OpenAI-compatible API

App · 2 actions

Chat with models on any server that takes OpenAI API requests at a Base URL you give, such as vLLM, LM Studio, NVIDIA NIM or an AI gateway, and list the models it serves.

List models

List the models the server offers, with who owns each one.

Inputs

None.

Outputs

countnumber
How many models there are.
modelslist
The models, in the order the server lists them.
Example output
{
  "count": 2,
  "models": [
    {
      "id": "openai/gpt-oss-120b",
      "owned_by": "vllm"
    },
    {
      "id": "Qwen/Qwen3-32B",
      "owned_by": "vllm"
    }
  ]
}

Send a message

Send a message to a model on the server and get its answer, with an optional system prompt, or a JSON schema to get the answer back as data.

Inputs

ModelmodeltextRequired
The model to answer, as the server names it, such as openai/gpt-oss-120b. Pick one the server lists, or type its name.
PromptprompttextRequired
What to ask or tell the model.
System promptsystemtext
Instructions the model follows for the whole answer, such as its role or the format to answer in.
Temperaturetemperaturenumber
How varied the answer is, from 0 (the same answer every time) to 2. Leave empty for the server's own setting.From 0 to 2.0.
Max tokensmax_tokensnumber
The most tokens the model may write, its thinking included (about three quarters of a word each). Leave empty to let the server decide.At least 1.
JSON schemajson_schematext
A JSON schema the answer has to follow, pasted as JSON, such as {"type": "object", "properties": {"summary": {"type": "string"}}}. A later step then reads the answer's fields from json. Leave empty for an answer in plain text.

Outputs

finish_reasontext
Why the model stopped: stop when it finished, length when it reached the maximum tokens.
jsonobject
The answer read as JSON, usually a record with the fields the JSON schema names, when one was given; null without one.
modeltext
The model that answered, as the server names it.
texttext
The model's answer.
thinkingtext
The model's reasoning before it answered, from a model that thinks first; null for one that doesn't.
usageobject
The tokens the request took, as the server counts them; 0 where it doesn't say.
Example output
{
  "finish_reason": "stop",
  "json": {
    "sentiment": "positive"
  },
  "model": "openai/gpt-oss-120b",
  "text": "{\"sentiment\": \"positive\"}",
  "thinking": null,
  "usage": {
    "input_tokens": 42,
    "output_tokens": 9
  }
}

On this page