gpt-oss-120b:exacto

completions

byopenrouter

gpt-oss-120b:exacto

completions

Published by: openaiProvider:

openrouter

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.

Released

Aug 5, 2025

Knowledge

Feb 6, 2025

License

Apache-2.0

Context

131072

Input

$0.08 / 1M tokens

Output

$0.36 / 1M tokens

Capabilities: tools, reasoning

Accepts: text

Returns: text

Released Aug 5, 2025Knowledge Cutoff: Feb 6, 2025License: Apache-2.0

Context: 131072 Input: $0.08 / 1M tokensOutput: $0.36 / 1M tokensCapabilities: tools, reasoningAccepts: textReturns: text

Access gpt-oss-120b:exacto through LangDB AI Gateway

Recommended

Integrate with openai's gpt-oss-120b:exacto 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

Benchmark Results for gpt-oss-120b:exacto

Category Performance Scores:

Maths: Score 93.40 (Top 3% - Rank #10)
Finance: Score 76.95 (Top 6% - Rank #20)
Science: Score 73.05 (Top 22% - Rank #71)
Writing: Score 63.85 (Top 18% - Rank #58)
Academia: Score 69.83 (Top 9% - Rank #29)
Marketing: Score 66.12 (Top 11% - Rank #36)
Programming: Score 49.60 (Top 8% - Rank #26)

Overall Performance: 70.39896825396826 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
HLE	18.50	Top 7%	General Knowledge
GPQA	79.15	Top 18%	STEM (Physics, Chemistry, Biology)
MMLU	90.00	Top 10%	General Knowledge
SciCode	38.90	Top 20%	Scientific
MMLU-Pro	80.80	Top 32%	General Knowledge
LiveCodeBench	87.80	Top 1%	Programming
AA Math Index	93.40	Top 3%	Mathematics
AA Coding Index	49.60	Top 8%	Programming
AAII	60.50	Top 6%	General

MMLU Score: 90.00 - Massive Multitask Language Understanding benchmark

GPQA Score: 79.15 - Graduate-level reasoning benchmark

Model Comparison:

Provider: openrouter

Model Type: completions

Context Size: 131072 tokens

Comparing against 320 models in the database

Performance Analytics for gpt-oss-120b:exacto

Usage Statistics (Last 1 Days):

Total Requests: 1 API calls
Average TPS: 593.37 tokens per second
Average Response Time: 1304.40ms
Average Time to First Token: 984.80ms
Total Cost: $0.00
Average Request Cost: $0.0001

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
11/17/2025	1	593.37	1304.40ms	984.80ms	$0.00

Performance Summary:

Model: gpt-oss-120b:exacto by openrouter

Monitoring Period: 11/11/2025 to 11/18/2025

Average Daily Requests: 1

Peak Daily Requests: 1

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

593.37 tokens/s

Category Scores

maths#6 finance#9

Benchmark Tests

View Other Benchmarks

HLE

18.5

General Knowledge

GPQA

79.2

STEM (Physics, Chemistry, Biology)

MMLU

90.0

General Knowledge

SciCode

38.9

Scientific

MMLU-Pro

80.8

General Knowledge

LiveCodeBench

87.8

Programming

AA Math Index

93.4

Mathematics

AA Coding Index

49.6

Programming

AAII

60.5

General

Metric	HLE	GPQA	MMLU	SciCode	MMLU-Pro	LiveCodeBench	AA Math Index	AA Coding Index	AAII
Score	18.5	79.2	90.0	38.9	80.8	87.8	93.4	49.6	60.5

Compare with Similar Models

Code Examples

Integration samples and API usage

Code Samples for gpt-oss-120b:exacto

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

Model: gpt-oss-120b:exacto

Provider: openrouter

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

Create API Key

Related Models

Similar models from openrouter

gpt-oss-120b:exacto

gpt-oss-120b:exacto

Access gpt-oss-120b:exacto through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

afm-4.5b

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2-preview-deepseek-671b

gpt-oss-120b:exacto by openrouter - AI Model Details, Pricing, and Performance Metrics

gpt-oss-120b:exacto

gpt-oss-120b:exacto

Access gpt-oss-120b:exacto through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

afm-4.5b

aion-1.0

aion-1.0-mini

aion-rp-llama-3.1-8b

coder-large

cogito-v2-preview-deepseek-671b