Open WebUI provides an OpenAI-compatible Rest API. While working with researchers and students, it was discovered that OpenAI's documentation lacks any description of the REST parameters. If you find that these are incorrect please notify the Research Computing Team via a ticket.
OpenWeb UI API:
Open WebUI safeguards its API through features like mandatory authentication using API keys, endpoint restrictions, backend routing for Ollama API requests, granular user permissions, and the ability to configure environment variables to further restrict access, ensuring that only authorized users can interact with the AI models through the API.
Swagger Documentation:
Users are recommended to test out the API using the provided Swagger docs. https://chat.hpc.fau.edu/docs

Creating an API Key:
- Login to https://chat.hpc.fau.edu/
- Click on the profile icon on the bottom left or top right
- Click "Account"
- Click Show next to the API Keys header and click create API key.

Example Calls:
Example Completion / Chat:
List Models:
Request:
#!/bin/bash
OPENAI_API_KEY=YOURAPITOKENFROMSETTINGS
curl -X 'GET' \
'https://chat.hpc.fau.edu/openai/models' \
-H 'accept: application/json' \
-H "Authorization: Bearer $OPENAI_API_KEY" | jq
Response:
{
"data": [
{
"id": "llava",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "llava",
"openai": {
"id": "llava",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "Llama-3.2-11B-Vision-Instruct",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "Llama-3.2-11B-Vision-Instruct",
"openai": {
"id": "Llama-3.2-11B-Vision-Instruct",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "gemma2",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "gemma2",
"openai": {
"id": "gemma2",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "codestral",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "codestral",
"openai": {
"id": "codestral",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "Llama-3.2-3B-Instruct",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "Llama-3.2-3B-Instruct",
"openai": {
"id": "Llama-3.2-3B-Instruct",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "mistral-large",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "mistral-large",
"openai": {
"id": "mistral-large",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "tinyllama",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "tinyllama",
"openai": {
"id": "tinyllama",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "qwen2",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "qwen2",
"openai": {
"id": "qwen2",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
},
{
"id": "microsoft/phi-4",
"object": "model",
"created": 1677610602,
"owned_by": "openai",
"name": "microsoft/phi-4",
"openai": {
"id": "microsoft/phi-4",
"object": "model",
"created": 1677610602,
"owned_by": "openai"
},
"urlIdx": 1
}
]
}
Chat Completions:
Request:
#!/bin/bash
OPENAI_API_KEY=YOURAPITOKENFROMSETTINGS
curl https://chat.hpc.fau.edu/openai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "microsoft/phi-4",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}' | jq
Response:
{
"id": "chatcmpl-a3328b366e3848699e0a353e23080987",
"created": 1740508508,
"model": "microsoft/phi-4",
"object": "chat.completion",
"system_fingerprint": null,
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hello! How can I assist you today? Let me know if there's anything specific you'd like help with. ๐",
"role": "assistant",
"tool_calls": null,
"function_call": null,
"refusal": null,
"reasoning_content": null
}
}
],
"usage": {
"completion_tokens": 26,
"prompt_tokens": 19,
"total_tokens": 45,
"completion_tokens_details": null,
"prompt_tokens_details": null
},
"service_tier": null,
"prompt_logprobs": null
}
Example Text-To-Voice using OwlChat.
#!/bin/bash
OPENAI_API_KEY=YOURAPITOKENFROMSETTINGS
OPENAPI_BASE_URL=https://chat.hpc.fau.edu/api
curl $OPENAPI_BASE_URL/v1/audio/speech \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-1",
"input": "Today is a wonderful day to build something people love!",
"voice": "alloy",
"response_format": "mp3",
"speed": 1.0
}' \
--output speech.mp3
Prompt Attributes:
Please reference the following curated list of parameters taken from the Azure OpenAI Site. We are validating this list manually to confirm functionality. In the meantime, this is an excellent starting place for users who are interested in manipulating the default settings of different AI models via the REST interface.
API Parameters
Name
|
Type
|
Description
|
prompt
|
string or array
|
The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.
Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt isn't specified the model will generate as if from the beginning of a new document.
|
best_of
|
integer
|
Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results can't be streamed.
When used with n, best_of controls the number of candidate completions and n specifies how many to return รขโฌโ best_of must be greater than n.
Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.
|
echo
|
boolean
|
Echo back the prompt in addition to the completion
|
frequency_penalty
|
number
|
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.
|
logit_bias
|
object
|
Modify the likelihood of specified tokens appearing in the completion.
Accepts a JSON object that maps tokens (specified by their token ID in the GPT 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.
As an example, you can pass {"50256": -100} to prevent the <|endoftext|> token from being generated.
|
logprobs
|
integer
|
Include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the five most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.
The maximum value for logprobs is 5.
|
max_tokens
|
integer
|
The maximum number of tokens that can be generated in the completion.
The token count of your prompt plus max_tokens can't exceed the model's context length.
|
n
|
integer
|
How many completions to generate for each prompt.
Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.
|
presence_penalty
|
number
|
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.
|
seed
|
integer
|
If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.
Determinism isn't guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.
|
stop
|
string or array
|
Up to four sequences where the API will stop generating further tokens. The returned text won't contain the stop sequence.
|
stream
|
boolean
|
Whether to stream back partial progress. If set, tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
|
suffix
|
string
|
The suffix that comes after a completion of inserted text.
This parameter is only supported for gpt-3.5-turbo-instruct.
|
temperature
|
number
|
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_p
|
number
|
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.
|
user
|
string
|
A unique identifier representing your end-user, which can help to monitor and detect abuse.
|
|