---
title: "Get a specific provider"
method: GET
path: "/api/providers/{provider}"
tags: ["Providers"]
---

# Get a specific provider

`GET /api/providers/{provider}`

Returns the configuration for a specific provider.

## Path parameters

- `provider` string, required

## Response `200`

Successful response

- ProviderResponse — Provider configuration response
  - `name` 'openai' | 'azure' | 'anthropic' | 'bedrock' | 'cohere' | 'vertex' | 'vllm' | 'mistral' | 'ollama' | 'groq' | 'sgl' | 'parasail' | 'perplexity' | 'replicate' | 'cerebras' | 'deepseek' | 'gemini' | 'openrouter' | 'elevenlabs' | 'huggingface' | 'nebius' | 'xai' | 'runway' | 'fireworks' — AI model provider identifier
  - `network_config` NetworkConfig — Network configuration for provider connections
    - `base_url` string — Base URL for the provider (optional)
    - `extra_headers` object — Additional headers to include in requests
    - `default_request_timeout_in_seconds` integer — Default timeout for requests
    - `max_retries` integer — Maximum number of retries
    - `retry_backoff_initial` integer — Initial backoff duration in milliseconds
    - `retry_backoff_max` integer — Maximum backoff duration in milliseconds
    - `insecure_skip_verify` boolean — Disable TLS certificate verification for provider connections. This bypasses server certificate validation and should be used only as a last resort when a trusted CA chain cannot be configured. Prefer ca_cert_pem for self-signed or private CA deployments.
    - `ca_cert_pem` string — PEM-encoded CA certificate to trust for provider endpoint connections (e.g. self-signed or internal CA)
    - `allow_private_network` boolean — Allow connections to RFC 1918 private IPs (10.x, 172.16.x, 192.168.x). Enable for providers on a k8s pod network, LAN, or private VPC. Loopback addresses (localhost, 127.0.0.1, ::1) remain allowed regardless of this setting. Link-local addresses (169.254.x.x) are always blocked.
  - `concurrency_and_buffer_size` ConcurrencyAndBufferSize — Concurrency settings
    - `concurrency` integer — Number of concurrent operations
    - `buffer_size` integer — Size of the buffer
  - `proxy_config` object — Proxy configuration
    - `type` 'none' | 'http' | 'socks5' | 'environment'
    - `url` string
    - `username` string
    - `password` string
    - `ca_cert_pem` string
  - `send_back_raw_request` boolean
  - `send_back_raw_response` boolean
  - `store_raw_request_response` boolean
  - `custom_provider_config` object — Custom provider configuration
    - `is_key_less` boolean
    - `base_provider_type` 'openai' | 'azure' | 'anthropic' | 'bedrock' | 'cohere' | 'vertex' | 'vllm' | 'mistral' | 'ollama' | 'groq' | 'sgl' | 'parasail' | 'perplexity' | 'replicate' | 'cerebras' | 'deepseek' | 'gemini' | 'openrouter' | 'elevenlabs' | 'huggingface' | 'nebius' | 'xai' | 'runway' | 'fireworks' — AI model provider identifier
    - `allowed_requests` object — Allowed request types for custom providers
      - `list_models` boolean
      - `text_completion` boolean
      - `text_completion_stream` boolean
      - `chat_completion` boolean
      - `chat_completion_stream` boolean
      - `responses` boolean
      - `responses_stream` boolean
      - `count_tokens` boolean
      - `embedding` boolean
      - `speech` boolean
      - `speech_stream` boolean
      - `transcription` boolean
      - `transcription_stream` boolean
      - `image_generation` boolean
      - `image_generation_stream` boolean
      - `batch_create` boolean
      - `batch_list` boolean
      - `batch_retrieve` boolean
      - `batch_cancel` boolean
      - `batch_results` boolean
      - `file_upload` boolean
      - `file_list` boolean
      - `file_retrieve` boolean
      - `file_delete` boolean
      - `file_content` boolean
    - `request_path_overrides` object
  - `provider_status` 'active' | 'error' | 'deleted' — Status of the provider
  - `status` string — Operational status (e.g., list_models_failed)
  - `description` string — Error/status description
  - `config_hash` string — Hash of config.json version, used for change detection

## Other responses

- `400` — Bad request
- `404` — Provider not found
- `500` — Internal server error

---

[API](https://skmtc.net/getbifrost/apis/bifrost-api.md) · [All operations](https://skmtc.net/getbifrost/apis/bifrost-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/getbifrost/bifrost-api/versions/f8cab88f64ea/schema)