API Reference Overview

The DeepintShield gateway exposes an HTTP API that is drop-in compatible with the OpenAI, Anthropic, and Google Gemini wire formats. Point your existing client at the gateway, supply a virtual key, and every request is guarded, cached, routed, and logged before it reaches a provider - no SDK changes required.

Base URL

Point your client at the hosted DeepintShield cloud gateway:

https://app.deepintshield.com

If you run the Enterprise VPC / Self-Hosted data plane, replace the host with your own control plane (for example https://<your-deepintshield-host>) - the API surface remains the same. See Setting up the gateway.

Authentication

Inference requests are authenticated with a virtual key. Create and manage keys from the Web UI - see Virtual Keys.

The gateway accepts the virtual key in any of the following headers, so you can keep using whichever header your existing client already sends:

Header	Typical client
x-bf-vk: <virtual-key>	DeepintShield-native clients
Authorization: Bearer <virtual-key>	OpenAI SDKs and most HTTP clients
x-api-key: <virtual-key>	Anthropic SDK
x-goog-api-key: <virtual-key>	Google Gemini SDK

curl -X POST https://app.deepintshield.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DEEPINTSHIELD_VIRTUAL_KEY" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello, DeepintShield!"}]
  }'

Note

The model value carries the provider prefix (for example openai/gpt-4o-mini or anthropic/claude-3-5-sonnet). DeepintShield uses the prefix to resolve which configured provider to route to. See Supported providers.

Unified OpenAI-compatible endpoints

These routes accept and return the OpenAI request/response format and work with any configured provider - the gateway translates as needed. Send them to the gateway base URL.

Method	Path	Purpose
POST	/v1/chat/completions	Chat completions (streaming and non-streaming)
POST	/v1/responses	OpenAI Responses API
POST	/v1/completions	Legacy text completions
POST	/v1/embeddings	Embeddings
POST	/v1/rerank	Reranking
POST	/v1/audio/speech	Text-to-speech
POST	/v1/audio/transcriptions	Speech-to-text
POST	/v1/images/generations	Image generation
GET	/v1/models	List available models
GET	/health	Gateway health check (no auth)

Streaming responses follow the standard OpenAI Server-Sent Events format - set "stream": true in the request body. See Streaming.

Asynchronous jobs

Every inference endpoint above has an /v1/async/... variant that returns a job id you can poll, which is useful for long-running or batched work:

Method	Path	Purpose
POST	/v1/async/chat/completions	Submit an async chat completion job
GET	/v1/async/chat/completions/{job_id}	Retrieve the result of a job

The same {POST submit, GET {job_id} retrieve} pattern applies to responses, embeddings, audio/speech, audio/transcriptions, and the images/* endpoints.

Provider-native passthrough

If you prefer to keep your client speaking a provider’s exact dialect, send requests to the matching prefix. The gateway still applies guardrails, caching, routing, and logging, then forwards in the provider’s native format.

OpenAI

Prefix every OpenAI path with /openai:

POST /openai/v1/chat/completions
POST /openai/v1/responses
POST /openai/v1/embeddings
GET  /openai/v1/models

See the OpenAI integration.

Anthropic

Prefix every Anthropic path with /anthropic:

POST /anthropic/v1/messages
POST /anthropic/v1/messages/count_tokens
GET  /anthropic/v1/models

See the Anthropic integration.

Gemini

Prefix every Google Gemini path with /genai:

POST /genai/v1beta/models/{model}:generateContent
POST /genai/v1beta/models/{model}:streamGenerateContent
POST /genai/v1beta/models/{model}:embedContent
GET  /genai/v1beta/models

See the Gemini (GenAI) integration.

DeepintShield also exposes passthrough routes for Azure OpenAI, Amazon Bedrock, Cohere, LiteLLM, LangChain, and PydanticAI. Browse them all under Integrations.

Errors

Errors are returned with standard HTTP status codes and a JSON body. Common cases:

Status	Meaning
401	Missing or invalid virtual key
403	Request blocked by a guardrail or governance policy
429	Rate limit or budget exceeded
5xx	Upstream provider or gateway error

Where to next

Connect a provider

Add your provider keys and pick models.

Supported providers →

Use an SDK

Drop-in adapters for OpenAI, Anthropic, Gemini, and more.

Browse integrations →

Secure traffic

Configure guardrails across input, output, and tool calls.

Configure guardrails →

Manage keys

Create virtual keys, budgets, and rate limits.

Virtual keys →