# Model Serving - Active Models

This is the list of AI models currently **live and available** on the Sunrise Model Service. All models are served on Sunrise infrastructure through an OpenAI-compatible API and are ready for production use. **Your data is never retained, and we do not train our models on your inputs.**

For real-time health and availability, see the [model status dashboard](https://status.ai.sunrise.ch/).

---

## Active Models

*Input and Output (chf): credits per million tokens. Context window: maximum tokens per API call.*

### Chat

Instruction-following models for assistants, dialogue, and general text tasks.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-deepseek-v32` | 3.2 | [deepseek-ai/DeepSeek-V3.2](https://huggingface.co/deepseek-ai/DeepSeek-V3.2) | [MIT](https://opensource.org/license/mit) | 0.6156 | 1.8469 | 163'840 | Optimized for Reasoning chat completions. |
| `inference-gpt-oss-120b` | --- | [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.1154 | 0.4617 | 131'072 | Optimized for powerful reasoning, agentic tasks, and versatile developer use cases. |
| `inference-granite-33-8b` | 3.3 | [ibm-granite/granite-3.3-8b-instruct](https://huggingface.co/ibm-granite/granite-3.3-8b-instruct) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.1539 | 0.1539 | 32'768 | Optimized for Reasoning and instruction-following capabilities. |
| `inference-mistral-v03-7b` | 0.3 | [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.1539 | 0.1539 | 32'768 | Optimized for multilingual dialogue use cases. |

### Reasoning

Models for deliberate, step-by-step thinking and chain-of-thought tasks.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-deepseek-v4-flash` | 4 | [deepseek-ai/DeepSeek-V4-Flash-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731) | [MIT](https://opensource.org/license/mit) | 0.1462 | 0.3925 | 1'000'000 | Optimized for thinking and reasoning with extended context. |
| `inference-glm53-flash` | 5.3 | [zai-org/GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash/tree/main) | [MIT](https://opensource.org/license/mit) | 0.123 | 0.410 | 1'000'000 | High-performance multimodal reasoning model optimized for agentic workflows, coding, tool use, and long-context applications. |
| `inference-glm5` | 5.2 | [zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) | [MIT](https://opensource.org/license/mit) | 1.077 | 3.386 | 131'072 | Optimized for agentic engineering and long-horizon coding. Designed for sustained performance across extended agentic sessions with stronger coding, terminal, and software-engineering task capabilities. |
| `inference-qwen3-8b` | 3 | [RedHatAI/Qwen3-8B-quantized.w4a16](https://huggingface.co/RedHatAI/Qwen3-8B-quantized.w4a16) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.0269 | 0.1062 | 40'960 | Optimized for thinking and reasoning. |
| `inference-qwq-32b` | --- | [RedHatAI/QwQ-32B-quantized.w8a8](https://huggingface.co/RedHatAI/QwQ-32B-quantized.w8a8) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.9234 | 0.9234 | 32'768 | Optimized for thinking and reasoning. |

### Multimodal

Vision-language models for image understanding, analysis, and text generation from visual input.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-apertus-v15-70b` | 1.5 | [swiss-ai/Apertus-v1.5-70B](https://huggingface.co/swiss-ai/Apertus-v1.5-70B) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.6195 | 2.2201 | 262'144 | Optimized for multilingual dialogue, tool use, and agent workflows. |
| `inference-gemma4-31b` | 4 | [RedHatAI/gemma-4-31B-it-FP8-block](https://huggingface.co/RedHatAI/gemma-4-31B-it-FP8-block) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.118 | 0.325 | 131'072 | Optimized for handling text and image input and generating text output. |
| `inference-granite-vision-2b` | 3.2 | [ibm-granite/granite-vision-3.2-2b](https://huggingface.co/ibm-granite/granite-vision-3.2-2b) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.0770 | 0.0770 | 8'192 | Optimized for compact and efficient vision-language model |
| `inference-llama4-maverick` | 4 | [RedHatAI/Llama-4-Maverick-17B-128E-Instruct-quantized.w4a16](https://huggingface.co/RedHatAI/Llama-4-Maverick-17B-128E-Instruct-quantized.w4a16) | [Llama 4 Community License (custom)](https://www.llama.com/llama4/license/) | 0.2693 | 1.0773 | 1'048'576 | Optimized for text and multimodal experiences. Max images per prompt is 4 and no video prompts |
| `inference-llama4-scout-17b` | 4 | [RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16](https://huggingface.co/RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16) | [Llama 4 Community License](https://www.llama.com/llama4/license/) | 0.1924 | 0.6387 | 62'256 | Optimized for text and multimodal experiences. |
| `inference-qwen3-vl-235b` | 3 | [RedHatAI/Qwen3-VL-235B-A22B-Instruct-FP8-dynamic](https://huggingface.co/RedHatAI/Qwen3-VL-235B-A22B-Instruct-FP8-dynamic) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.7003 | 2.0000 | 128'000 | Optimized for text and multimodal experiences. |

### Embedding

Convert text into vector representations for semantic search and RAG retrieval.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-bge-m3` | --- | [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) | [MIT](https://opensource.org/license/mit) | 0.4309 | --- | , | Optimized for Embeddings and sparse retrieval with support for Multi-Functionality, Multi-Linguality, and Multi-Granularity. |
| `inference-granite-emb-278m` | --- | [ibm-granite/granite-embedding-278m-multilingual](https://huggingface.co/ibm-granite/granite-embedding-278m-multilingual) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.0770 | --- | , | Optimized for Embeddings. |
| `inference-qwen3-embedding-8b` | 3 | [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.0540 | --- | , | Optimized for text embeddings and retrieval across 100+ languages. |

### Reranker

Score and reorder retrieved passages by relevance to improve search quality.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-bge-reranker` | 2 | [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.0077 | --- | , | Optimized for Reranker to get relevance score. |
| `inference-qwen3-reranker-8b` | 3 | [Qwen/Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.0080 | --- | , | Optimized for reranking to get relevance scores across 100+ languages. |

### OCR

Extract text from images and scanned documents using optical character recognition.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-deepseek-ocr` | --- | [inference-deepseek-ocr](https://huggingface.co/deepseek-ai/DeepSeek-OCR) | [MIT](https://opensource.org/license/mit) | 0.3848 | 1.5391 | , | Optimized for Contexts Optical Compression. |

### Vision-language

Parse complex document layouts and extract structured content from PDFs and files.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-miner-u25` | 2.5 | [opendatalab/MinerU2.5-Pro-2605-1.2B](https://huggingface.co/opendatalab/MinerU2.5-Pro-2605-1.2B) | [AGPL 3.0](https://www.gnu.org/licenses/agpl-3.0.html) | 0.38 | 0.23 | 8'192 | Optimized for document parsing that achieves state-of-the-art accuracy with high computational efficiency. |

### Speech to Text

Transcribe spoken audio into text, including long-form and multilingual speech.

| Model Name | Version | Model | License type | Input (chf) | Output (chf) | Context window | Description |
| --- | --- | --- | --- | --- | --- | --- | --- |
| `inference-whisper-large-v3` | 3 | [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.006 per minute | NA | , | Optimized for automatic speech recognition (ASR) and speech translation. WhisperX model support high throughput, ASR, long audio files support, speaker diarization & attribution and word-level alignments. |
| `inference-flix-swissgerman-full` | --- | [Flix-AI/flix-swissgerman-full](https://huggingface.co/Flix-AI/flix-swissgerman-full) | [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) | 0.006 per minute | NA | , | Optimized for Swiss German automatic speech recognition (ASR). Transcribes Swiss German dialect speech into Standard German text via WhisperX. |

---
**Model Updates and Deprecation Disclaimer**
We reserve the right to modify, upgrade, or replace any AI models used in our services at any time. This may include deprecating older models and introducing newer versions as we deem necessary to maintain performance, security, and service quality. While we aim to provide notice when feasible, changes may occur without prior notification.

**NOTE** Pricing is subject to change at our discretion.

---

### Active Models by Use Case

The groups below mirror the **Active Models** sections: every live model appears exactly once, grouped by primary workload.

- **Chat, assistants, and general text (instruction-following)**  
  Multilingual dialogue, coding help, and broad assistant-style tasks: **DeepSeek V3.2**, **GLM 4.6** (chat; deployed on demand), **GPT OSS 120B**, **Granite 3.3 8B**, **Mistral 7B Instruct v0.3**.

- **Reasoning and chain-of-thought**  
  Deliberate, step-heavy tasks: **DeepSeek V4 Flash**, **GLM 5.3 Flash**, **GLM 5**, **Qwen3 8B**, **QwQ 32B**.

- **Multimodal (images and text)**  
  Image+text input and text output, or compact vision-language: **Apertus v1.5 70B**, **Gemma 4 31B**, **Granite Vision 3.2 2B**, **Llama 4 Maverick**, **Llama 4 Scout 17B**, **Qwen3 VL 235B**.

- **RAG (retrieval-augmented generation)**  
  Embeddings, reranking, and retrieval stacks: **BGE M3** (embedding), **BGE Reranker v2 M3**, **Granite Embedding 278M**, **Qwen3 Embedding 8B**, **Qwen3 Reranker 8B**.

- **OCR, layout, and document parsing**  
  Optical compression, layout, and structured document workflows: **DeepSeek OCR**, **MinerU 2.5**.

- **Speech**  
  Transcription and speech-centric workflows: **Whisper Large v3**, **Flix Swiss German Full**.

- **File conversion**
  To transform files from one format to another, use the Docling service hosted by Sunrise Model Service. You can access it via the REST API endpoint: **https://maas.ai.sunrise.ch/v1/convert/file**. For implementation details, see the [sample API calls](/maas/model-service-guides/sample-api-calls/#transform-files-from-one-format-to-another-example-pdf-to-markdown).

**Agents, tool calling, and orchestration** usually pick one primary LLM from the **chat** or **reasoning** groups, then add other pieces only when the workflow needs them: **multimodal** models for image inputs; **OCR** or **MinerU** to extract text or structure from documents; and **RAG** (embedding, reranking) when the agent must **retrieve** relevant passages from content you have already chunked and indexed.

---

### Active Models by Risk

| Risk Level      | Typical Models                                                                         | Main Risks                                               |
| --------------- | -------------------------------------------------------------------------------------- | -------------------------------------------------------- |
| **Low Risk**    | Embedding models, OCR, translation, sentiment analysis                                 | Limited misuse potential                                 |
| **Medium Risk** | General LLMs, code generation, image generation                                        | Hallucinations, insecure code, copyright issues          |
| **High Risk**   | Unmoderated LLMs, NSFW models, unsafe diffusion models, executable pickle-based models | Malware, harmful content, prompt injection, data leakage |

---

## Using the models

Looking for ready-to-run examples? See the [Model Service Guides](model-service-guides/index.md):

- [How to inference an AI model](model-service-guides/how-to-inference-a-model.md), what you need to make a call (Base URL, Model Name, API Key).
- [Sample API calls](model-service-guides/sample-api-calls.md), cURL examples for chat, embeddings, multimodal, OCR, and more.