> ## Documentation Index
> Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction to AI Gateway

> TrueFoundry AI Gateway: A unified interface for accessing 1000+ LLMs with enterprise-grade security, observability, and governance

TrueFoundry AI Gateway is the proxy layer that sits between your applications and the LLM providers and MCP Servers. It is an enterprise-grade platform that enables users to access 1000+ LLMs using a unified interface while taking care of observability and governance.

<img src="https://mintcdn.com/truefoundry/yOHcIuJN9I1uqUfe/images/new-ai-copy.png?fit=max&auto=format&n=yOHcIuJN9I1uqUfe&q=85&s=60d0d6629a9d197ac25041b8f708a80b" alt="TrueFoundry AI Gateway architecture diagram showing the gateway as a proxy between applications and multiple LLM providers" width="2518" height="1468" data-path="images/new-ai-copy.png" />

## Key Features

<CardGroup cols={3}>
  <Card title="Unified API for 1000+ LLMs" icon="plug" href="/docs/ai-gateway/chat-completions-overview">
    One endpoint with an OpenAI-compatible schema for every provider.
  </Card>

  <Card title="Multimodal & Audio APIs" icon="photo-film" href="/docs/ai-gateway/intro-to-llm-gateway#supported-apis">
    Chat, embeddings, images, audio, rerank, and realtime APIs.
  </Card>

  <Card title="Native SDK Compatibility" icon="code" href="/docs/ai-gateway/native-sdk-support">
    Drop-in support for OpenAI, Anthropic, and other provider SDKs.
  </Card>

  <Card title="Load Balancing & Fallbacks" icon="scale-balanced" href="/docs/ai-gateway/virtual-model">
    Route across models by weight, latency, or priority with automatic retries.
  </Card>

  <Card title="Semantic Caching" icon="bolt" href="/docs/ai-gateway/caching">
    Cut cost and latency on repeat requests.
  </Card>

  <Card title="Batch APIs" icon="layer-group" href="/docs/ai-gateway/batch-predictions-with-truefoundry-llm-gateway">
    Run large workloads asynchronously at batch pricing.
  </Card>

  <Card title="Access Control & API Keys" icon="lock" href="/docs/ai-gateway/gateway-access-control">
    RBAC and scoped keys for users, teams, and applications.
  </Card>

  <Card title="Rate Limiting" icon="gauge-high" href="/docs/ai-gateway/ratelimiting">
    Per-user, per-model, and per-application throttles.
  </Card>

  <Card title="Budgets & Cost Tracking" icon="wallet" href="/docs/ai-gateway/budgetlimiting">
    Enforce spend limits and attribute cost across teams.
  </Card>

  <Card title="Guardrails" icon="shield" href="/docs/ai-gateway/guardrails-overview">
    PII, prompt injection, content moderation, and custom policies.
  </Card>

  <Card title="Observability & Logs" icon="chart-line" href="/docs/ai-gateway/analytics">
    OpenTelemetry-compliant metrics, traces, and request logs.
  </Card>

  <Card title="Prompt Management" icon="message" href="/docs/ai-gateway/prompt-management">
    Versioned prompts with a built-in playground.
  </Card>

  <Card title="MCP Registry" icon="server" href="/docs/ai-gateway/mcp/mcp-server-getting-started">
    Host, publish, and discover MCP servers in one place.
  </Card>

  <Card title="Centralized MCP Auth" icon="key" href="/docs/ai-gateway/mcp/mcp-gateway-auth-security">
    One API key to reach every MCP server and tool.
  </Card>

  <Card title="Virtual MCP Servers" icon="diagram-project" href="/docs/ai-gateway/mcp/virtual-mcp-server">
    Combine tools from multiple MCP servers into one.
  </Card>

  <Card title="Agent Registry" icon="robot" href="/docs/agent-platform/agent-registry/agent-registry">
    Build, publish, and share AI agents natively on TrueFoundry.
  </Card>

  <Card title="Skills Registry" icon="screwdriver-wrench" href="/docs/ai-gateway/skills/skills-registry">
    Versioned, reusable `SKILL.md` instructions for agents and IDEs.
  </Card>

  <Card title="Flexible Deployment" icon="cloud" href="/docs/ai-gateway/modes-of-deployment">
    SaaS, hybrid, or fully self-hosted in your own VPC.
  </Card>
</CardGroup>

## Supported Model Providers

We integrate with 1000+ LLMs through the following providers.

<Tip>
  If you don't see the provider you need, there is a high change it will just work as self hosted models or OpenAI provider. Please reach out to us at [support@truefoundry.com](mailto:support@truefoundry.com) and we will be happy to guide you.
</Tip>

<CardGroup cols={4}>
  <Card className="!py-2 !px-3" href="/docs/ai-gateway/google-vertex">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/FrY4JbiyZud2He3p/images/0530d732-852cf2ae041019e3322649a2731ef87fe038bb09ce2271e7114f4fb2ed9da415-file.png?fit=max&auto=format&n=FrY4JbiyZud2He3p&q=85&s=99bf56cda35ee8fe027ec9ccbef71a6f" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/0530d732-852cf2ae041019e3322649a2731ef87fe038bb09ce2271e7114f4fb2ed9da415-file.png" />

      <span className="text-sm font-semibold leading-tight">
        Gemini & Vertex AI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/google-gemini">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/gonlEy8fl_2fR_5Y/images/icons/gemini-logo.png?fit=max&auto=format&n=gonlEy8fl_2fR_5Y&q=85&s=21e5ae33d0b2b3ef879b326fd2bdff65" alt="Google Gemini logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/icons/gemini-logo.png" />

      <span className="text-sm font-semibold leading-tight">
        Google Gemini
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/aws-bedrock">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/yRoKH_fkKi2nPtuV/images/fa5bae4c-3d9a209788691caf01ac023fd388edcb5eb0bebddc7a6cbcfdfe5749d7167efa-file_1.png?fit=max&auto=format&n=yRoKH_fkKi2nPtuV&q=85&s=a4bee47a494a35f975d194c421b3a183" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/fa5bae4c-3d9a209788691caf01ac023fd388edcb5eb0bebddc7a6cbcfdfe5749d7167efa-file_1.png" />

      <span className="text-sm font-semibold leading-tight">
        AWS Bedrock
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/aws-sagemaker">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/aws-sagemaker.svg" alt="AWS SageMaker logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        AWS SageMaker
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/azure-openai">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/DdP_2rhue4AQQlob/images/4ba5199c-3e375f637423c83621df291e00c7fcd27ed05a0d3a5b90794e6a85d4702662a1-file_3.jpg?fit=max&auto=format&n=DdP_2rhue4AQQlob&q=85&s=4b0067ff5ecf8cf568e4c551fc602fbb" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/4ba5199c-3e375f637423c83621df291e00c7fcd27ed05a0d3a5b90794e6a85d4702662a1-file_3.jpg" />

      <span className="text-sm font-semibold leading-tight">
        Azure OpenAI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/azure-ai-foundry">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/DdP_2rhue4AQQlob/images/4ba5199c-3e375f637423c83621df291e00c7fcd27ed05a0d3a5b90794e6a85d4702662a1-file_3.jpg?fit=max&auto=format&n=DdP_2rhue4AQQlob&q=85&s=4b0067ff5ecf8cf568e4c551fc602fbb" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/4ba5199c-3e375f637423c83621df291e00c7fcd27ed05a0d3a5b90794e6a85d4702662a1-file_3.jpg" />

      <span className="text-sm font-semibold leading-tight">
        Azure AI Foundry
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/openai">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/yRoKH_fkKi2nPtuV/images/f863f110-89598b0f5a65b24a53d4e81077408fb7201ec861bfd2aace4665afc6a7e46d24-file_14.png?fit=max&auto=format&n=yRoKH_fkKi2nPtuV&q=85&s=8a9a714cb2c486f252e95948b5a5e5fb" alt="OpenAI logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/f863f110-89598b0f5a65b24a53d4e81077408fb7201ec861bfd2aace4665afc6a7e46d24-file_14.png" />

      <span className="text-sm font-semibold leading-tight">
        OpenAI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/cohere">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/s4Aj2_qGCrSP-zc8/images/889ac4a7-fe5113cbdecff51ea30fd7a2f9de3dabc76a656274bdb5cf789bb0829dc1226f-file_2.png?fit=max&auto=format&n=s4Aj2_qGCrSP-zc8&q=85&s=c16d6313f920d64c5c46be5db297a299" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/889ac4a7-fe5113cbdecff51ea30fd7a2f9de3dabc76a656274bdb5cf789bb0829dc1226f-file_2.png" />

      <span className="text-sm font-semibold leading-tight">
        Cohere
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/databricks-models">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/_wMKf6ALFfIRnUSQ/images/databricks.svg?fit=max&auto=format&n=_wMKf6ALFfIRnUSQ&q=85&s=d1af0b862115159b3473e89df853c12d" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/databricks.svg" />

      <span className="text-sm font-semibold leading-tight">
        Databricks
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/ai21">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/DdP_2rhue4AQQlob/images/47429280-27551f097d32d959f0c4c61a42ba6bf529ce637f85658742edce85f0d5347d29-file_5.png?fit=max&auto=format&n=DdP_2rhue4AQQlob&q=85&s=7dec74b7b9d9eb403afb2dff8c795514" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/47429280-27551f097d32d959f0c4c61a42ba6bf529ce637f85658742edce85f0d5347d29-file_5.png" />

      <span className="text-sm font-semibold leading-tight">
        AI21
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/anthropic">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/4MAaF__cLD4iud16/images/5f73a51c-d876ed2262e9a83e2e08daaf7386c2d47fca02d2ac74d15166d5163c0f8cf386-file_6.png?fit=max&auto=format&n=4MAaF__cLD4iud16&q=85&s=455f52ce6f6237e43faa06531790cad5" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/5f73a51c-d876ed2262e9a83e2e08daaf7386c2d47fca02d2ac74d15166d5163c0f8cf386-file_6.png" />

      <span className="text-sm font-semibold leading-tight">
        Anthropic
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/together-ai">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/OHzlp6GY5G-JfKle/images/d3067631-a4374539855336dc486639bd82d7440b841c19f537d15e65e0195d5ab4c912a4-file_13.png?fit=max&auto=format&n=OHzlp6GY5G-JfKle&q=85&s=394b88f2bb9609d8f75dceee3251f961" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/d3067631-a4374539855336dc486639bd82d7440b841c19f537d15e65e0195d5ab4c912a4-file_13.png" />

      <span className="text-sm font-semibold leading-tight">
        Together AI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/xai">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/1XZGPKeV4QNYX7dI/images/xai.png?fit=max&auto=format&n=1XZGPKeV4QNYX7dI&q=85&s=36c5e1282975cd58476a589d54c23c0c" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/xai.png" />

      <span className="text-sm font-semibold leading-tight">
        xAI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/deepinfra">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/4MAaF__cLD4iud16/images/59c01ead-636bf9baad4503876e179f1047874d50dccb083a8c4e8c385e76d7c360c2f1e6-file_3.png?fit=max&auto=format&n=4MAaF__cLD4iud16&q=85&s=03ceff9e1d841caf2e9b12b00630c437" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/59c01ead-636bf9baad4503876e179f1047874d50dccb083a8c4e8c385e76d7c360c2f1e6-file_3.png" />

      <span className="text-sm font-semibold leading-tight">
        DeepInfra
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/perplexity-ai">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/s4Aj2_qGCrSP-zc8/images/8d4ef381-9e235c1c05e84fed849a0c378f60c9a9ed408d950c2c4fd016ca74c4b7ef2fd1-file_12.png?fit=max&auto=format&n=s4Aj2_qGCrSP-zc8&q=85&s=87f18eb81cd7bc56f9b1be95ca6f5d88" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/8d4ef381-9e235c1c05e84fed849a0c378f60c9a9ed408d950c2c4fd016ca74c4b7ef2fd1-file_12.png" />

      <span className="text-sm font-semibold leading-tight">
        Perplexity AI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/mistral">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/4MAaF__cLD4iud16/images/504a8e0a-2f6ad398a7cae8352f0ac97224304abfb07789c9405369e68f07494a259d6340-file_7.png?fit=max&auto=format&n=4MAaF__cLD4iud16&q=85&s=e61c0c8a7b762af5f5b90d416148a884" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/504a8e0a-2f6ad398a7cae8352f0ac97224304abfb07789c9405369e68f07494a259d6340-file_7.png" />

      <span className="text-sm font-semibold leading-tight">
        Mistral AI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/cloudera">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/cloudera.svg" alt="Cloudera logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        Cloudera
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/groq">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/FrY4JbiyZud2He3p/images/115edf07-91692a7eb9b4b5670fd7bb682b0870a098663889cafa4475df06496d3f8073ac-file_4.png?fit=max&auto=format&n=FrY4JbiyZud2He3p&q=85&s=58e9a3c2e65e5784c396e18b0afcc464" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/115edf07-91692a7eb9b4b5670fd7bb682b0870a098663889cafa4475df06496d3f8073ac-file_4.png" />

      <span className="text-sm font-semibold leading-tight">
        Groq
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/elevenlabs">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/elevenlabs.svg" alt="ElevenLabs logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        ElevenLabs
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/deepgram">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/deepgram.svg" alt="Deepgram logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        Deepgram
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/cartesia">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/cartesia.svg" alt="Cartesia logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        Cartesia
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/smallest-ai">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/smallest-ai.svg" alt="Smallest AI logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        Smallest AI
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/snowflake-cortex">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/snowflake-cortex.svg" alt="Snowflake Cortex logo" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        Snowflake Cortex
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/self-hosted-models">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/6bbtTt95c1iCcyph/favicon.svg?fit=max&auto=format&n=6bbtTt95c1iCcyph&q=85&s=f55bde34214b38034126d05b08ea16c7" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="favicon.svg" />

      <span className="text-sm font-semibold leading-tight">
        Self Hosted
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/openrouter">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://assets.production.truefoundry.com/openrouter.svg" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} />

      <span className="text-sm font-semibold leading-tight">
        OpenRouter
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/sambanova">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/6SYERHht8PcdzWk0/images/SambaNova%20Favicon.webp?fit=max&auto=format&n=6SYERHht8PcdzWk0&q=85&s=36fffc3387a8312ea9958e206b2a7e48" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/SambaNova Favicon.webp" />

      <span className="text-sm font-semibold leading-tight">
        SambaNova
      </span>
    </div>
  </Card>

  <Card className="!py-2 !px-3" href="/docs/ai-gateway/cerebras">
    <div className="flex items-center gap-1.5 w-full">
      <img src="https://mintcdn.com/truefoundry/qsnIjfIPg_BZ5d3X/images/cerebras-logo.jpeg?fit=max&auto=format&n=qsnIjfIPg_BZ5d3X&q=85&s=07d0b1589ba23c45c06695ca98319176" width="24" height="24" style={{ maxWidth:"24px",maxHeight:"24px",objectFit:"contain" }} data-path="images/cerebras-logo.jpeg" />

      <span className="text-sm font-semibold leading-tight">
        Cerebras
      </span>
    </div>
  </Card>
</CardGroup>

## Supported APIs

The following accordions summarize provider support for each gateway endpoint. Each section links to the full guide for that API (same order as **Supported APIs** in the sidebar).

<Info>
  Legend:

  * **✅** Supported by Provider and Truefoundry
  * <Icon icon="circle-xmark" iconType="regular" color="red" /> Provided by provider, but not by Truefoundry
  * <Icon icon="circle-minus" iconType="regular" /> Provider does not support this feature
</Info>

<AccordionGroup>
  <Accordion title="Chat Completion (/chat/completions)" defaultOpen="true">
    **Documentation:** [Chat Completions API](/docs/ai-gateway/chat-completions-overview) · [API Reference](/docs/api-reference/chat/chat-completions)

    | Provider      | Stream | Non Stream | Tools                                           | JSON Mode                                       | Schema Mode                                     | Prompt Caching                                  | Reasoning                                       | Structured Output                               |
    | ------------- | ------ | ---------- | ----------------------------------------------- | ----------------------------------------------- | ----------------------------------------------- | ----------------------------------------------- | ----------------------------------------------- | ----------------------------------------------- |
    | OpenAI        | ✅      | ✅          | ✅                                               | ✅                                               | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Azure OpenAI  | ✅      | ✅          | ✅                                               | ✅                                               | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Anthropic     | ✅      | ✅          | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Bedrock       | ✅      | ✅          | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Vertex        | ✅      | ✅          | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Cohere        | ✅      | ✅          | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Gemini        | ✅      | ✅          | ✅                                               | ✅                                               | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Groq          | ✅      | ✅          | ✅                                               | ✅                                               | ✅                                               | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | AI21          | ✅      | ✅          | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> |
    | Cerebras      | ✅      | ✅          | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Wafer         | ✅      | ✅          | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> |
    | SambaNova     | ✅      | ✅          | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
    | Perplexity-AI | ✅      | ✅          | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | ✅                                               |
    | Together-AI   | ✅      | ✅          | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | ✅                                               | ✅                                               |
    | xAI           | ✅      | ✅          | ✅                                               | ✅                                               | ✅                                               | ✅                                               | ✅                                               | ✅                                               |
    | DeepInfra     | ✅      | ✅          | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> | ✅                                               | ✅                                               | <Icon icon="circle-minus" iconType="regular" /> |
  </Accordion>

  <Accordion title="Embedding (/embeddings)">
    **Documentation:** [Embeddings API](/docs/ai-gateway/embed) · [API Reference](/docs/api-reference/embeddings/generate-embeddings)

    | Provider     | String                                                      | List of String                                              |
    | ------------ | ----------------------------------------------------------- | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           | ✅                                                           |
    | Azure OpenAI | ✅                                                           | ✅                                                           |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock      | ✅                                                           | ✅                                                           |
    | Vertex       | ✅                                                           | ✅                                                           |
    | Cohere       | ✅                                                           | ✅                                                           |
    | Gemini       | <Icon icon="circle-minus" iconType="regular" />             | <Icon icon="circle-minus" iconType="regular" />             |
    | Groq         | <Icon icon="circle-minus" iconType="regular" />             | <Icon icon="circle-minus" iconType="regular" />             |
    | SambaNova    | <Icon icon="circle-xmark" iconType="regular" color="red" /> | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Together-AI  | ✅                                                           | ✅                                                           |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Batch (/batches)">
    **Documentation:** [Batch API](/docs/ai-gateway/batch-predictions-with-truefoundry-llm-gateway) · [API Reference](/docs/api-reference/batch/create-batch)

    | Provider     | Batch                                                       |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | ✅                                                           |
    | Anthropic    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Bedrock      | ✅                                                           |
    | Vertex       | ✅                                                           |
    | Cohere       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Gemini       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Groq         | <Icon icon="circle-minus" iconType="regular" />             |
    | Cerebras     | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Fine Tune">
    **Documentation:** [Finetune API](/docs/ai-gateway/finetune) · [API Reference](/docs/api-reference/fine-tuning/create-fine-tuning-job)

    | Provider     | Fine Tune                                                   |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | <Icon icon="circle-minus" iconType="regular" />             |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock      | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Vertex       | ✅                                                           |
    | Cohere       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Gemini       | <Icon icon="circle-minus" iconType="regular" />             |
    | Groq         | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Cerebras     | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Model Response (/responses)">
    **Documentation:** [Responses API](/docs/ai-gateway/responses-api) · [API Reference](/docs/api-reference/responses/model-responses)

    | Provider     | Model Response                                              |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | ✅                                                           |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock      | <Icon icon="circle-minus" iconType="regular" />             |
    | Vertex       | <Icon icon="circle-minus" iconType="regular" />             |
    | Cohere       | <Icon icon="circle-minus" iconType="regular" />             |
    | Gemini       | <Icon icon="circle-minus" iconType="regular" />             |
    | Groq         | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Cerebras     | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-minus" iconType="regular" />             |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-minus" iconType="regular" />             |
  </Accordion>

  <Accordion title="Image Generation (/images/generations)">
    **Documentation:** [Image Generation API](/docs/ai-gateway/image-generation) · [API Reference](/docs/api-reference/image/generate-images)

    | Provider     | Generate                                                    |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | ✅                                                           |
    | Bedrock      | ✅                                                           |
    | Vertex       | ✅                                                           |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             |
    | Cohere       | <Icon icon="circle-minus" iconType="regular" />             |
    | Gemini       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Groq         | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Image Edit (/images/edits)">
    **Documentation:** [Image Edit API](/docs/ai-gateway/image-edit) · [API Reference](/docs/api-reference/image/edit-images)

    | Provider     | Edit                                                        |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | ✅                                                           |
    | Bedrock      | ✅                                                           |
    | Vertex       | ✅                                                           |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             |
    | Cohere       | <Icon icon="circle-minus" iconType="regular" />             |
    | Gemini       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Groq         | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Image Variation (/images/variations)">
    **Documentation:** [Image Variation API](/docs/ai-gateway/image-variation) · [API Reference](/docs/api-reference/image/create-image-variation)

    | Provider     | Variation                                                   |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock      | ✅                                                           |
    | Vertex       | <Icon icon="circle-minus" iconType="regular" />             |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             |
    | Cohere       | <Icon icon="circle-minus" iconType="regular" />             |
    | Gemini       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Groq         | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Text To Speech">
    **Documentation:** [Text to Speech API](/docs/ai-gateway/text-to-speech) · [API Reference](/docs/api-reference/audio/generate-speech)

    | Provider         | Text To Speech                                              |
    | ---------------- | ----------------------------------------------------------- |
    | OpenAI           | ✅                                                           |
    | Azure OpenAI     | ✅                                                           |
    | Azure AI Foundry | ✅                                                           |
    | Anthropic        | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock          | <Icon icon="circle-minus" iconType="regular" />             |
    | Vertex           | ✅                                                           |
    | Cohere           | <Icon icon="circle-minus" iconType="regular" />             |
    | Gemini           | ✅                                                           |
    | Groq             | ✅                                                           |
    | Together-AI      | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI              | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra        | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | DeepGram         | ✅                                                           |
    | Cartesia         | ✅                                                           |
    | ElevenLabs       | ✅                                                           |
    | Resemble AI      | ✅                                                           |
    | Smallest AI      | ✅                                                           |
  </Accordion>

  <Accordion title="Audio Translation">
    **Documentation:** [Audio Translation API](/docs/ai-gateway/audio-translation) · [API Reference](/docs/api-reference/audio/translate-audio)

    | Provider         | Translation                                                 |
    | ---------------- | ----------------------------------------------------------- |
    | OpenAI           | ✅                                                           |
    | Azure OpenAI     | ✅                                                           |
    | Azure AI Foundry | ✅                                                           |
    | Anthropic        | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock          | <Icon icon="circle-minus" iconType="regular" />             |
    | Vertex           | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Cohere           | <Icon icon="circle-minus" iconType="regular" />             |
    | Gemini           | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Groq             | ✅                                                           |
    | Together-AI      | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI              | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra        | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Speech to Text">
    **Documentation:** [Speech to Text API](/docs/ai-gateway/audio-transcription) · [API Reference](/docs/api-reference/audio/transcribe-audio)

    | Provider         | Transcription                                               |
    | ---------------- | ----------------------------------------------------------- |
    | OpenAI           | ✅                                                           |
    | Azure OpenAI     | ✅                                                           |
    | Azure AI Foundry | ✅                                                           |
    | Anthropic        | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock          | <Icon icon="circle-minus" iconType="regular" />             |
    | Vertex           | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Cohere           | <Icon icon="circle-minus" iconType="regular" />             |
    | Gemini           | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Groq             | ✅                                                           |
    | Together-AI      | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI              | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra        | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | DeepGram         | ✅                                                           |
    | Cartesia         | ✅                                                           |
    | ElevenLabs       | ✅                                                           |
    | Smallest AI      | ✅                                                           |
  </Accordion>

  <Accordion title="Live / Realtime API">
    **Documentation:** [Live / Realtime API](/docs/ai-gateway/live-api)

    | Provider         | Live / Realtime API |
    | ---------------- | ------------------- |
    | Gemini           | ✅                   |
    | Vertex           | ✅                   |
    | OpenAI           | ✅                   |
    | Azure AI Foundry | ✅                   |
  </Accordion>

  <Accordion title="Files (/files)">
    **Documentation:** [Files API](/docs/ai-gateway/file-endpoints) · [API Reference](/docs/api-reference/files/upload-file)

    | Provider     | Files                                                       |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Anthropic    | ✅                                                           |
    | Bedrock      | ✅                                                           |
    | Vertex       | ✅                                                           |
    | Cohere       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Gemini       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Groq         | ✅                                                           |
    | Cerebras     | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Rerank (/rerank)">
    **Documentation:** [Rerank API](/docs/ai-gateway/rerank) · [API Reference](/docs/api-reference/rerank/rerank-documents)

    | Provider     | Rerank                                                      |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | <Icon icon="circle-minus" iconType="regular" />             |
    | Azure OpenAI | <Icon icon="circle-minus" iconType="regular" />             |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock      | ✅                                                           |
    | Vertex       | <Icon icon="circle-minus" iconType="regular" />             |
    | Cohere       | ✅                                                           |
    | Gemini       | <Icon icon="circle-minus" iconType="regular" />             |
    | Groq         | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Moderation (/moderations)">
    **Documentation:** [Moderation API](/docs/ai-gateway/moderation) · [API Reference](/docs/api-reference/moderations/create-moderation)

    | Provider     | Moderation                                                  |
    | ------------ | ----------------------------------------------------------- |
    | OpenAI       | ✅                                                           |
    | Azure OpenAI | <Icon icon="circle-minus" iconType="regular" />             |
    | Anthropic    | <Icon icon="circle-minus" iconType="regular" />             |
    | Bedrock      | <Icon icon="circle-minus" iconType="regular" />             |
    | Vertex       | <Icon icon="circle-minus" iconType="regular" />             |
    | Cohere       | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | Gemini       | <Icon icon="circle-minus" iconType="regular" />             |
    | Groq         | <Icon icon="circle-minus" iconType="regular" />             |
    | Cerebras     | <Icon icon="circle-minus" iconType="regular" />             |
    | Together-AI  | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
    | xAI          | <Icon icon="circle-minus" iconType="regular" />             |
    | DeepInfra    | <Icon icon="circle-xmark" iconType="regular" color="red" /> |
  </Accordion>

  <Accordion title="Compaction API">
    **Documentation:** [Compaction API](/docs/ai-gateway/compaction) · [API Reference](/docs/api-reference/responses/model-responses-compact)

    | Provider | Compaction API |
    | -------- | -------------- |
    | OpenAI   | ✅              |
  </Accordion>

  <Accordion title="Messages API">
    **Documentation:** [Messages API](/docs/ai-gateway/messages-overview) · [API Reference](/docs/api-reference/messages/messages)

    | Provider  | Messages API |
    | --------- | ------------ |
    | Anthropic | ✅            |
  </Accordion>

  <Accordion title="Proxy API (/proxy)">
    **Documentation:** [Proxy API](/docs/ai-gateway/proxy-api)

    Forward provider-native requests through the gateway while keeping logging, rate limiting, and budget controls. See the guide for setup, headers, and examples by provider.
  </Accordion>
</AccordionGroup>

## Deployment Options

You can run the AI Gateway as fully managed SaaS, keep LLM request–response data in your own object storage while Truefoundry operates the gateway, or host the gateway plane (and optionally more of the stack) in your cloud or on-prem for stricter data residency and control. Each option differs in who hosts infrastructure, where traffic flows, and pricing tier.

Read the full comparison—including a scenario table, diagrams, and operational notes—in [AI Gateway deployment options](/docs/ai-gateway/modes-of-deployment). For background on how the gateway fits the platform, see [gateway plane architecture](/docs/platform/gateway-plane-architecture). To start on managed SaaS, follow the [quick start](/docs/ai-gateway/quick-start).

## Frequently Asked Questions

<AccordionGroup>
  <Accordion title="What's the performance impact of using the gateway?">
    The latency overhead is minimal, typically less than 5ms. Our benchmarks show enterprise-grade performance that scales with your needs. Our SaaS offering is hosted in multiple regions across the world to ensure low latency and high availability. You can also deploy the gateway on-premise or on any cloud provider in your region which \
    is closer to your users.

    <Frame caption="AI Gateway on the edge, close to your applications for optimal performance">
      <img src="https://mintcdn.com/truefoundry/FrY4JbiyZud2He3p/images/081e6057-686a04943a81ee773a3a94dcddff05647776f82f7a2f32d4155d4df0f61f0032-image.png?fit=max&auto=format&n=FrY4JbiyZud2He3p&q=85&s=c96dc61ac031c4c4dae8edf115f6f0f4" alt="" width="2438" height="1544" data-path="images/081e6057-686a04943a81ee773a3a94dcddff05647776f82f7a2f32d4155d4df0f61f0032-image.png" />
    </Frame>
  </Accordion>

  <Accordion title="Can I deploy the gateway on-premise?">
    Yes, the AI Gateway supports on-premise deployments on any infrastructure or cloud provider, giving you complete control over your AI operations.
  </Accordion>

  <Accordion title="How do I integrate my self-hosted models?">
    You can easily integrate any OpenAI-compatible self-hosted model. Check our [self-hosted models guide](/docs/ai-gateway/self-hosted-models) for detailed instructions.
  </Accordion>

  <Accordion title="Can I use the gateway without the full MLOps platform?">
    Yes, The AI Gateway can be used as a standalone solution. You can use the full MLOps platform if you're using features like model deployment(traditional models and LLMs), model training, llm fine-tuning or training/data-processing workflows.
  </Accordion>
</AccordionGroup>
