Passthrough

Overview

Passthrough integrations let you call provider-native API paths and payloads through DeepintShield. You keep the exact request and response shapes your provider SDK expects, and the provider’s response (status, headers, and body) comes back unchanged for both streaming and non-streaming requests, while still gaining DeepintShield features such as governance, logging, and observability.

Use passthrough when you need a provider endpoint that is not yet covered by a dedicated DeepintShield integration route.

---

Endpoints

Point your provider SDK or HTTP client at the matching passthrough endpoint:

Endpoint	Provider
/openai_passthrough	OpenAI
/anthropic_passthrough	Anthropic
/genai_passthrough	Gemini, or Vertex AI (auto-detected)

For GenAI, send Gemini-style requests to /genai_passthrough as usual. To route a request through Vertex AI instead, configure your client for Vertex (vertexai=True) - DeepintShield routes to Vertex automatically when the request uses a Vertex-style path (/projects/{PROJECT_ID}/locations/{LOCATION}/), a Vertex model resource path, or a Vertex OAuth token (Bearer ya29...). See the Vertex-style example below.

---

Usage Examples

OpenAI Passthrough

DeepintShield SDK

from deepintshield import DeepintShield

shield = DeepintShield(virtual_key="sk-bf-your-virtual-key")
client = shield.openai(passthrough=True)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "hello from passthrough"}],
)

print(response.choices[0].message.content)

Native SDK

import openai

client = openai.OpenAI(
    base_url="https://app.deepintshield.com/openai_passthrough/v1",
    api_key="sk-bf-your-virtual-key",
    default_headers={"x-bf-vk": "sk-bf-your-virtual-key"},
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "hello from passthrough"}],
)

print(response.choices[0].message.content)

cURL

curl -X POST "https://app.deepintshield.com/openai_passthrough/v1/chat/completions" \
  -H "content-type: application/json" \
  -H "authorization: Bearer sk-your-openai-key" \
  -H "x-bf-vk: sk-bf-your-virtual-key" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role":"user","content":"hello from passthrough"}]
  }'

Anthropic Passthrough

DeepintShield SDK

from deepintshield import DeepintShield

shield = DeepintShield(virtual_key="sk-bf-your-virtual-key")
client = shield.anthropic(passthrough=True)

response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "hello from passthrough"}],
)

print(response.content[0].text)

Native SDK

import anthropic

client = anthropic.Anthropic(
    base_url="https://app.deepintshield.com/anthropic_passthrough",
    api_key="sk-bf-your-virtual-key",
    default_headers={"x-bf-vk": "sk-bf-your-virtual-key"},
)

response = client.messages.create(
    model="claude-sonnet-4-20250514",
    max_tokens=1024,
    messages=[{"role": "user", "content": "hello from passthrough"}],
)

print(response.content[0].text)

cURL

curl -X POST "https://app.deepintshield.com/anthropic_passthrough/v1/messages" \
  -H "content-type: application/json" \
  -H "x-api-key: your-anthropic-key" \
  -H "anthropic-version: 2023-06-01" \
  -H "x-bf-vk: sk-bf-your-virtual-key" \
  -d '{
    "model": "claude-sonnet-4-20250514",
    "max_tokens": 1024,
    "messages": [{"role":"user","content":"hello from passthrough"}]
  }'

GenAI Passthrough (Gemini)

DeepintShield SDK

from deepintshield import DeepintShield

shield = DeepintShield(virtual_key="sk-bf-your-virtual-key")
client = shield.genai(passthrough=True)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="hello from passthrough",
)

print(response.text)

Native SDK

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(
    api_key="sk-bf-your-virtual-key",
    http_options=HttpOptions(
        base_url="https://app.deepintshield.com/genai_passthrough",
        headers={"x-bf-vk": "sk-bf-your-virtual-key"},
    ),
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="hello from passthrough",
)

print(response.text)

cURL

curl -X POST "https://app.deepintshield.com/genai_passthrough/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "content-type: application/json" \
  -H "x-goog-api-key: your-gemini-key" \
  -H "x-bf-vk: sk-bf-your-virtual-key" \
  -d '{
    "contents":[{"parts":[{"text":"hello from passthrough"}]}]
  }'

GenAI Passthrough (Vertex-style request)

Python SDK

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(
    vertexai=True,
    api_key="sk-bf-your-virtual-key",
    http_options=HttpOptions(
        base_url="https://app.deepintshield.com/genai_passthrough",
        headers={"x-bf-vk": "sk-bf-your-virtual-key"},
    ),
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="hello from vertex passthrough"
)

print(response.text)

cURL

curl -X POST "https://app.deepintshield.com/genai_passthrough/v1/projects/my-project/locations/us-central1/publishers/google/models/gemini-2.5-flash:generateContent" \
  -H "content-type: application/json" \
  -H "authorization: Bearer ya29.your-vertex-token" \
  -H "x-bf-vk: sk-bf-your-virtual-key" \
  -d '{
    "contents":[{"parts":[{"text":"hello from vertex passthrough"}]}]
  }'

---

Notes

• Add your virtual key with the x-bf-vk header (or pass it as the api_key when using the DeepintShield SDK) so the request is attributed for governance, logging, and observability.
• The provider’s native authentication header (for example authorization, x-api-key, or x-goog-api-key) is forwarded to the provider unchanged.