# Models

> The models available on Serenity Edge: the Orion family and the open models, with context, output limits and capabilities read from the API.

Source: https://docs.serenityedge.ai/docs/models/

Serenity Edge serves two families of chat models: **Orion**, Serenity's own model line, and a set of **open models** addressed by their published names. It also serves [decision models](https://docs.serenityedge.ai/docs/models/#decision-models) and the models of the [embeddings, rerank and redaction](https://docs.serenityedge.ai/docs/models/#embeddings-rerank-and-redaction) routes, each on its own endpoint.

## Catalogue

The table is read from `GET /v1/models` when this page is published and again when you open it, so it shows what the API serves right now; the line under it says when it was read.

| Model id | Family | Context | Max output | Capabilities |
| --- | --- | --- | --- | --- |
| `orion-pro`, Orion Pro | Orion | 262,144 | 32,768 | Streaming, Tool calling, Structured outputs, Reasoning, Prefix caching |
| `orion-plus`, Orion Plus | Orion | 262,144 | 32,768 | Streaming, Tool calling, Structured outputs, Reasoning, Prefix caching |
| `qwen3.8-27b`, Qwen3.8 27B | Open | 262,144 | 32,768 | Streaming, Tool calling, Structured outputs, Reasoning, Prefix caching |
| `qwen3.6-35b-a3b`, Qwen3.6 35B A3B | Open | 262,144 | 32,768 | Streaming, Tool calling, Structured outputs, Reasoning, Prefix caching |
| `paddleocr-vl-1.6`, PaddleOCR-VL 1.6 | Open | 16,384 | 8,192 | Streaming |

Read from the API (`GET /v1/models`) when this page was published, on 6 November 2026, 19:49 UTC.

Pricing is listed on [Pricing and limits](https://docs.serenityedge.ai/docs/pricing-and-limits/). Use `GET /v1/models` to retrieve the catalogue programmatically; see [List models](https://docs.serenityedge.ai/docs/api/edge/list-models/).

## Two families

### Orion

`orion-pro` and `orion-plus` are the Orion family, Serenity's own model line. Each id is the configuration that Substrate AI recommends and maintains for a kind of workload (sampling defaults, prompt handling and serving configuration tuned for it): `orion-plus` for volume and latency, `orion-pro` for depth. Address the Orion ids to follow that recommended configuration and to benefit from future improvements without changing your code.

> **Preview**
> 
> Substrate AI is preparing fine-tuned Orion models. When they ship, the `orion-pro` and `orion-plus` ids will resolve to them; the change will be announced in the [release notes](https://docs.serenityedge.ai/release-notes/) in advance.

### Open models

`qwen3.8-27b` and `qwen3.6-35b-a3b` are general-purpose open models, served as published by their authors. Use these ids when you want to address an open model by its own name, for example to compare results with other providers.

`paddleocr-vl-1.6` is an open model for reading document pages: see [Document OCR](https://docs.serenityedge.ai/docs/models/#document-ocr).

## Choosing between `pro` and `plus`

-   Start with `orion-plus`. It is the fast, inexpensive option and handles most conversational, classification and extraction workloads well.
-   Move to `orion-pro` when the task needs more depth: long multi-document reasoning, strict adherence to complex instructions, or reliable multi-step tool calling.

The Orion models, `qwen3.8-27b` and `qwen3.6-35b-a3b` support [streaming](https://docs.serenityedge.ai/docs/streaming/), [tool calling](https://docs.serenityedge.ai/docs/tool-calling/), [structured outputs](https://docs.serenityedge.ai/docs/structured-outputs/) and reasoning; `paddleocr-vl-1.6` supports streaming only. The catalogue above shows the capabilities of each one. See the [API reference](https://docs.serenityedge.ai/docs/api/edge/create-chat-completion/) for the full parameter list.

## Image input

Every chat model reads images as well as text. Send them in a user message as `image_url` parts whose `url` is a base64 data URL (`data:image/png;base64,...`; PNG, JPEG, WebP or GIF), up to the model's limit per request:

```json
{"role": "user", "content": [
  {"type": "text", "text": "What does this chart show?"},
  {"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBORw0KGgo..."}}
]}
```

| Model | Images per request |
| --- | --- |
| `orion-pro` | 8 |
| `orion-plus` | 8 |
| `qwen3.8-27b` | 8 |
| `qwen3.6-35b-a3b` | 8 |
| `paddleocr-vl-1.6` | 1 |

Images count as input tokens and are billed at the model's input price. Image URLs are not fetched: a part with an `http` or `https` URL, more images than the model reads, or video, audio or file parts are refused with HTTP 400 (`invalid_request_error`, with the offending `param`). Images are counted over the whole conversation, earlier turns included: too many images carry the code `too_many_images`, so in a long conversation send only the most recent images and replace the older ones with a short text. Each model's limit is `supported_inputs.references.max` of its `image` input modality in [`GET /v1/models`](https://docs.serenityedge.ai/docs/api/edge/list-models/). The request body limit of 4 MB applies to the base64 data.

## Document OCR

`paddleocr-vl-1.6` (aliases `baidu/paddleocr-vl-1.6` and `paddlepaddle/paddleocr-vl-1.6`) is PaddleOCR-VL 1.6, an open vision-language model for documents. It reads one page image and returns the page's text, a table, a formula or the data of a chart, depending on the task prompt you send with the image. It is a chat model: call it with [`POST /v1/chat/completions`](https://docs.serenityedge.ai/docs/api/edge/create-chat-completion/).

Send one user message with the page as an `image_url` part (a base64 data URL, as in [Image input](https://docs.serenityedge.ai/docs/models/#image-input)) followed by a `text` part with one of these task prompts, exactly as written:

| Task prompt | What the answer contains |
| --- | --- |
| `OCR:` | The text of the page |
| `Table Recognition:` | The table in the image |
| `Formula Recognition:` | The formula in the image |
| `Chart Recognition:` | The data of the chart in the image |

```bash
curl https://api.serenityedge.ai/v1/chat/completions \
  -H "Authorization: Bearer $SERENITY_EDGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "paddleocr-vl-1.6",
    "messages": [
      {"role": "user", "content": [
        {"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBORw0KGgo..."}},
        {"type": "text", "text": "OCR:"}
      ]}
    ]
  }'
```

With the OpenAI Python library, read the page from a file and encode it:

```python
import base64

from openai import OpenAI

client = OpenAI(
    base_url="https://api.serenityedge.ai/v1",
    api_key="YOUR_SERENITY_EDGE_API_KEY",
)

with open("page-1.png", "rb") as image:
    page = base64.b64encode(image.read()).decode("ascii")

completion = client.chat.completions.create(
    model="paddleocr-vl-1.6",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{page}"}},
                {"type": "text", "text": "OCR:"},
            ],
        }
    ],
)

print(completion.choices[0].message.content)
```

What to know about this model:

-   **One image per request.** A second image is refused with HTTP 400 (`invalid_request_error`, `code: "too_many_images"`, `param: "messages"`, `This model reads at most 1 image(s) per request.`). Send a document of several pages as one request per page; the requests can run in parallel.
-   **Temperature 0 by default.** Without a `temperature` in the request, the model decodes greedily, which keeps transcriptions stable. A `temperature` you send is used as is.
-   **Text in, text out.** The model does not reason, call tools or produce structured outputs: send the image and the task prompt, and read the answer from `choices[0].message.content`. If a transcription reaches the model's maximum output, shown in the [catalogue](https://docs.serenityedge.ai/docs/models/#catalogue), the answer ends with `finish_reason: "length"`.
-   **Billing.** The image counts as prompt tokens: a full page is about 1,250 prompt tokens. Prompt and completion tokens are billed at the prices on [Pricing and limits](https://docs.serenityedge.ai/docs/pricing-and-limits/). In our measurements of 13 October 2026, a full page took 1,243 to 1,273 prompt tokens and was answered in 221 to 312 ms of server time, without the network.
-   **Access.** Call `paddleocr-vl-1.6` directly on the API at `https://api.serenityedge.ai/v1`. Since 2026-10-14 it is also ready for the [OpenRouter onboarding](https://docs.serenityedge.ai/docs/access/openrouter/), which is not live yet.
-   **Output length.** A `max_tokens` or `max_completion_tokens` above 8,192, the model's maximum output, is clamped to 8,192 rather than refused.

## Precision

The Orion models, `qwen3.8-27b` and `qwen3.6-35b-a3b` run in NVFP4, a 4-bit floating-point format for NVIDIA GPUs. It is the standard serving precision on Serenity Edge and is what the published prices assume. `paddleocr-vl-1.6` runs in BF16, the precision of its published weights.

## Decision models

> **Preview**
> 
> Decision models are in public preview. Their availability will be announced in the [release notes](https://docs.serenityedge.ai/release-notes/).

Decision models answer typed questions (yes or no, one of several options, a level on a scale) with calibrated probabilities instead of generating text, on their own endpoints: `POST /v1/decisions` and `POST /v1/systemone`. They are not chat models and are not listed in the catalogue above. `orion-compass` is for questions that need more depth; `orion-compass-flash` is for the lowest latency and price at volume. See [Decisions](https://docs.serenityedge.ai/docs/decisions/) for when to use them and how.

The table is read from `GET /v1/models?format=openai` when this page is published and again when you open it.

| Model id | Context | Reads | Input | Output | Endpoints |
| --- | --- | --- | --- | --- | --- |
| `d3`, also `vllm-sr/d3` | 24,576 | text, image | $0.042 | Free | /v1/decisions, /v1/systemone |
| `orion-compass`, alias of `orion-compass-26.1` | 32,000 | text | $0.034 | Free | /v1/decisions, /v1/systemone |
| `orion-compass-flash`, alias of `orion-compass-flash-26.1` | 32,000 | text, image | $0.017 | Free | /v1/decisions, /v1/systemone |

Read from the API (`GET /v1/models?format=openai`) when this page was published, on 6 November 2026, 19:49 UTC.

## Embeddings, rerank and redaction

Three more models are served on their own routes, for search, retrieval-augmented generation and privacy: `qwen3-embedding-0.6b` on `POST /v1/embeddings` (vectors in OpenAI's format), `qwen3-reranker-0.6b` on `POST /v1/rerank` (relevance scores in the format of Cohere and Jina) and `privacy-filter` on `POST /v1/redact` (personal data found and masked). They are not chat models and are not listed in the catalogue above. See [Embeddings, rerank and redaction](https://docs.serenityedge.ai/docs/embeddings-rerank-and-redaction/) for how to call them.

The table is read from `GET /v1/models?format=openai` when this page is published and again when you open it. Prices are in US dollars per million input tokens.

| Model id | Input | Endpoint |
| --- | --- | --- |
| `privacy-filter`, also `openai/privacy-filter` | $0.009 | /v1/redact |
| `qwen3-embedding-0.6b`, also `qwen/qwen3-embedding-0.6b` | $0.008 | /v1/embeddings |
| `qwen3-reranker-0.6b`, also `qwen/qwen3-reranker-0.6b` | $0.008 | /v1/rerank |

Read from the API (`GET /v1/models?format=openai`) when this page was published, on 6 November 2026, 19:49 UTC.