t1128: update model registry with current Anthropic model IDs#1712
t1128: update model registry with current Anthropic model IDs#1712marcusquinn merged 3 commits intomainfrom
Conversation
- claude-opus-4 -> claude-opus-4-6 ($15/$75 -> $5/$25 per MTok) - claude-sonnet-4 -> claude-sonnet-4-6 (pricing unchanged) - claude-haiku-3.5 -> claude-haiku-4-5 ($0.80/$4 -> $1/$5 per MTok) - Update model-registry.db: models + subagent_models tables - Fix opus.md: model field was claude-opus-4-20250514, now claude-opus-4-6 - Fix haiku.md: model field was claude-3-5-haiku-20241022, now claude-haiku-4-5-20251001 - Regenerate MODELS.md from updated registry - Source: https://docs.anthropic.com/en/docs/about-claude/models/overview
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. WalkthroughThis change updates Claude model identifiers and associated metadata across the framework from legacy versions (opus-4, sonnet-4, haiku-3.5) to newer releases (opus-4-6, sonnet-4-6, haiku-4-5), refreshing pricing, context limits, cost multipliers, tier mappings, and task recommendations throughout helper scripts and documentation. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Summary of ChangesHello @marcusquinn, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request updates the internal model registry and associated documentation to align with the current Anthropic model IDs and their respective pricing structures. The changes ensure that the system uses the most up-to-date model identifiers and cost information, impacting model recommendations and pricing displays throughout the application. This update improves accuracy and consistency with official Anthropic documentation. Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Wed Feb 18 17:08:25 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request updates the Anthropic model IDs and their associated pricing across several files, including a helper script and documentation. The changes are consistent with the latest information from Anthropic. However, I've noticed a couple of inconsistencies in the auto-generated MODELS.md file where the relative cost for the updated haiku and opus tiers appear to be stale after the pricing changes. Please see my detailed comments.
MODELS.md
Outdated
| | Tier | Primary Model | Relative Cost | | ||
| |------|---------------|---------------| | ||
| | haiku | claude-3-5-haiku | ~0.25x | | ||
| | haiku | claude-haiku-4-5 | ~0.25x | |
There was a problem hiding this comment.
The relative cost for the haiku tier appears to be outdated. With the new claude-haiku-4-5 pricing ($1/$5 per MTok) and sonnet baseline pricing ($3/$15 per MTok), the cost ratio is approximately 0.33x. The table still shows ~0.25x, which was the ratio for the previous claude-3-5-haiku model.
MODELS.md
Outdated
| | sonnet | claude-sonnet-4-6 | 1x (baseline) | | ||
| | pro | gemini-2.5-pro-preview-06-05 | ~1.5x | | ||
| | opus | claude-opus-4 | ~3x | | ||
| | opus | claude-opus-4-6 | ~3x | |
There was a problem hiding this comment.
The relative cost for the opus tier seems incorrect. With the new claude-opus-4-6 pricing ($5/$25 per MTok) and sonnet baseline pricing ($3/$15 per MTok), the cost ratio is approximately 1.7x. The table still shows ~3x.
This also conflicts with the opus.md file, which was correctly updated in this PR to mention a 1.7x cost ratio relative to sonnet.
- haiku: ~0.25x -> ~0.33x (claude-haiku-4-5 $1/$5 vs sonnet $3/$15) - opus: ~3x -> ~1.7x (claude-opus-4-6 $5/$25 vs sonnet $3/$15) - Regenerate MODELS.md with corrected values - Addresses Gemini code review feedback on PR #1712
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Wed Feb 18 17:36:12 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Wed Feb 18 17:39:56 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
.agents/scripts/compare-models-helper.sh (1)
296-298:⚠️ Potential issue | 🟡 MinorStale
Last updateddates in three user-facingechostrings.The code comment on line 146 was correctly updated to
2026-02-18, but the threeechostatements that users actually see weren't touched:
- Line 298:
"Prices: USD per 1M tokens. Last updated: 2025-02-08."- Line 536:
"Last updated: 2025-02-08. Run /compare-models for live pricing check."- Line 1025:
"Data is embedded in this script. Last updated: 2025-02-08."These will show an out-of-date timestamp to anyone running
list,pricing, orhelp.📅 Proposed fix — sync the three displayed dates
- echo "Prices: USD per 1M tokens. Last updated: 2025-02-08." + echo "Prices: USD per 1M tokens. Last updated: 2026-02-18."- echo "Last updated: 2025-02-08. Run /compare-models for live pricing check." + echo "Last updated: 2026-02-18. Run /compare-models for live pricing check."- echo "Data is embedded in this script. Last updated: 2025-02-08." + echo "Data is embedded in this script. Last updated: 2026-02-18."🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.agents/scripts/compare-models-helper.sh around lines 296 - 298, Update the three user-facing echo strings that still show "Last updated: 2025-02-08" to the correct date "Last updated: 2026-02-18": find and replace the echo statements containing "Prices: USD per 1M tokens. Last updated: 2025-02-08.", "Last updated: 2025-02-08. Run /compare-models for live pricing check." and "Data is embedded in this script. Last updated: 2025-02-08." with the same messages but using 2026-02-18; ensure only the displayed strings are changed and formatting/whitespace around the echo calls remains unchanged.MODELS.md (1)
78-82:⚠️ Potential issue | 🟡 MinorContest results section still references the old model names
claude-opus-4/claude-sonnet-4.The Quality Scores table was not regenerated against the new model IDs because the scoring DB entries were recorded under the old names. Anyone glancing at MODELS.md will see the catalog claim
claude-opus-4-6while the contest section still namesclaude-opus-4, creating a confusing split view.Since
MODELS.mdis auto-generated from live DBs, the fix must happen at the data layer: thecomparisonsandresponsestables inresponse-scoring.dbneed a targeted rename of the old model IDs, or a post-generation sed pass to normalise well-known aliases. A migration script or a note in the PR description would help track this gap.Would you like me to draft a one-off SQLite migration snippet to rename
claude-opus-4→claude-opus-4-6andclaude-sonnet-4→claude-sonnet-4-6in the scoring DB, or open a tracking issue for this cleanup?🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@MODELS.md` around lines 78 - 82, The MODELS.md contest table shows outdated model IDs because the scoring DB recorded entries under old names; run a targeted data migration to update model IDs in the scoring DB: open response-scoring.db and UPDATE the comparisons and responses tables replacing 'claude-opus-4' → 'claude-opus-4-6' and 'claude-sonnet-4' → 'claude-sonnet-4-6' (ensure you update any model_id/model_name columns and related indexes/foreign keys), or add a post-generation normalisation step that maps known aliases before writing MODELS.md so generation uses the canonical IDs; include the migration SQL or alias map in the PR or add a one-off script and document it for audit.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In @.agents/scripts/compare-models-helper.sh:
- Around line 296-298: Update the three user-facing echo strings that still show
"Last updated: 2025-02-08" to the correct date "Last updated: 2026-02-18": find
and replace the echo statements containing "Prices: USD per 1M tokens. Last
updated: 2025-02-08.", "Last updated: 2025-02-08. Run /compare-models for live
pricing check." and "Data is embedded in this script. Last updated: 2025-02-08."
with the same messages but using 2026-02-18; ensure only the displayed strings
are changed and formatting/whitespace around the echo calls remains unchanged.
In `@MODELS.md`:
- Around line 78-82: The MODELS.md contest table shows outdated model IDs
because the scoring DB recorded entries under old names; run a targeted data
migration to update model IDs in the scoring DB: open response-scoring.db and
UPDATE the comparisons and responses tables replacing 'claude-opus-4' →
'claude-opus-4-6' and 'claude-sonnet-4' → 'claude-sonnet-4-6' (ensure you update
any model_id/model_name columns and related indexes/foreign keys), or add a
post-generation normalisation step that maps known aliases before writing
MODELS.md so generation uses the canonical IDs; include the migration SQL or
alias map in the PR or add a one-off script and document it for audit.
1 participant
Updates Anthropic model IDs in the model registry to current versions per official docs.
Changes
claude-opus-4→claude-opus-4-6(pricing corrected: $15/$75 → $5/$25 per MTok)claude-sonnet-4→claude-sonnet-4-6(pricing unchanged)claude-haiku-3.5→claude-haiku-4-5(pricing updated: $0.80/$4 → $1/$5 per MTok)model-registry.db: bothmodelsandsubagent_modelstablesopus.mdfrontmatter: wasclaude-opus-4-20250514, nowclaude-opus-4-6haiku.mdfrontmatter: wasclaude-3-5-haiku-20241022, nowclaude-haiku-4-5-20251001MODELS.mdfrom updated registryVerification
compare-models-helper.shgenerate-models-md.shran successfully, MODELS.md shows correct IDsRef #1690
Summary by CodeRabbit