
Link Parsing
API Overview
Add link parsing capabilities to any large language model
API Console
Log in to explore more features! Click to Log In
API Reference (1)
| API Description | API Endpoint | Request Method | Stability | Parameter Description |
|---|---|---|---|---|
Chat(Link Parsing) | POST | Stable | View Details | |
Document Details Add webpage/file parsing capabilities to all models, with two available methods—choose either one: 1.Append -file-parse to the model suffix, e.g., gpt-4o-file-parse (convenient for third-party software). 2.Add the parameter “file-parse”: true when making a model request (convenient for API usage). This feature will automatically extract and parse links from messages, sending the content to the model without requiring additional parameters. Supported formats: Web links, PDF, DOCX, CSV, TXT, HTML, ODT, RTF, EPUB, MD, XML, XSL, PPTX, POTX, JS, C. Support Parameters:
Price: Base model price + File Parsing API(0.02 PTC / 1M Token) Request Parameters Header ParametersContent-TypestringRequired Example Value: application/jsonAcceptstringRequired Example Value: application/jsonAuthorizationstringRequired Example Value: Bearer {{YOUR_API_KEY}}Request Body application/jsonmodelstringRequired The ID of the model to use. For details on which models are suitable for the chat API, please refer to the model endpoint compatibility table. messagesarray[object]Required Generate chat completion messages in chat format. rolestringOptional contentstringOptional temperatureintegerOptional What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both. top_pintegerOptional An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. nintegerOptional How many chat completion choices to generate for each input message. streambooleanOptional If set, partial messages will be sent as they become available, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a [DONE] message. See the OpenAI Cookbook for example code. stopstringOptional Up to 4 sequences where the API will stop generating further tokens. max_tokensintegerOptional The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model’s context length. presence_penaltynumberOptional A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics. See more information about frequency and presence penalties. frequency_penaltynumberOptional A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim. See more information about frequency and presence penalties. logit_biasnullOptional Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. userstringOptional A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.。 | ||||
API Pricing
| Model | Description | 302.AI Price |
|---|
Service | Based on the original model + file parsing interface fee (0.02 PTC / 1M Token) |
|