gpt-oss-120b

OpenAI · Active · available in 11 of 16 regions

Batch inferenceStreaming Tool useVisionPrompt cachingEmbeddingsFine-tuning
Context window
Max output
Input / 1M
$0.150
us-east-1
Output / 1M
$0.600

Model & inference profile IDs

Base model ID — direct on-demand invoke

Pricing by region

USD per 1M tokens
Region Input Output Cache read Cache write Batch in Batch out Source
us-east-1 US East (N. Virginia) $0.150 $0.600 $0.075 $0.300 API
us-east-2 US East (Ohio) $0.150 $0.600 $0.075 $0.300 API
us-west-2 US West (Oregon) $0.150 $0.600 $0.075 $0.300 API
eu-west-1 EU (Ireland) $0.180 $0.700 $0.090 $0.350 API
eu-west-2 EU (London) $0.230 $0.930 $0.120 $0.470 API
eu-central-1 EU (Frankfurt) $0.200 $0.790 $0.100 $0.400 API
eu-north-1 EU (Stockholm) $0.150 $0.600 $0.075 $0.300 API
ap-southeast-2 Asia Pacific (Sydney) $0.154 $0.618 $0.077 $0.309 API
ap-northeast-1 Asia Pacific (Tokyo) $0.180 $0.730 $0.090 $0.360 API
ap-south-1 Asia Pacific (Mumbai) $0.180 $0.710 $0.090 $0.350 API
sa-east-1 South America (Sao Paulo) $0.180 $0.730 $0.090 $0.360 API

Region availability

TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.

Common questions

How much does gpt-oss-120b cost on Amazon Bedrock?
$0.150 per 1M input tokens and $0.600 per 1M output tokens in us-east-1.
Which AWS regions support gpt-oss-120b?
11 of 16 regions: us-east-1, us-east-2, us-west-2, eu-west-1, eu-west-2, eu-central-1, eu-north-1, ap-southeast-2, ap-northeast-1, ap-south-1, sa-east-1.
What is the model ID for gpt-oss-120b on Bedrock?
openai.gpt-oss-120b-1:0.

Other OpenAI models