Skip to content

Meet DeepintShield at Bengaluru Tech Summit 2026, 17 to 19 November, BIEC Hall 1, booth H1A106. Book 20 minutes

Start For Free

Integrations

DeepintShield integrations: connect the AI stack you already run

DeepintShield integrations connect one gateway to the model providers, agent frameworks, identity systems and monitoring tools you already use. Most need one change: point an existing client at a new base URL with a virtual key, or add the Python SDK. Every listing below links to its documentation page.

One control point, connected to everything

Traffic from your apps, agents and coding tools passes through one gateway. Policy, identity, logging and cost controls apply on the way through, at the stages shown in how the request path works.

Model providers

  • OpenAI
  • Anthropic
  • Azure
  • AWS Bedrock
  • Vertex AI
  • Google Gemini
  • Mistral
  • Cohere
  • Groq
  • DeepSeek
  • xAI
  • Ollama and vLLM
  • Custom OpenAI-compatible endpoints

Agent frameworks and SDKs

  • LangChain and LangGraph
  • OpenAI Agents SDK
  • LlamaIndex
  • AutoGen / AG2
  • PydanticAI
  • AWS Strands
  • Google ADK
  • LiteLLM
  • Temporal

Identity

  • Microsoft Entra ID
  • Okta
  • Google Workspace
  • Auth0
  • Keycloak
  • Any OIDC provider

One control point

Observability and export

  • OpenTelemetry
  • Prometheus
  • Grafana Cloud
  • Datadog
  • New Relic
  • Honeycomb
  • Langfuse
  • S3, GCS and Azure Blob
  • Snowflake, Redshift and BigQuery

Safety providers

  • AWS Bedrock Guardrails
  • Azure AI Content Safety
  • Google Model Armor
  • Your own webhook

Coding agents

  • Claude Code
  • Codex CLI
  • Gemini CLI
  • Cursor
  • Qwen Code
  • Opencode
  • Zed
  • Roo Code

Product names belong to their owners. A listing means a documented integration path, not a partnership.

29 built-in model providers behind one API

Pick a provider per request with a provider/model prefix, such as anthropic/claude-sonnet-4-5. All providers return responses in the OpenAI-compatible format, and provider credentials stay on the gateway. The AI Gateway adds weighted load balancing and fallbacks across them.

Custom providers add OpenAI-compatible or self-hosted endpoints, and passthrough routes send provider-native OpenAI, Anthropic or Gemini requests unchanged while governance and logging still apply.

  • Frontier labs, cloud AI platforms and inference hosts
  • Self-hosted runtimes: Ollama, vLLM and SGLang
  • Speech, image and video providers

All integrations

Filter by group to find your provider, framework, identity system or monitoring tool. Each card links to its documentation page, and the docs keep a full list of providers and frameworks.

Model providers

OpenAI

GPT chat, Responses, embeddings, images, audio, video, files and batch.

Model providers

Anthropic

Claude chat and Responses with thinking, prompt caching, files and batch.

Model providers

Azure OpenAI Service

OpenAI and Claude deployments on Azure via API key, Entra ID or Managed Identity.

Model providers

AWS Bedrock

Claude, Nova, Llama, Mistral, Cohere and Titan using your AWS credentials or IAM role.

Model providers

Amazon Bedrock Mantle

Bedrock's OpenAI-compatible endpoint: chat, Responses, embeddings and files.

Model providers

Vertex AI

Gemini and Claude on Google Cloud with service-account auth, Imagen and Veo.

Model providers

Google Gemini

Gemini chat, embeddings, Imagen images, Veo video, speech, files and batch.

Model providers

Mistral

Mistral chat, embeddings, transcription and document OCR.

Model providers

Cohere

Command chat, Embed embeddings and reranking.

Model providers

Groq

Groq-hosted models through Chat Completions and Responses.

Model providers

xAI

Grok chat, Responses, reasoning, vision and image generation.

Model providers

DeepSeek

DeepSeek chat, Responses and text completions with streaming.

Model providers

Perplexity

Sonar answers with built-in web search and citations; no tool calling.

Model providers

Cerebras

Cerebras-hosted models for chat, Responses and text completions.

Model providers

Fireworks AI

Fireworks-hosted models for chat, Responses, completions and embeddings.

Model providers

Nebius

Nebius-hosted models for chat, embeddings and image generation.

Model providers

Parasail

Parasail-hosted models for chat and Responses with tool calling.

Model providers

OpenRouter

Access 100+ models from multiple vendors through OpenRouter.

Model providers

Hugging Face

Hugging Face inference backends for chat, embeddings, speech and images.

Model providers

Replicate

Replicate models and deployments for text, images and video.

Model providers

Wafer

Wafer Serverless models with live pricing and per-model capability metadata.

Model providers

OpenCode Zen

OpenCode's pay-as-you-go gateway for chat and Responses.

Model providers

OpenCode Go

OpenCode's subscription gateway for chat and Responses.

Model providers

Ollama

Local or private Ollama models for chat, completions and embeddings.

Model providers

vLLM

Self-hosted vLLM servers: chat, embeddings, transcription and reranking.

Model providers

SGLang

Self-hosted SGLang servers for chat, completions and embeddings.

Model providers

ElevenLabs

Text-to-speech and transcription with timestamps and speaker diarization.

Model providers

Sarvam AI

Sarvam chat, streaming text-to-speech and speech-to-text models.

Model providers

Runway

Runway image generation, reference-image editing and video generation.

SDKs and clients

OpenAI SDK

Point the OpenAI client at DeepintShield to reach all 29 provider identities.

SDKs and clients

Anthropic SDK

Keep native Anthropic Messages code; change the base URL.

SDKs and clients

Google GenAI SDK

Use native Google GenAI clients against the /genai endpoint.

SDKs and clients

LiteLLM

Route LiteLLM completion calls through the gateway with one wrapper.

SDKs and clients

Passthrough

Send provider-native OpenAI, Anthropic, Gemini or Vertex requests unchanged.

Agent frameworks

PydanticAI

Native PydanticAI agents with gateway-routed models and governed tools.

Agent frameworks

OpenAI Agents SDK

Native model binder; the Agents SDK keeps its runner and tools.

Agent frameworks

LlamaIndex

Native binder for LlamaIndex LLMs and embedders.

Agent frameworks

AutoGen / AG2

Native binder supplies AutoGen model clients routed through the gateway.

Agent frameworks

AWS Strands

Native binder for Strands agent models.

Agent frameworks

Google ADK

Native binder for Google ADK agents with OpenAI-compatible routing.

Agent frameworks

Temporal

Call the gateway from Temporal activities; Temporal keeps workflow execution.

Identity

Microsoft Entra ID

Console SSO, role and team sync, SCIM, and Entra Agent ID for agents.

Identity

Okta

Console SSO over OIDC with roles from claims or group mappings.

Identity

Google Workspace

Console SSO over OIDC with JIT provisioning and domain restriction.

Identity

Auth0

Console SSO over OIDC and Auth0-issued identities for agents.

Identity

Generic OIDC

Any OIDC provider for console SSO and verified agent identity.

Observability

OpenTelemetry

Export traces and metrics over OTLP with GenAI conventions.

Observability

Prometheus

Scrape cost, cache and latency metrics from /metrics or a Push Gateway.

Observability

Log exports

Scheduled log exports to S3, GCS, Azure Blob, Snowflake, Redshift or BigQuery.

Observability

Durable webhooks

Signed, at-least-once delivery of control-plane events to your endpoints.

Cloud guardrails

AWS Bedrock Guardrails

Run AWS Bedrock Guardrails as a safety provider inside DeepintShield policies.

Cloud guardrails

Azure AI Content Safety

Run Azure AI Content Safety as a safety provider inside DeepintShield policies.

Cloud guardrails

Google Model Armor

Run Google Model Armor as a safety provider inside DeepintShield policies.

Most integrations are one line

Keep your client and change where it points. Callers authenticate with a DeepintShield virtual key, so provider keys never sit in application code. Compatibility is route-specific, so test the exact endpoints and SDK version your application uses.

  • MCP clients: the gateway’s /mcp endpoint with a virtual key
  • OpenTelemetry: OTLP over HTTP or gRPC
  • Python SDK 3.2.3 for Python 3.10 or newer
import openai

client = openai.OpenAI(
    base_url="https://app.deepintshield.com/openai",
    api_key="sk-ds-your-virtual-key"
)

Need an integration that is not listed? Tell us what you run and an engineer will check it with you.

Connect your stack with one base URL

Start free with 50,000 requests a month, or book a demo to see your own providers and frameworks behind one gateway.

Start For Free