/ Claude Code v2.1.96

No new environment variables, commands, or configuration options were added in this release.
Users of AWS_BEARER_TOKEN_BEDROCK and CLAUDE_CODE_SKIP_BEDROCK_AUTH do not need to change their configuration; existing setups will continue to work as before.

How sure we are

One source agreesOne thing we can check says the same as this entry.

Anthropic's release notes agreeFixed Bedrock requests failing with 403 "Authorization header is missing" when using AWS_BEARER_TOKEN_BEDROCK or…

See this entry in the whole of v2.1.96 →

The build it came inv2.1.96

8 Apr 2026 · 3 entries, this one is #3.

Either side of it

v2.1.94Older
v2.1.97Newer

Open the release →

Names in this entry

envAWS_BEARER_TOKEN_BEDROCK
Amazon Bedrock API key for authentication (see Amazon Bedrock API keys)
envCLAUDE_CODE_SKIP_BEDROCK_AUTH
When true, Claude Code talks to Bedrock without looking up AWS credentials: its AWS SDK Bedrock clients use the smithy.api#noAuth auth scheme, and its Anthropic Bedrock client sends an Authorization header from the client's default headers (for example ANTHROPIC_CUSTOM_HEADERS) as its credential when one is present, or else is created with skipAuth; AWS_BEARER_TOKEN_BEDROCK still takes precedence. At startup it skips running the configured awsAuthRefresh and awsCredentialExport helpers, and the status panel shows AWS auth skipped.

Anthropic's note

Upstream's own release notes for v2.1.96 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Fixed Bedrock requests failing with 403 "Authorization header is missing" when using AWS_BEARER_TOKEN_BEDROCK or CLAUDE_CODE_SKIP_BEDROCK_AUTH (regression in 2.1.94)

Is this right?