Changelog

OpenAI GPT OSS Models via Bedrock: Access Open-Source Models Through AWS

‍You can now use OpenAI's open-source models on Relevance via our partner AWS Bedrock!

OpenAI GPT OSS models via Bedrock gives you seamless access to gpt-oss-120b and gpt-oss-20b. You can also bring your own Bedrock deployment by configuring Bedrock credentials in Relevance. This integration provides enterprise-grade reliability while maintaining the performance benefits of OpenAI's open-source offerings.

➡️ Doesn't use OpenAI API keys – Use your existing AWS Bedrock configuration if you're bringing your own deployment

➡️ Access to multiple model sizes – Choose between gpt-oss-120b and gpt-oss-20b based on your needs‍

➡️ Cost-optimized options – Benefit from low credit consumption at just 0.23 credits per 1000 tokens‍

➡️ Enterprise-ready performance – Achieve near-parity with OpenAI o4-mini on core reasoning benchmarks

➡️ Generous context windows – Work with up to 128,000 tokens for complex tasks

With OpenAI GPT OSS Models via Bedrock, you can leverage powerful open-source AI capabilities through the security and reliability of AWS infrastructure, giving your team more deployment options without sacrificing performance.

To access these models, simply select "OpenAI" in the model selection interface and choose the Bedrock-powered OSS model that fits your performance needs and budget.

Start building with OpenAI's open-source models on AWS Bedrock today!