Provider: AWS Bedrock
Provider: AWS Bedrock
Use Respan Gateway to call AWS Bedrock models (Anthropic Claude on Bedrock, Meta Llama, Amazon Nova, and the rest) while keeping unified observability (logs, cost, latency, reliability) in Respan.
Quick setup
Add credits (recommended)
Top up credits to pay through Respan. No AWS credentials required, Respan handles provider auth and billing.
Prefer to route through your own AWS account? See Use your own AWS Bedrock key.
Send your first request
Pick the integration that matches your stack. The base URL is https://api.respan.ai/api and the only key needed is your RESPAN_API_KEY.
AWS SDK
Vercel AI SDK
Respan API
Bedrock’s native AWS SDKs (boto3, AWS SDK for JS) talk to AWS endpoints directly. To route through Respan, point the OpenAI-compatible Chat Completions interface at the gateway. Install with pip install boto3 or npm install @aws-sdk/client-bedrock-runtime for native AWS calls, or pip install openai / npm install openai for the gateway path shown below.
More integrations
Bedrock models work with every Respan gateway integration:
Switch models
Change the model parameter to call any supported model through the same client. Use the bedrock/ prefix to disambiguate when routing across providers. Browse the full list on the Models page.
Use your own AWS Bedrock key (BYOK)
Credits are the default path. If you’d rather bill AWS directly, attach your own IAM credentials.
Global (UI)
Per-request (Code)
Override credentials per model (Optional)
Use credential_override when one model on a request should use a different AWS account or region than the default.
Log without proxying (Optional)
Already calling Bedrock directly? Send logs to Respan asynchronously to track cost, latency, and performance for those external calls.
See the logging guide for the full setup.