Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/Jatin-Mehra119/PDF-Insight-Beta/llms.txt

Use this file to discover all available pages before exploring further.

The /models endpoint returns the complete list of LLM model configurations that the server supports. The id value from any entry in the response can be passed as the model_name field in POST /upload-pdf (to set the default model for a session) or in POST /chat (to override the model for a single request). This endpoint requires no authentication and no request body.

​
Request

Method: GET
Path: /models

​
curl example

curl http://localhost:8000/models

​
Response

Status: 200 OK
​
models
array
Ordered list of available model configurations. Pass the id of any entry as model_name in upload or chat requests.

​
Available models

idname
meta-llama/llama-4-scout-17b-16e-instructLlama 4 Scout 17B
llama-3.1-8b-instantLlama 3.1 8B Instant
llama-3.3-70b-versatileLlama 3.3 70B Versatile
openai/gpt-oss-120bGPT-OSS 120B

​
Example response

{
  "models": [
    {
      "id": "meta-llama/llama-4-scout-17b-16e-instruct",
      "name": "Llama 4 Scout 17B"
    },
    {
      "id": "llama-3.1-8b-instant",
      "name": "Llama 3.1 8B Instant"
    },
    {
      "id": "llama-3.3-70b-versatile",
      "name": "Llama 3.3 70B Versatile"
    },
    {
      "id": "openai/gpt-oss-120b",
      "name": "GPT-OSS 120B"
    }
  ]
}
The server default model (used when model_name is omitted from /upload-pdf) is llama-3.1-8b-instant — a fast, lightweight option well-suited for straightforward document Q&A. For the most accurate answers on complex or technical documents, consider selecting meta-llama/llama-4-scout-17b-16e-instruct (Llama 4 Scout 17B), which offers significantly stronger reasoning and instruction-following capability at the cost of slightly higher latency.

Build docs developers (and LLMs) love

Get started for freeTalk to us