Providers & Models
AWS Bedrock
Connect an AWS account to Multi-Router and route requests to the models AWS Bedrock serves.
AWS Bedrock is Amazon's managed model platform, serving models from Anthropic, Amazon, Meta, Mistral, DeepSeek, Qwen, OpenAI, Moonshot, Nvidia and Z.ai in AWS regions under your AWS account. Multi-Router calls Bedrock with a provider key that holds AWS credentials and a default region. AWS bills usage to the account that owns the credentials, and Multi-Router records the cost of each request at the catalog price of the region and inference scope that served it.
Preparing your AWS account
The AWS account that serves requests needs model access and an IAM identity whose credentials Multi-Router uses:
- Bedrock enables serverless models automatically on first use. Before the first call to an Anthropic model, submit Anthropic's one-time use-case form in the Bedrock console. Models sold through AWS Marketplace subscribe on first use, so the identity that makes the first call needs
aws-marketplace:Subscribeandaws-marketplace:ViewSubscriptions, or an administrator with those permissions calls each model once. - Create an IAM user for Multi-Router and attach a policy that allows
bedrock:InvokeModelandbedrock:InvokeModelWithResponseStream, such as the policy below. To use a Bedrock API key, also allowbedrock:CallWithBearerToken. - Create the credential Multi-Router will use: an access key for the IAM user, or a long-term Bedrock API key.
These actions cover every request Multi-Router sends to Bedrock, including streaming. Requests through geo inference profiles are authorized against the profile and against the foundation model in every region of the geography, and requests through global profiles are also authorized against the region-less foundation model resource, which the policy lists. A service control policy that limits aws:RequestedRegion must allow every region of the geography for geo profiles, and the value unspecified for global profiles.
Adding a Bedrock provider key
A Bedrock provider key holds one set of AWS credentials and the AWS region requests go to by default. To add one, open LLM Provider Keys in the dashboard, add a key, select AWS Bedrock, and choose Access key (SigV4) or API key (bearer) at the top of the form:
| Field | Description |
|---|---|
| Name | Required, up to 80 characters. |
| AWS Region | The region requests go to when the router names none. |
| AWS Access Key ID | For Access key (SigV4): the access key id of the IAM user, 16 to 128 letters and digits. |
| Secret access key | For Access key (SigV4): the secret access key of the IAM user. For API key (bearer), the field reads Bedrock API key and holds the API key. |
| Session token | Optional, for Access key (SigV4) with temporary AWS credentials, up to 4,096 bytes. |
| Description | Optional. |
The key's region is one of us-east-1, us-east-2, us-west-2, ca-central-1, sa-east-1, eu-central-1, eu-west-1, eu-west-2, eu-west-3, eu-north-1, eu-south-1, ap-south-1, ap-southeast-1, ap-southeast-2, ap-northeast-1, ap-northeast-2 and ap-northeast-3, and a router can name any region the catalog lists for its variant. When the key is saved, Multi-Router checks the region, the access key id format and the session token length, and AWS checks the credentials on the first request. Multi-Router uses a Bedrock API key only in the key's region.
Temporary credentials with a session token expire, and AWS short-term Bedrock API keys last at most 12 hours, so long-running routers use an IAM user access key or a long-term Bedrock API key. The region and credentials of a saved key are fixed, and changing them means adding a new key; see Provider Key.
Regions and inference scopes
Each Bedrock request goes to one AWS region, which is the router's region or, when the router names none, the provider key's region. The router's variant then sets where inference runs: in_region keeps it in that region, geo keeps it in that region's geography, and global lets AWS run it in any region. A model not offered in the selected region and variant returns region_not_served with the regions where it is available. See Regions & Variants.
Models and features
Bedrock features depend on the model's publisher:
| Feature | Claude models | Other publishers |
|---|---|---|
| Streaming | Yes | Yes, for models whose catalog entry lists streaming |
| System prompts | Yes | Yes |
| Tools | Yes | Yes, for models whose catalog entry lists tools |
| Tool choice | Yes | Yes, for models whose catalog entry lists tools |
| Images | Yes | Models whose catalog entry lists image input, such as Amazon Nova, Llama 4 and Qwen3 VL |
| Reasoning | Yes, with thinking and budget_tokens on the Messages API | No |
| Prompt caching | Yes, with cache_control on the Messages API | No |
| Structured output | No | No |
| Sampling | temperature, top_p, top_k, stop sequences | temperature, top_p, stop sequences |
A request with a json_object or json_schema response format returns an error for every Bedrock model. Multi-Router downloads images sent as URLs and passes them to Bedrock as image data: an image URL must use HTTPS and return HTTP 200, with a PNG, JPEG, GIF or WebP content type, and an image of at most 5 MiB, within 10 seconds.
Errors and retries
Bedrock errors reach the caller as Multi-Router errors, with the AWS error in the response's upstream object. Multi-Router retries HTTP 429, 500, 502, 503, 504 and 529 responses, timeouts and connection failures, with exponential backoff and any whole-second retry delay AWS sends, within five minutes of the first attempt. Each attempt must receive a response within 120 seconds, so long outputs use streaming. When retries are exhausted, the request returns 429 upstream_rate_limit, or 502 upstream_server_error when the last attempt failed with a server error, with the upstream code max_attempts_exceeded.
| AWS error | Multi-Router error | Common cause |
|---|---|---|
ThrottlingException | 429 upstream_rate_limit after retries | Requests exceed the account quota for the model and region. |
ModelNotReadyException | 429 upstream_rate_limit after retries | The model is not yet ready to serve requests. |
InternalServerException | 502 upstream_server_error after retries | Bedrock had an internal error. |
ServiceUnavailableException | 502 upstream_server_error after retries | Bedrock is temporarily unavailable. |
ServiceQuotaExceededException | 402 upstream_insufficient_quota | The account has reached a Bedrock service quota. |
AccessDeniedException | 502 upstream_invalid_credentials | The IAM policy does not allow the action, or the model has not been enabled for the account. |
UnrecognizedClientException | 502 upstream_invalid_credentials | The access key or Bedrock API key is invalid. |
ExpiredTokenException | 502 upstream_invalid_credentials | The temporary credentials or session token have expired. |
ValidationException | 400 upstream_invalid_request | Bedrock rejected the request, such as a parameter the model does not accept or a prompt longer than its context window. |
ResourceNotFoundException | 400 upstream_model_not_found | The model or inference profile is not available in the region. |
ModelTimeoutException | 408 upstream_other | The model timed out while processing the request. |
ModelErrorException | 424 upstream_other | The model failed while processing the request. |
Errors that occur after a streaming response has started are returned as an error event in the stream.
Pricing
Bedrock prices differ by region and inference scope. Multi-Router records the cost of each request at the price of the region and variant that served it, including separate rates for prompt cache reads and cache writes on Claude models, and sends requests on Bedrock's standard on-demand tier. See Model Catalog.
Claude Code on Bedrock
A Claude Proxy on a Bedrock route serves Claude Code in its Bedrock mode. The Claude Proxy routes are Bedrock (Global), Bedrock (Geo) and Bedrock (In-region), each with a region set on the Claude Proxy, and the route and region decide where inference runs, whatever inference profile prefix the client sends. Multi-Router forwards the request body unchanged, replaces the model id with the route's id for the proxy's region, and signs the request with the organization's Bedrock key. Claude Proxy requests are sent to Bedrock once, without retries, and Bedrock's status and error body are returned to the client unchanged. The dashboard generates the environment for each developer:
See Agents & Editors.