Release 2026.10.14
API changes
Decision model d3
d3 (alias vllm-sr/d3) joins the decision models in public preview. It is vLLM Semantic Router's open-weight 27B decision model (Apache-2.0) and first on the text board of the Jev Decision Index. It costs $0.042 per million input tokens, and output is not billed. It reads text only, has a context of 24,576 tokens, and is served on both POST /v1/decisions and POST /v1/systemone.
Embeddings
New POST /v1/embeddings takes OpenAI's embeddings request, so client.embeddings.create in the OpenAI SDKs works as it is: vectors of 1024 dimensions for up to 512 inputs per request, billed on usage.prompt_tokens. Use a Serenity Edge API key. See Embeddings, rerank and redaction.
Rerank
New POST /v1/rerank scores up to 1000 documents against a query, in the format of the rerank APIs of Cohere and Jina. Its tokens are estimated as ceil((characters(query) + characters(document)) / 4) per document, with characters counted as Unicode code points, and returned in usage. See Rerank.
Redaction
New POST /v1/redact finds and masks personal data in up to 256 texts (192 KiB per request) in the privacy filter's own format, with model optional; the text sent is processed in memory only. Its tokens are estimated as ceil(characters / 4) over all the inputs. See Redaction.
Access and errors on the new routes
The three routes take Serenity Edge API keys; any other key gets HTTP 403 permission_denied with a message that names the route's API. A model sent to a route that does not serve it, or a request the model cannot process (The model server rejected the request. Check the input sizes and parameters.), gets HTTP 400. See Errors and rate limits.
Models
Embeddings, rerank and redaction models
Three models join the OpenAI-style list (GET /v1/models?format=openai), each with its route in endpoints and billed on input tokens only:
| Model | Alias | Route | Price per million input tokens |
|---|---|---|---|
qwen3-embedding-0.6b | qwen/qwen3-embedding-0.6b | POST /v1/embeddings | $0.008 |
qwen3-reranker-0.6b | qwen/qwen3-reranker-0.6b | POST /v1/rerank | $0.008 |
privacy-filter | openai/privacy-filter | POST /v1/redact | $0.009 |
Current prices are listed live on Pricing and limits.
paddleocr-vl-1.6 for document pages
paddleocr-vl-1.6 (aliases baidu/paddleocr-vl-1.6 and paddlepaddle/paddleocr-vl-1.6) joins the chat models: send one page image with a task prompt (OCR:, Table Recognition:, Formula Recognition: or Chart Recognition:) and it returns the page's text, table, formula or chart data, at $0.016 per million prompt tokens and $0.016 per million completion tokens (a full page is about 1,250 prompt tokens). It reads one image per request, uses temperature 0 unless you send one, has a context of 16,384 tokens and at most 8,192 output tokens, and does not reason, call tools or produce structured outputs. It is available on the API now, and ready for the OpenRouter onboarding, which is not live yet; see Document OCR.
Documentation
- New guide: Embeddings, rerank and redaction.
- New page: Routers and marketplaces. Serenity Edge is available as a provider on cortecs and EUrouter, with that platform's own account, key and billing; OpenRouter and other platforms are in onboarding, and the OpenRouter page now describes that status.
- Models: document OCR with
paddleocr-vl-1.6, and a live table of the embeddings, rerank and redaction models. - Pricing and limits: prices, token estimates and limits of the three routes.
- Errors and rate limits: the 400 for a model on the wrong route or rejected by the model server, the 403 that names the route's API, and the 192 KiB limit of
POST /v1/redact. - API reference: Create embeddings, Rerank documents and Redact personal data, and the
endpointsof the new models in List models.