OpenAI models on Amazon Bedrock
8 OpenAI models available through Bedrock, with price per 1M tokens, context window and region coverage.
| Model | Context | Input | Output | Regions |
|---|---|---|---|---|
| GPT OSS Safeguard 120B openai.gpt-oss-safeguard-120b | — | $0.150 | $0.600 | On-demand 10 Inference profile only 0 |
| GPT OSS Safeguard 20B openai.gpt-oss-safeguard-20b | — | $0.070 | $0.200 | On-demand 10 Inference profile only 0 |
| GPT-5.6 Luna openai.gpt-5.6-luna | 1M | $0.200 | $1.20 | On-demand 0 Inference profile only 28 |
| GPT-5.6 Sol openai.gpt-5.6-sol | 1M | $4.00 | $20.00 | On-demand 0 Inference profile only 28 |
| GPT-5.6 Terra openai.gpt-5.6-terra | 1M | $2.00 | $12.00 | On-demand 0 Inference profile only 28 |
| GPT-6 Astra openai.gpt-6-astra | 1.1M | $10.00 | $50.00 | On-demand 0 Inference profile only 31 |
| gpt-oss-120b openai.gpt-oss-120b-1:0 | — | $0.150 | $0.600 | On-demand 13 Inference profile only 0 |
| gpt-oss-20b openai.gpt-oss-20b-1:0 | — | $0.070 | $0.300 | On-demand 13 Inference profile only 0 |
Common questions
- Which OpenAI model is cheapest on Amazon Bedrock?
- GPT OSS Safeguard 20B at $0.070 per 1M input tokens in us-east-1, against $0.200 per 1M output tokens.
- Which OpenAI model is available in the most AWS regions?
- GPT-6 Astra, callable in 31 of the 31 regions tracked here — 0 on-demand and 31 through a cross-region inference profile.
- Which OpenAI model has the largest context window on Bedrock?
- GPT-6 Astra, with a 1.1M-token context window.