> ## Documentation Index
> Fetch the complete documentation index at: https://docs.inworld.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Models
Inworld's platform provides access to a wide variety of state-of-the-art models. These models offer diverse capabilities, performance levels, price points, and deployment options, enabling users to select and customize models that best match their specific use cases and application needs.
## Overview of Model Offerings
This section provides some high-level context on Inworld's model offerings, and how they can be used in your application.
* **[TTS](#tts)**: Text-to-Speech models can be used to generate high-quality audio for your application, such as powering a character's voice.
* **[LLM](#llm)**: Large Language Models are powerful models that can intake inputs (typically text, but certain models may also support other modalities) and generate text outputs. These models can be used to determine in-game actions, power conversations, generate dynamic narratives, and more.
* **[Embeddings](#embeddings)**: Embeddings models convert text into high-dimensional vectors, which can be used to power intent detection, text similarity comparison, and retrieval-augmented generation (RAG).
## TTS
Inworld's Agent Runtime and API offer access to Inworld's family of state-of-the-art TTS models, optimized for different use cases, quality levels, and performance requirements.
### Our flagship, top-ranked model — the best quality plus steerability
* Natural language steering for more contextually aware speech
* Support for 200+ languages and locales
* Optimized for real-time use
* High quality instant voice cloning
* Enhanced timestamps with phonetic details and visemes
### Rich, expressive speech with maximum stability
* Support for 15 languages
* Optimized for real-time use (\<200ms median latency)
* High quality instant voice cloning
### Our ultra-fast model — for when latency is the top priority
* Ultra-low latency (\~120ms median latency)
* Support for 15 languages
* High quality instant voice cloning
### Models overview
| **Name** | **Model ID** | **Description** | **Supported languages** |
| :------------------------------ | :----------------------------------------------------------- | :---------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------- |
| **Llama Realtime TTS-2** | `inworld-tts-2` | Our newest, most powerful model with natural language steering and stronger multilingual capabilities | 200+ languages and locales — see [Languages](/tts/capabilities/multilingual) |
| **Llama Realtime TTS 1.5 Max** | `inworld-tts-1.5-max` | High-quality, maximum-stability model with enhanced timestamps | `en`, `zh`, `ja`, `ko`, `ru`, `it`, `es`, `pt`, `fr`, `de`, `pl`, `nl`, `hi`, `he`, `ar` |
| **Llama Realtime TTS 1.5 Mini** | `inworld-tts-1.5-mini` | Ultra-fast, lowest-latency model, with enhanced timestamps | `en`, `zh`, `ja`, `ko`, `ru`, `it`, `es`, `pt`, `fr`, `de`, `pl`, `nl`, `hi`, `he`, `ar` |
Looking for `inworld-tts-1` or `inworld-tts-1-max`? These previous-generation models were discontinued on **June 15, 2026**. Requests to them are now automatically routed to their 1.5 successors (`inworld-tts-1` → `inworld-tts-1.5-mini`, `inworld-tts-1-max` → `inworld-tts-1.5-max`). We recommend migrating to `inworld-tts-2` to improve quality and latency.
## LLM
### Chat Completion
Inworld provides access to hundreds of LLMs from various providers through a unified [Chat Completions](/api-reference/routerAPI/chat-completions) API.
* **Available models**: See the [List Models](/api-reference/modelsAPI/modelservice/list-models) API or the [Models page](https://portal.inworld.ai/models) in the Inworld Portal for the full list of supported models and providers
* **Pricing**: Visit [inworld.ai/pricing](https://inworld.ai/pricing) for model pricing details
* **Specific model**: Call a model directly using the `provider/model` format (e.g., `openai/gpt-5`)
* **Auto-select**: Set `model` to `"auto"` to automatically pick the best model based on price, latency, or performance
* **Router**: [Create a router](/router/introduction) for conditional routing, A/B testing, and reusable configurations, then reference it via the `model` field (e.g., `my-router`)
## Embeddings
| | **Service Provider** | **Model ID** | **Description** |
| :---------- | :------------------------- | :------------------------------------------------------------ | :----------------------------------------------------------------------------------- |
| **Inworld** | SERVICE\_PROVIDER\_INWORLD | `BAAI/bge-large-en-v1.5` | Great for English text |
| **Inworld** | SERVICE\_PROVIDER\_INWORLD | `sentence-transformers/paraphrase-multilingual-mpnet-base-v2` | Great for multi-lingual text |
| **OpenAI** | SERVICE\_PROVIDER\_OPENAI | `text-embedding-3-small` | General purpose, efficient embedder with support for English and multi-lingual text. |
## Terms of Service
You may not violate the terms of service or policies of third-party model providers using Inworld's platform or your account will be subject to deactivation.
* Anthropic: [https://www.anthropic.com/legal/commercial-terms](https://www.anthropic.com/legal/commercial-terms)
* Cerebras: [https://www.cerebras.ai/terms-of-service](https://www.cerebras.ai/terms-of-service)
* DeepInfra: [https://deepinfra.com/terms](https://deepinfra.com/terms)
* Fireworks: [https://fireworks.ai/terms-of-service](https://fireworks.ai/terms-of-service)
* Google Vertex: [https://cloud.google.com/terms/](https://cloud.google.com/terms/)
* Groq: [https://groq.com/terms-of-use](https://groq.com/terms-of-use)
* Mistral: [https://mistral.ai/terms/#terms-of-use](https://mistral.ai/terms/#terms-of-use)
* OpenAI: [https://openai.com/policies/row-terms-of-use/](https://openai.com/policies/row-terms-of-use/)
* Tenstorrent: [https://tenstorrent.com/terms](https://tenstorrent.com/terms)
* XAI: [https://x.ai/legal/terms](https://x.ai/legal/terms)