ParalonCloud
← All Resources

Tag

Qwen3

8 articles tagged with “Qwen3”

The Paralon capybara plugging a glowing cable into the last block of a workflow diagram
Guides & Tutorials

11 min read

Using n8n with an Open LLM API: One Credential Field, One Toggle, and the Node That Will Not Work

n8n talks to any OpenAI-compatible endpoint through the Base URL field of its OpenAI credential, and its OpenAI Chat Model node lists whatever /v1/models returns. n8n's OpenAI nodes now default to the Responses API, which most open endpoints answer with a 404; ours serves it, and both the Chat Model and the OpenAI node's Message a Model work. The setup, tested on n8n 2.38, a ticket-triage workflow you can import, and the one Extra Body line that cut the model's answer from 3.3 s to 1.0 s.

Read
The Paralon capybara feeding a stack of glowing cards onto a conveyor belt into a small machine
Guides & Tutorials

8 min read

Batch API for Open Models: Half-Price Chat, Embeddings and Responses Jobs with the OpenAI SDK

Paralon's Batch API takes a JSONL file of requests and returns a file of results, at 50% of the token price, through the same /v1/files and /v1/batches calls as OpenAI's. We ran it with the official Python SDK: 300 support tickets classified with zero failures, 100 embeddings and 20 Responses API drafts, billed at exactly half the live price, while live requests kept their normal latency.

Read
The Paralon capybara seated as a judge with a glowing gavel, weighing two floating sheets on a holographic balance
Guides & Tutorials

13 min read

LLM-as-a-Judge with an Open Model: 990 Planted Errors, 99.6% Caught, and What the Rubric Changes

We used Qwen 3.8 27B over an OpenAI-compatible API as a judge of dataset labels, and scored it against errors we planted ourselves so every number is exact. With a written rubric the judge caught 491 of 493 wrong labels and also rejected 58 labels the dataset called correct, 43 of them the same systematic mistake in the generator. Without the rubric it agreed with the dataset more and missed 20 planted errors. The rubric is not a tuning knob; it decides what the judge measures.

Read
The Paralon capybara joining two glowing cables with differently shaped plugs through a small adapter
Guides & Tutorials

11 min read

The OpenAI Responses API on Open Models: responses.create, the Agents SDK and n8n, Measured on Qwen 3.8

Tools are moving from Chat Completions to OpenAI's Responses API, and most open-model endpoints answer it with a 404. We now serve /v1/responses on Qwen 3.8 27B and ran the official OpenAI SDK, the OpenAI Agents SDK and n8n against it unchanged: all 10 SDK checks behaved as designed, a 24-task tool-using agent correct 24 of 24 through all three paths, and no measurable latency added by the translation. What is not supported, and the one setting that cut an n8n node from 3.3 s to 1.0 s.

Read
The Paralon capybara sorting a stream of glowing paper sheets into a row of green trays
Guides & Tutorials

13 min read

Document Classification with an Open LLM API: 7,218 Documents, No Training Data, $0.05 per Thousand

We classified the full 20 Newsgroups test split with Qwen 3.8 27B over an OpenAI-compatible API, zero-shot, ten documents per request, with the label set enforced by a JSON schema. 72% accuracy on twenty classes with no labeled data, 70,000 documents an hour on one key, and a third of all errors inside three categories that overlap by definition. Few-shot examples doubled the cost and moved accuracy half a point.

Read
The Paralon capybara holding a magnifying glass over a floating invoice while glowing rows of extracted fields lift off the page
Guides & Tutorials

10 min read

Invoice Data Extraction with a Vision LLM API: 60 Invoices, Every Field Scored, $0.78 per Thousand

We ran 60 invoices, half of them degraded like phone scans, through Qwen 3.8 27B's vision input over an OpenAI-compatible API with a JSON schema on the output. Vendor, customer, invoice number, currency, every amount and every line item came back right on all 60. The one thing that failed, half the time, was a date written with slashes, and the fix is two lines of code, not a bigger model.

Read
The Paralon capybara holding a magnifying lens up to a floating cloud of glowing connected dots
Guides & Tutorials

12 min read

Semantic Search with an Open Embeddings API: 990 Tickets, 5 Languages, and Where Keyword Search Still Wins

We indexed 990 support tickets with a 384-dimension open embedding model over an OpenAI-compatible /v1/embeddings endpoint and searched them 1,290 ways, scored against known intents and a TF-IDF keyword baseline. Same-language, keyword search was better. Across languages it collapsed to chance while embeddings held 47 to 58% precision. Adding a 27B reranker over the top ten lifted every language by 17 to 37 points for $0.09 per thousand queries. The whole index cost a tenth of a cent.

Read