gpt-oss-120b

completions

On:fireworksaideepinfragroqparasail

gpt-oss-120b

completions

Published by: openaiProviders:

fireworksai deepinfra groq parasail

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Provider	Input	Output
fireworksai	$0.15 / 1M tokens	$0.6 / 1M tokens
deepinfra	$0.09 / 1M tokens	$0.45 / 1M tokens
groq	$0.15 / 1M tokens	$0.75 / 1M tokens
parasail	$0.15 / 1M tokens	$0.6 / 1M tokens

Released

Aug 5, 2025

Knowledge

Feb 6, 2025

Context

131072

Input

$0.15 / 1M tokens

Output

$0.6 / 1M tokens

Capabilities: tools

Accepts: text

Returns: text

Providers	Context	Input Price	Output Price	Input Formats	Output Formats	License
fireworksai	131072 tokens	$0.15 / 1M tokens	$0.6 / 1M tokens	text	text	Apache-2.0
deepinfra	131072 tokens	$0.09 / 1M tokens	$0.45 / 1M tokens	text	text	Apache-2.0
groq	131072 tokens	$0.15 / 1M tokens	$0.75 / 1M tokens	text	text	Apache-2.0
parasail	131072 tokens	$0.15 / 1M tokens	$0.6 / 1M tokens	text	text	Apache-2.0

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

Access gpt-oss-120b through LangDB AI Gateway

Recommended

Integrate with openai's gpt-oss-120b 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 4 providers

Provider:

Benchmark Results for gpt-oss-120b

Category Performance Scores:

Academia: Score 68.58 (Top 5% - Rank #17)
Finance: Score 75.70 (Top 4% - Rank #14)
Marketing: Score 65.87 (Top 9% - Rank #31)
Maths: Score 93.40 (Top 1% - Rank #4)
Programming: Score 41.20 (Top 18% - Rank #61)
Science: Score 73.05 (Top 15% - Rank #51)
Writing: Score 63.85 (Top 14% - Rank #47)

Overall Performance: 68.80611111111112 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AA Coding Index	41.20	Top 18%	Programming
AAII	58.00	Top 5%	General
AA Math Index	93.40	Top 1%	Mathematics
GPQA	79.15	Top 12%	STEM (Physics, Chemistry, Biology)
HLE	18.50	Top 3%	General Knowledge
LiveCodeBench	65.30	Top 17%	Programming
MMLU-Pro	80.80	Top 23%	General Knowledge
SciCode	36.20	Top 20%	Scientific

GPQA Score: 79.15 - Graduate-level reasoning benchmark

Model Comparison:

Provider: fireworksai

Model Type: completions

Context Size: 131072 tokens

Comparing against 335 models in the database

Performance Analytics for gpt-oss-120b

Usage Statistics (Last 1 Days):

Total Requests: 2 API calls
Average TPS: 212.20 tokens per second
Average Response Time: 1008.50ms
Average Time to First Token: 1008.50ms
Total Cost: $0.00
Average Request Cost: $0.0001

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
10/8/2025	2	212.20	1008.50ms	1008.50ms	$0.00

Performance Summary:

Model: gpt-oss-120b by fireworksai

Monitoring Period: 10/2/2025 to 10/9/2025

Average Daily Requests: 2

Peak Daily Requests: 2

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

212.20 tokens/s

Category Scores

academia#9 finance#5 maths#2

Benchmark Tests

View Other Benchmarks

AA Coding Index

41.2

Programming

AAII

58.0

General

AA Math Index

93.4

Mathematics

GPQA

79.2

STEM (Physics, Chemistry, Biology)

HLE

18.5

General Knowledge

LiveCodeBench

65.3

Programming

MMLU-Pro

80.8

General Knowledge

SciCode

36.2

Scientific

Metric	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MMLU-Pro	SciCode
Score	41.2	58.0	93.4	79.2	18.5	65.3	80.8	36.2

Compare with Similar Models

gemini-2.5-pro-preview

Code Examples

Integration samples and API usage

Code Samples for gpt-oss-120b

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-120b",
    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-120b",
    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-120b",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: gpt-oss-120b

Provider: fireworksai

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

Create API Key

Related Models

Similar models from fireworksai

gpt-oss-120b

gpt-oss-120b

Access gpt-oss-120b through LangDB AI Gateway

Statistics

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-r1-0528

deepseek-r1-05-28

gpt-oss-120b by fireworksai - AI Model Details, Pricing, and Performance Metrics

gpt-oss-120b

gpt-oss-120b

Access gpt-oss-120b through LangDB AI Gateway

Statistics

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-r1-0528

deepseek-r1-05-28