GPT-OSS 20B

Invoke GPT-OSS 20B, a 20B-parameter large language model with a 131k-token context length, and send it a tool-calling request.

Last updated

View as Markdown Agent setup

GPT-OSS 20B is an open-source large language model with 20 billion parameters, built for text generation, conversation, and other natural language processing tasks. It reads text, returns text, and accepts tool definitions in the request. AI Inference runs it under the id gpt-oss-20b.

Model details

The model id is the string that selects this model, and it is the first argument Azion.AI.run takes. The HuggingFace repository holds the model card.

DetailValue
Model nameGPT-OSS 20B
Version20B
Model categoryLarge Language Model (LLM)
Model idgpt-oss-20b
Size20B parameters
HuggingFace modelopenai/gpt-oss-20b
OpenAI-compatible endpointOpenAI Chat API
LicenseApache 2.0

Capabilities

These values belong to the model and are not part of the request body. For the fields every chat request accepts, with their types, defaults, and bounds, refer to Model invocation.

CapabilityValue
Input dataText
Context length131k tokens
Tool callingYes
Supports LoRANo

Usage

A function invokes the model with Azion.AI.run, passing the id as the first argument and an OpenAI-compatible request body as the second. The examples below use that binding. To send the same body to the OpenAI-compatible HTTP endpoint instead, refer to Model invocation.

Chat completion

This request carries a system message, a user message, and the sampling fields that shape the output:

TypeScript
01const modelResponse = await Azion.AI.run("gpt-oss-20b", {
02 "stream": false,
03 "max_tokens": 1024,
04 "temperature": 0.7,
05 "top_p": 0.9,
06 "messages": [
07 { "role": "system", "content": "You are a helpful assistant." },
08 { "role": "user", "content": "Name the European capitals." }
09 ]
10})

The model answers with one entry in choices, and the generated text sits at choices[0].message.content:

JSON
01{
02 "id": "chatcmpl-example",
03 "object": "chat.completion",
04 "created": 1767268800,
05 "model": "gpt-oss-20b",
06 "choices": [
07 {
08 "index": 0,
09 "message": {
10 "role": "assistant",
11 "reasoning_content": null,
12 "content": "Sure! Here is a list of some European capitals...",
13 "tool_calls": []
14 },
15 "logprobs": null,
16 "finish_reason": "stop",
17 "stop_reason": null
18 }
19 ],
20 "usage": {
21 "prompt_tokens": 9,
22 "total_tokens": 527,
23 "completion_tokens": 518,
24 "prompt_tokens_details": null
25 },
26 "prompt_logprobs": null
27}

Tool calling

A tool-calling request adds a tools array to the body. Each entry sets type to function and carries a function object holding the name the model calls, a description of what it does, and its parameters in JSON Schema form:

TypeScript
01const modelResponse = await Azion.AI.run("gpt-oss-20b", {
02 "stream": false,
03 "max_tokens": 1024,
04 "messages": [
05 { "role": "system", "content": "You are a helpful assistant with access to tools." },
06 { "role": "user", "content": "What is the weather in London?" }
07 ],
08 "tools": [
09 {
10 "type": "function",
11 "function": {
12 "name": "get_weather",
13 "description": "Get the current weather for a location",
14 "parameters": {
15 "type": "object",
16 "properties": {
17 "location": {
18 "type": "string",
19 "description": "The city and state"
20 }
21 },
22 "required": ["location"]
23 }
24 }
25 }
26 ]
27})

When the model selects a tool, it returns content as null, names the call in tool_calls with the arguments it chose, and sets finish_reason to tool_calls:

JSON
01{
02 "id": "chatcmpl-tool-example",
03 "object": "chat.completion",
04 "created": 1746821866,
05 "model": "gpt-oss-20b",
06 "choices": [
07 {
08 "index": 0,
09 "message": {
10 "role": "assistant",
11 "reasoning_content": null,
12 "content": null,
13 "tool_calls": [
14 {
15 "id": "chatcmpl-tool-0123456789abcdef0123456789abcdef",
16 "type": "function",
17 "function": {
18 "name": "get_weather",
19 "arguments": "{\"location\": \"London\"}"
20 }
21 }
22 ]
23 },
24 "logprobs": null,
25 "finish_reason": "tool_calls",
26 "stop_reason": null
27 }
28 ],
29 "usage": {
30 "prompt_tokens": 293,
31 "total_tokens": 313,
32 "completion_tokens": 20,
33 "prompt_tokens_details": null
34 },
35 "prompt_logprobs": null
36}
Model invocation

Every field a request body accepts, and the HTTP endpoint that takes the same body.

AI models

The other models AI Inference runs, and the id each one answers to.

AI Inference

The product that runs this model.

Functions

The product whose runtime holds the binding the examples on this page call.

AI Inference limits

The conditions under which Azion terminates or deprovisions a model.

Glossary

Where model id, context length, and the rest of the AI Inference vocabulary are defined.