OpenAIChat

OpenAI: gpt-oss-20b

openai/gpt-oss-20b

131KContext Window

131KMax Output

Supported Protocols:reasoninginclude_reasoningmax_tokenstemperaturetop_pstopfrequency_penaltypresence_penaltyrepetition_penaltytop_kseedmin_presponse_formattoolstool_choice

Normal

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Capabilities

🧠 Reasoning🔧 Function CallingText GenerationCode GenerationAnalysis & ReasoningReasoning

Technical Specs

Input Modality

Text

Output Modality

Text

Arch

—

Default Temperature

0.7

Default Top_P

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$0.0300/M tokens
Text Output	—	$0.1400/M tokens

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="openai/gpt-oss-20b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)