providers API - Resource overview and permissions
• Authentication Guide - How to obtain and use API tokens