openai

GPT OSS 120B

gpt-oss

Open GPT reasoning model for self-hosted agents and controllable deployments

ReasoningTool CallingStructured OutputOpen Weights

Context Window

131K

Max Output

33K

Temperature

Yes

Open Weights

Yes

Knowledge Cutoff

N/A

Released

2025-08-05

Last Updated

2025-08-05

Modalities

Input:Text
→
Output:Text

Available Providers (23)

ProviderInput /1MOutput /1MCache Read /1MCache Write /1MReasoningStatus
STACKITSTACKITRp 9.486Rp 13.602——effort—
Vercel AI GatewayVercel AI GatewayRp 1.790Rp 8.949——effort—
submodelsubmodelRp 1.790Rp 8.949——✓—
Hugging FaceHugging FaceRp 4.475Rp 12.349——effort—
NovitaAINovitaAIRp 895Rp 4.475——effort—
Nebius Token FactoryNebius Token FactoryRp 2.685Rp 10.738Rp 269Rp 3.222effort—
Berget.AIBerget.AIRp 3.938Rp 14.854——effort—
GroqGroqRp 2.685Rp 10.738Rp 1.343—effort—
NEAR AI CloudNEAR AI CloudRp 2.685Rp 9.843——effort—
AbacusAbacusRp 1.432Rp 7.875——effort—
CloudFerro SherlockCloudFerro SherlockRp 52.258Rp 52.258——effort—
Deep InfraDeep InfraRp 698Rp 3.043——effort—
NvidiaNvidiaGratisGratis——effort—
evrocevrocRp 4.117Rp 16.465——effort—
SiliconFlowSiliconFlowRp 895Rp 8.054——budget_tokens—
IO.NETIO.NETRp 716Rp 7.159Rp 358Rp 1.432——
Weights & BiasesWeights & BiasesRp 2.685Rp 10.738——✓—
Kilo GatewayKilo GatewayRp 698Rp 3.401——effort—
Together AITogether AIRp 2.685Rp 10.738——effort—
OpenRouterOpenRouterRp 537Rp 2.685——effort—
FastRouterFastRouterRp 2.685Rp 10.738——effort—
BasetenBasetenRp 1.790Rp 8.949——effort—
NanoGPTNanoGPTRp 895Rp 4.475——effort—