S CostSaver
Sign in

gpt-oss-120b (batch)

LLM

by openai · openai-gpt-oss-120b

Context window

131K

Max output

118K

Providers

21

Best input

$0.0296

About this model

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...

Providers & prices

Provider Input $/MTok Output $/MTok Context
O OpenAI $0.0296 $0.136 131K
D DekaLLM $0.03 $0.18 131K
C CoreWeave $0.03 $0.17 131K
A AkashML $0.03 $0.17 131K
C Crusoe $0.05 $0.25 131K
M2 Mancer 2 $0.05 $0.3 131K
NA Novita AI $0.05 $0.25 131K
D DigitalOcean $0.06 $0.42 128K
G Google $0.09 $0.36 131K
P Parasail $0.1 $0.75 131K
B BaseTen $0.1 $0.5 128K
S SambaNova $0.14 $0.95 131K
TA Together AI $0.15 $0.6 131K
AB Amazon Bedrock $0.15 $0.6 131K
P Phala $0.15 $0.6 131K
S SiliconFlow $0.15 $0.6 131K
N Nebius $0.15 $0.6 131K
M Mara $0.15 $0.75 131K
G Groq $0.15 $0.6 131K
D DeepInfra $0.2 $0.95 131K
C Cerebras $0.35 $0.75 131K