Skip to content

AWS Bedrock Claude 3.7 and 4 Sonnet 'thinking' support #1162

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
+7 −0
Closed

AWS Bedrock Claude 3.7 and 4 Sonnet 'thinking' support #1162

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions docs/cody/capabilities/supported-models.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,10 @@ In addition, Sourcegraph Enterprise customers using GCP Vertex (Google Cloud Pla

<Callout type="info">Claude 3.7 Sonnet with thinking is not supported for BYOK deployments.</Callout>

#### Claude 3.7 Sonnet and Claude 4 Sonnet for AWS Bedrock

Cody's BYOK AWS Bedrock support can use Claude 3.7 Sonnet's **thinking mode**. Once enabled, Cody routes your prompts through Claude 3.7 Sonnet, using its expanded context window and advanced reasoning abilities to return noticeably smarter, more context-aware responses.

## Autocomplete

Cody uses a set of models for autocomplete which are suited for the low latency use case.
Expand Down
3 changes: 3 additions & 0 deletions docs/cody/enterprise/model-configuration.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,6 +228,9 @@ This field is an array of items, each with the following fields:
- `reasoningEffort`: Specifies the effort on reasoning for reasoning models (having `reasoning` capability). Supported values: `high`, `medium`, `low`. How this value is treated depends on the specific provider.
For example, for Anthropic models supporting thinking, `low` effort means that the minimum [`thinking.budget_tokens`](https://docs.anthropic.com/en/api/messages#body-thinking) value (1024) will be used. For other `reasoningEffort` values, the `contextWindow.maxOutputTokens / 2` value will be used.
For OpenAI reasoning models, the `reasoningEffort` field value corresponds to the [`reasoning_effort`](https://platform.openai.com/docs/api-reference/chat/create#chat-create-reasoning_effort) request body value.

<Callout type="note">If you are a Claude 3.0 user, you'll need to enable both the `reasoning` and `reasoningEffort` fields in order to get **thinking** support.</Callout>

- `serverSideConfig`: Additional configuration for the model. It can be one of the following:

- `awsBedrockProvisionedThroughput`: Specifies provisioned throughput settings for AWS Bedrock models with the following fields:
Expand Down