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

# Models

> The Hopper model catalog — Gemma 4 31B, OmniVoice, and Nemotron ASR

Hopper serves three models, one for each stage of the voice agent pipeline. Request a model by its API ID on the endpoints listed in its section below.

| Model                 | API ID         | Source                                                                                                    | Price                                                       |
| --------------------- | -------------- | --------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- |
| Gemma 4 31B (Google)  | `gemma-4-31b`  | [`nvidia/Gemma-4-31B-IT-NVFP4`](https://huggingface.co/nvidia/Gemma-4-31B-IT-NVFP4)                       | \$1 per million input tokens; \$3 per million output tokens |
| OmniVoice (k2-fsa)    | `omnivoice`    | [`k2-fsa/OmniVoice`](https://huggingface.co/k2-fsa/OmniVoice)                                             | \$30 per million characters                                 |
| Nemotron ASR (NVIDIA) | `nemotron-asr` | [`nvidia/nemotron-3.5-asr-streaming-0.6b`](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b) | \$0.30 per hour of audio                                    |

## Gemma 4 31B

Hopper serves Gemma 4 31B, Google's open model, as NVIDIA's NVFP4-quantized checkpoint [`nvidia/Gemma-4-31B-IT-NVFP4`](https://huggingface.co/nvidia/Gemma-4-31B-IT-NVFP4). It handles chat completions with streaming and tool calling on the OpenAI-compatible API. Time to first token is \~37 ms on short prompts, measured 2026-08-02 from us-west-2 with cold, unique prompts.

| API ID        | Context window | Tool calling | Endpoint                    | Price                                                       |
| ------------- | -------------- | ------------ | --------------------------- | ----------------------------------------------------------- |
| `gemma-4-31b` | 25,000 tokens  | Supported    | `POST /v1/chat/completions` | \$1 per million input tokens; \$3 per million output tokens |

See [Chat completions](/llm/chat-completions) for request parameters, streaming, and tool calling.

## OmniVoice

Hopper serves OmniVoice, k2-fsa's open text to speech model ([`k2-fsa/OmniVoice`](https://huggingface.co/k2-fsa/OmniVoice)). It generates 24 kHz English audio and streams as WAV or raw PCM; MP3 is available for non-streaming requests. Voices come from the shared library or from cloning: instant cloning uses a single clip of at least 10 seconds, and pro cloning trains on a larger dataset asynchronously.

| API ID      | Languages | Output       | Default voice | Streaming formats | Price                       |
| ----------- | --------- | ------------ | ------------- | ----------------- | --------------------------- |
| `omnivoice` | English   | 24 kHz audio | `sarah`       | WAV, raw PCM      | \$30 per million characters |

See [Generate speech](/tts/generate-speech) for request parameters, and [Voice cloning](/tts/cloning) for instant and pro cloning.

## Nemotron ASR

Hopper serves Nemotron ASR, NVIDIA's open streaming speech-to-text model ([`nvidia/nemotron-3.5-asr-streaming-0.6b`](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b)). It transcribes uploaded audio over HTTP and live audio over WebSocket, returns word-level timestamps, and accepts keyterm lists to bias recognition. Streaming sessions include turn detection with three presets: `balanced`, `patient`, and `responsive`.

| API ID         | Sample rates                                              | Modes               | Word timestamps | Price                    |
| -------------- | --------------------------------------------------------- | ------------------- | --------------- | ------------------------ |
| `nemotron-asr` | 8,000–48,000 Hz (8000, 16000, 22050, 24000, 44100, 48000) | Batch and streaming | Included        | \$0.30 per hour of audio |

See [Transcription](/stt/transcription) for batch requests and [Streaming](/stt/streaming) for the WebSocket protocol.