> For a complete documentation index, fetch https://docs.voximplant.ai/llms.txt # OpenAI API compatibility In addition to its many native Voice AI clients, Voximplant supports many additional OpenAI-compatible LLM models and deployment options through its **Bring your own LLM** interface. Use the *Bring your own LLM capability* when: * You need a specific model not offered via Voximplant's existing Voice AI clients - dozens of models are provided across several vendors with a growing list. * You need hosting of supported models on specific cloud endpoints for data sovereignty, compliance, or cost savings - control how and where models are deployed. * You plan to switch between supported providers and want to keep a consistent interface - avoid building custom interfaces for each provider. * Easy addition of text-based LLM support - use text-based LLMs to supplement functionality. The Bring your own LLM capability does have some limitations. Note these caveats: * Realtime API support is limited to only a few LLM providers * Most model support is via text-based LLMs that require implementing a [cascaded pipeline](/voice-ai-orchestration/pipeline-options#full-cascade) for Voice AI support. * While the core API interface is the same, event usage, parameters, and payloads may vary by provider. We recommend using one of Voximplant's direct speech-to-speech Voice AI clients when they are available. The existing Voice AI connectors usually provide a simpler implementation when the provider's built-in voice, language, and agent behavior meet your requirements. Voximplant's [HTTP requests API](/platform/voxengine/api-requests), [webhooks interface](/platform/management-api/callbacks), and [WebSocket module](/api-reference/voxengine/voxengine#createwebsocket) can be used to interface with unsupported LLM platforms. ## Supported API options Bring your own LLM is supported across all of OpenAI's LLM API options. | API option | Best for | VoxEngine client | | ---------------- | -------------------------------------------------------------------------------------- | ----------------------------------------- | | Chat Completions | Existing chat bot logic, simple streaming text generation, manual conversation history | `OpenAI.createChatCompletionsAPIClient()` | | Responses API | Newer agentic workflows, tool use, structured items, longer-running voice flows | `OpenAI.createResponsesAPIClient()` | | Realtime API | Direct speech-to-speech sessions where the model handles audio input and audio output | `OpenAI.createRealtimeAPIClient()` | Third-party OpenAI compatibility varies considerably by vendor. Always check the provider's supported endpoints, events, models, and streaming behavior. ## Using OpenAI-compatible interfaces For Chat Completions and Responses, the main integration requirement is specifying the provider's OpenAI-compatible API root as `baseUrl` and providing an API key from that provider. `OpenAI.createChatCompletionsAPIClient()`, `OpenAI.createResponsesAPIClient()`, and `OpenAI.createRealtimeAPIClient()` all accept `apiKey` and optional `baseUrl` parameters. You can securely store provider keys in [Voximplant Secrets](/platform/voxengine/secrets) and retrieve them in VoxEngine with `VoxEngine.getSecretValue()`. ## Reference examples | API option | Scenario | Example Description | | ---------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------- | | Chat Completions | [Chat Completions with Together AI](/voice-ai-orchestration/bring-your-own-llm/chat-completions-together) | Together AI through `https://api.together.ai/v1` | | Responses API | [Responses: Deepgram-Groq-Inworld](/voice-ai-orchestration/bring-your-own-llm/full-cascade-groq) | Deepgram STT, Groq Responses API, and Inworld TTS | | Realtime API | [Realtime: Azure OpenAI](/voice-ai-orchestration/bring-your-own-llm/azure-openai-realtime) | Azure OpenAI Realtime deployment | ## Provider options Provider support changes quickly. Treat this table as implementation guidance, then verify the provider's current API docs before production use. | Provider | Completions | Responses API | Realtime | Example base URL | | ----------------------------------- | --------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------- | ---------------------------------------------------------- | | xAI / Grok | [Yes](https://docs.x.ai/developers/rest-api-reference/inference/chat) | [Yes](https://docs.x.ai/developers/model-capabilities/text/generate-text) | [OpenAI Realtime-compatible](https://docs.x.ai/developers/model-capabilities/audio/voice-agent) | `https://api.x.ai/v1` | | Groq | [Yes](https://console.groq.com/docs/openai) | [Yes, beta](https://console.groq.com/docs/responses-api) | [Not documented](https://console.groq.com/docs/api-reference) | `https://api.groq.com/openai/v1` | | Fireworks | [Yes](https://docs.fireworks.ai/tools-sdks/openai-compatibility) | [Yes](https://docs.fireworks.ai/guides/response-api) | [Not documented](https://docs.fireworks.ai/tools-sdks/openai-compatibility) | `https://api.fireworks.ai/inference/v1` | | SambaNova | [Yes](https://docs.sambanova.ai/docs/en/features/openai-compatibility) | [Yes](https://docs.sambanova.ai/docs/en/features/responses) | [Not documented](https://docs.sambanova.ai/docs/en/features/openai-compatibility) | `https://api.sambanova.ai/v1` | | Google Gemini | [Yes](https://ai.google.dev/gemini-api/docs/openai) | [Not documented](https://ai.google.dev/gemini-api/docs/openai) | [Native Live API](https://ai.google.dev/gemini-api/docs/live-api) | `https://generativelanguage.googleapis.com/v1beta/openai/` | | Anthropic Claude | [Limited](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk) | [Not documented](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk) | [No audio support](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/openai-sdk) | `https://api.anthropic.com/v1/` | | Together AI | [Yes](https://docs.together.ai/docs/inference/openai-compatibility) | [Not documented](https://docs.together.ai/docs/inference/openai-compatibility) | [Speech APIs only](https://docs.together.ai/reference/audio-transcriptions-realtime) | `https://api.together.ai/v1` | | DeepSeek | [Yes](https://api-docs.deepseek.com/) | [Not documented](https://api-docs.deepseek.com/) | [Not documented](https://api-docs.deepseek.com/) | `https://api.deepseek.com` | | Mistral | [Yes](https://docs.mistral.ai/resources/migration-guides) | [Not documented](https://docs.mistral.ai/resources/migration-guides) | [Not documented](https://docs.mistral.ai/resources/migration-guides) | `https://api.mistral.ai/v1` | | Cerebras | [Limited](https://inference-docs.cerebras.ai/resources/openai) | [Not documented](https://inference-docs.cerebras.ai/resources/openai) | [Not documented](https://inference-docs.cerebras.ai/resources/openai) | `https://api.cerebras.ai/v1` | | Kimi / Moonshot | [Yes](https://platform.kimi.ai/docs/api/overview) | [Not documented](https://platform.kimi.ai/docs/api/overview) | [Not documented](https://platform.kimi.ai/docs/api/overview) | `https://api.moonshot.ai/v1` | | Qwen / Alibaba Cloud Model Studio | [Yes](https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions) | [Yes](https://www.alibabacloud.com/help/en/model-studio/compatibility-with-openai-responses-api) | [Qwen-Omni-Realtime](https://www.alibabacloud.com/help/en/model-studio/realtime) | Region-specific compatible-mode URLs | | Azure OpenAI / Microsoft Foundry v1 | [Yes](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt) | [Yes](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses) | [GPT Realtime](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio) | `https://.openai.azure.com/openai/v1/` | Provider examples can change. Confirm the current base URL, supported models, request fields, streaming behavior, and tool support in the provider's documentation before production use. Some third-party voice providers advertise OpenAI compatibility, but may use different event names, unsupported events, or different audio behavior. When Voximplant has a dedicated connector for a realtime provider, prefer that connector for production. ## Choosing Chat Completions vs Responses vs Realtime | Requirement | Recommended option | | -------------------------------------------------------------- | ----------------------------------------------------------------------------------------- | | Use the broadest set of OpenAI-compatible LLM providers | Chat Completions | | Reuse an existing text chatbot prompt and message history | Chat Completions | | Use newer OpenAI-style agent workflows | Responses API | | Use built-in tools, structured response items, or response IDs | Responses API, if the provider supports those features | | Build a direct OpenAI speech-to-speech voice agent | Realtime API | | Use a third-party realtime speech provider | Use the dedicated [Voximplant connector](/voice-ai-orchestration/overview) when available | | Mix independent STT, LLM, and TTS providers | Chat Completions or Responses inside a full cascade | ## Compatibility checklist Before using a third-party provider in production, verify: * The correct `baseUrl`. * The provider supports the API shape you are using: Chat Completions, Responses, or Realtime. * The selected model supports streaming. * The selected model supports your message format, role names, tools, and structured output settings. * Whether the provider supports stored context, `previous_response_id`, or requires you to resend conversation history. * The provider's timeout, rate limit, and maximum context behavior. * The provider's data retention, logging, and compliance terms. * Audio behavior if using a realtime speech API. ## Related guides * [Pipeline Options](/voice-ai-orchestration/pipeline-options) * [OpenAI overview](/voice-ai-orchestration/openai/overview) * [Responses: Deepgram-Groq-Inworld](/voice-ai-orchestration/bring-your-own-llm/full-cascade-groq) * [Run TTS in VoxEngine](/getting-started/enhance-and-deploy/telephony-and-voice-ai#run-tts-in-voxengine)