Amazon Bedrock
Route Pullfrog's model calls through Amazon Bedrock in your own AWS account. Use it to spend AWS credits or an enterprise AWS commitment, keep inference inside AWS for compliance, or use provisioned throughput you already pay for.
Setup
Store your AWS credential
In the Pullfrog console, click Set up on the Amazon Bedrock tile of the Providers card and save one of these:
- A Bedrock API key, created under API keys in the Bedrock console. It becomes
AWS_BEARER_TOKEN_BEDROCK. - An IAM access-key pair whose policy allows
bedrock:InvokeModelandbedrock:InvokeModelWithResponseStream.
You can store the credential as a GitHub Actions secret instead and map it in the workflow's env: block.
Set the region and model in your workflow
Add AWS_REGION and BEDROCK_MODEL_ID to the workflow's env: block. Neither is secret.
- name: Run agent
uses: pullfrog/pullfrog@v0
with:
prompt: ${{ inputs.prompt }}
env:
AWS_REGION: us-east-1
BEDROCK_MODEL_ID: us.anthropic.claude-opus-5-5
# only when the credential is a GitHub Actions secret
AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.AWS_BEARER_TOKEN_BEDROCK }}Submit the Anthropic use-case form
Anthropic models only: before the first call, submit the one-time use-case form in the Bedrock console. Open Model catalog, pick an Anthropic model, and complete the form.
Pick the model
Open the Model card's editor, choose Manual and pick Amazon Bedrock from the model menu.
Variables
| Name | Secret | Purpose |
|---|---|---|
AWS_BEARER_TOKEN_BEDROCK | Yes | Bedrock API key. Use this or the access-key pair. |
AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY | Yes | IAM access-key pair. |
AWS_SESSION_TOKEN | Yes | Optional. Needed only with temporary STS credentials. |
AWS_REGION | No | AWS region to call, for example us-east-1. |
BEDROCK_MODEL_ID | No | Exact Bedrock model ID. Pullfrog runs it as written and never upgrades it. |
CLAUDE_CODE_USE_MANTLE | No | Optional. Set to 1 to run Anthropic models on the Mantle endpoint. |
A credential stored in the console needs no env: line, because Pullfrog injects it into every run. A value set in the workflow wins over a stored one.
Model IDs
The model menu has a single Amazon Bedrock entry; BEDROCK_MODEL_ID names the actual model. Copy the ID from the Programmatic Access section of the model's card in Bedrock's model list.
us.anthropic.claude-opus-5-5 # Claude Opus 5.5, US cross-region inference profile
amazon.nova-pro-v1:0 # Amazon Nova Pro, in-region
openai.gpt-oss-120b-1:0 # gpt-oss-120b, in-regionCross-region inference profiles carry a geography prefix such as us., eu., jp., au. or global.. Pick the prefix that matches AWS_REGION, or use the bare in-region ID where the model card lists one. To change models, edit BEDROCK_MODEL_ID and commit.
Routing
Pullfrog reads the model ID to choose the agent:
- Anthropic models, whose ID contains an
anthropicsegment, run on Claude Code. Pullfrog setsCLAUDE_CODE_USE_BEDROCK=1for Claude Code. - Every other model runs on OpenCode's
amazon-bedrockprovider.
An application inference profile ARN routes to OpenCode unless its name contains an anthropic segment. For an Anthropic model behind such an ARN, set PULLFROG_AGENT: claude in the workflow env:.
Mantle endpoint
Pullfrog calls Bedrock's standard bedrock-runtime endpoint. A few models, such as Claude Mythos 5, run only on AWS's second endpoint, bedrock-mantle.
To run an Anthropic model on Mantle, set CLAUDE_CODE_USE_MANTLE and use the model's Mantle ID:
env:
AWS_REGION: us-east-1
BEDROCK_MODEL_ID: anthropic.claude-mythos-5
CLAUDE_CODE_USE_MANTLE: "1"Mantle changes four things:
- Credential. Use the same credential you stored for Amazon Bedrock. Mantle has its own IAM actions: grant
bedrock-mantle:CreateInference, plusbedrock-mantle:CallWithBearerTokenwhen the credential is a Bedrock API key. - Model ID. Copy it from the
bedrock-mantlerow of the model card's Programmatic Access table. A Mantle ID starts withanthropic.and has no geography prefix and no-v1:0-style suffix. WithCLAUDE_CODE_USE_MANTLEset, any ID of that shape goes to Mantle, and every other ID still goes tobedrock-runtime. One consequence:anthropic.claude-opus-5-5goes to Mantle even thoughbedrock-runtimeserves the same ID in-region ineu-west-2. - Region. Mantle has no cross-region inference profiles and serves each model in fewer regions, so check the model card's
bedrock-mantleavailability before choosingAWS_REGION. - Anthropic models only. Other models run on OpenCode through
bedrock-runtime, so the Amazon Bedrock option cannot reach a non-Anthropic model that only Mantle serves.
Troubleshooting
| Symptom | Fix |
|---|---|
"BEDROCK_MODEL_ID must be set when the model is bedrock/byok" | The repository uses Amazon Bedrock, but the workflow does not set BEDROCK_MODEL_ID. Add it to env:. |
| "Amazon Bedrock is missing required settings" | The message lists each missing value: the credential, AWS_REGION, or BEDROCK_MODEL_ID. |
AccessDeniedException on an Anthropic model | The account has not submitted the Anthropic use-case form. Submit it in the Bedrock console, then re-run. |
AccessDeniedException on another model | The IAM policy behind the access keys lacks bedrock:InvokeModel or bedrock:InvokeModelWithResponseStream for that model. |
ValidationException about the model ID | The ID is not valid in AWS_REGION. Check the model card's Programmatic Access section and match the geography prefix to the region. A model without on-demand throughput needs its inference profile ID. |
AccessDeniedException with a credential created for Mantle | Its IAM identity has only bedrock-mantle: permissions, and Pullfrog calls bedrock-runtime by default. Grant bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream, plus bedrock:CallWithBearerToken for a Bedrock API key, or run the model on the Mantle endpoint. |
| A model that only Mantle serves fails on its first call | CLAUDE_CODE_USE_MANTLE is not set, so the request went to bedrock-runtime. Add it to env:. |
403 from Mantle | An error naming a bedrock-mantle: action means the IAM identity lacks that action. An error that names no action means the AWS account has not been granted that model on Mantle. Contact your AWS account team. |

