Hi everyone,
Our team is running LLM inference services for production agent applications. We are looking for long-term technical collaborators who have stable access to AWS Bedrock model endpoints.
Models we prioritize:
- Opus 5.5
- Fable 5.2
We care about stable throughput, reasonable rate limits (TPM/RPM), and consistent uptime for continuous token workloads. We follow usage-based settlement for our cooperation, and we can start with small-scale testing first to verify stability.
If you operate reliable Bedrock access and are open to long-term partnership, feel free to reach out via DEV connect. Please briefly share your available models, rate limits and your preferred cooperation terms in your message.
Thanks!
Top comments (0)