gpt-oss-20b

completions

On:deepinfrafireworksai

gpt-oss-20b

completions

Published by: openaiProviders:

deepinfra fireworksai

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.

Provider	Input	Output
deepinfra	$0.04 / 1M tokens	$0.16 / 1M tokens
fireworksai	$0.07 / 1M tokens	$0.3 / 1M tokens

Released

Aug 5, 2025

Knowledge

Feb 6, 2025

Context

131072

Input

$0.04 / 1M tokens

Output

$0.16 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
deepinfra	131072 tokens	$0.04 / 1M tokens	$0.16 / 1M tokens	text	text	Apache-2.0
fireworksai	131072 tokens	$0.07 / 1M tokens	$0.3 / 1M tokens	text	text	Apache-2.0

Released Aug 5, 2025Knowledge Cutoff: Feb 6, 2025

Access gpt-oss-20b through LangDB AI Gateway

Recommended

Integrate with openai's gpt-oss-20b and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Available from 2 providers

Provider:

Benchmark Results for gpt-oss-20b

Category Performance Scores:

Academia: Score 58.15 (Top 22% - Rank #76)
Finance: Score 53.25 (Top 25% - Rank #87)
Marketing: Score 50.22 (Top 33% - Rank #114)
Maths: Score 61.70 (Top 25% - Rank #87)
Programming: Score 53.70 (Top 9% - Rank #32)
Science: Score 65.32 (Top 28% - Rank #97)
Writing: Score 49.77 (Top 38% - Rank #132)

Overall Performance: 56.01523809523809 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AA Coding Index	53.70	Top 9%	Programming
AAII	44.80	Top 17%	General
AA Math Index	61.70	Top 25%	Mathematics
GPQA	71.50	Top 23%	STEM (Physics, Chemistry, Biology)
HLE	8.50	Top 12%	General Knowledge
LiveCodeBench	72.10	Top 8%	Programming
MMLU-Pro	73.60	Top 47%	General Knowledge
SciCode	35.40	Top 23%	Scientific

GPQA Score: 71.50 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 131072 tokens

Comparing against 345 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

AA Coding Index

53.7

Programming

AAII

44.8

General

AA Math Index

61.7

Mathematics

GPQA

71.5

STEM (Physics, Chemistry, Biology)

HLE

8.5

General Knowledge

LiveCodeBench

72.1

Programming

MMLU-Pro

73.6

General Knowledge

SciCode

35.4

Scientific

Metric	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MMLU-Pro	SciCode
Score	53.7	44.8	61.7	71.5	8.5	72.1	73.6	35.4

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for gpt-oss-20b

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

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

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "gpt-oss-20b",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-oss-20b",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: gpt-oss-20b

Provider: deepinfra

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from deepinfra

gpt-oss-20b

gpt-oss-20b

Access gpt-oss-20b through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

deepseek-r1

DeepSeek-R1

deepseek-r1-0528

gpt-oss-20b by deepinfra - AI Model Details, Pricing, and Performance Metrics

gpt-oss-20b

gpt-oss-20b

Access gpt-oss-20b through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

deepseek-r1

DeepSeek-R1

deepseek-r1-0528