Loading...
About
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...
Related Models
Pricing
Input
$0.04
per 1M tokens
Output
$0.18
per 1M tokens
Blended
$0.07
per 1M tokens
Cheaper than 87% of models. Median price is $0.56/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.07
Monthly
$2.23
vs. Similar Models
OpenAI: o4 MiniQ:-0.2
$1.93+2493%
Google: Gemini 3.1 Flash Lite PreviewQ:+0.2
$0.56+658%
Claude 4 Opus (Non-reasoning)Q:-0.3
$32.81+44093%
Claude 4 Sonnet (Non-reasoning)Q:-0.3
$6.56+8739%
Performance
244
tokens/sec
Faster than 94% of models
0.51
seconds
Faster than 81% of models
8.69
seconds
Faster than 41% of models
Market Median
86 tok/s
185% faster
Median TTFT
1.07s
53% faster
Throughput/Dollar
3292
tok/s per $/1M
Speed Comparison
Qwen3.5 Omni Flash
244 tok/s-0%
gpt-oss-120B (low)
254 tok/s+4%
Google: Gemini 2.5 Flash Lite
259 tok/s+6%
Context Window
131K
tokens
Larger than 33% of models
Max Output
131K
tokens
100% of context
Benchmarks
MMLU-Pro
80.8%
GPQA Diamond
78.2%
HLE
18.5%
LiveCodeBench
87.8%
SciCode
38.9%
TerminalBench Hard
23.5%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
93.4%
IFBench
69.0%
Long Context Recall
50.7%
Tau2
65.8%
Market AverageTop Score
Open Source
apache-2.0120BGGUF / GPTQ / AWQ
Downloads
4.4M
Likes
4.8K
VRAM (FP16)
Multi-GPU
GPU
8x A100 / H100
