Skip to content

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

fix(llm-info): correct AWS Bedrock Claude model IDs (#9299)

Shahmir Varqha64fcbc27bd80
diff --git a/packages/llm-info/data/models.yml b/packages/llm-info/data/models.yml
index 06929732f0..1366884fb4 100644
--- a/packages/llm-info/data/models.yml
+++ b/packages/llm-info/data/models.yml
@@ -136,16 +136,31 @@
thinking: false
# Bedrock
+# To verify/update Bedrock model IDs, see https://github.com/marimo-team/marimo/issues/9280
+
+- name: Claude 4.7 Opus (Bedrock)
+ model: global.anthropic.claude-opus-4-7
+ description: Latest Opus model, strongest for coding and long-running professional tasks
+ providers: [bedrock]
+ roles: [chat, edit]
+ thinking: true
+
+- name: Claude 4.6 Sonnet (Bedrock)
+ model: global.anthropic.claude-sonnet-4-6
+ description: Most capable Sonnet-class model, with frontier performance across coding, agents, and professional work
+ providers: [bedrock]
+ roles: [chat, edit]
+ thinking: true
- name: Claude 4.6 Opus (Bedrock)
- model: global.anthropic.claude-opus-4-6-20260206-v1:0
+ model: global.anthropic.claude-opus-4-6-v1
description: Strongest model for coding and long-running professional tasks
providers: [bedrock]
roles: [chat, edit]
thinking: true
- name: Claude 4.5 Opus (Bedrock)
- model: global.anthropic.claude-opus-4-5-20251120-v1:0
+ model: global.anthropic.claude-opus-4-5-20251101-v1:0
description: Frontier reasoning model optimized for complex software engineering
providers: [bedrock]
roles: [chat, edit]
@@ -159,7 +174,7 @@
thinking: true
- name: Claude 4.5 Haiku (Bedrock)
- model: global.anthropic.claude-haiku-4-5-latest-v1:0
+ model: global.anthropic.claude-haiku-4-5-20251001-v1:0
description: Most efficient model, delivering near-frontier intelligence at a fraction of the cost
providers: [bedrock]
roles: [chat, edit]