Skip to content

docs: add MiniMax-M3 and update minimax default model#1335

Open
octo-patch wants to merge 3 commits into
VoltAgent:mainfrom
octo-patch:feature/upgrade-minimax-m3
Open

docs: add MiniMax-M3 and update minimax default model#1335
octo-patch wants to merge 3 commits into
VoltAgent:mainfrom
octo-patch:feature/upgrade-minimax-m3

Conversation

@octo-patch
Copy link
Copy Markdown
Contributor

@octo-patch octo-patch commented Jun 2, 2026

Summary

  • Add MiniMax-M3 (latest flagship) to the minimax and minimax-cn provider docs and use it as the default in the quickstart code samples.
  • Drop the older MiniMax-M2.5 / M2.5-highspeed / M2.1 / M2 rows from the model tables since they are no longer recommended for new integrations.
  • Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as previous-generation options.
  • Update the provider unit tests to use MiniMax-M3 as the default model and assert that M3, M2.7, and M2.7-highspeed all resolve through @ai-sdk/openai-compatible.

The auto-generated model-provider-registry.generated.ts and model-provider-types.generated.ts are intentionally left alone — the existing EXTRA_PROVIDER_REGISTRY overrides take care of the runtime registration regardless of which models models.dev currently lists, so this PR only touches the user-facing docs and tests.

Test plan

  • pnpm vitest run src/registries/model-provider-registry-minimax.spec.ts passes (8/8) inside packages/core.
  • npx biome check clean on the modified spec file.
  • npx prettier --check clean on the modified markdown after applying prettier --write.

Summary by cubic

Make MiniMax-M3 the default model for minimax and minimax-cn, update quickstart samples and provider tests, and remove M2.5/M2.1/M2 from docs while keeping M2.7 and M2.7-highspeed as previous-gen options. Tests confirm M3, M2.7, and M2.7-highspeed resolve via @ai-sdk/openai-compatible; no runtime registry changes.

  • Bug Fixes
    • Corrected MiniMax context windows in docs: M3 = 512K, M2.7/M2.7-highspeed = 192K.

Written for commit 3b11827. Summary will update on new commits.

Review in cubic

Summary by CodeRabbit

  • New Features

    • Added support for the MiniMax-M3 model and made M3 the default MiniMax model.
  • Documentation

    • Updated MiniMax and MiniMax (China) docs and examples to show MiniMax-M3 as default and refreshed the supported models table; older variants (M2.5, M2.1, M2) removed from public docs.

MiniMax-M3 is the latest flagship model. Add it to the provider docs,
make it the default in the quickstart examples for minimax and
minimax-cn, and remove the older M2.5/M2.1/M2 variants that are no
longer recommended for new integrations. Keep M2.7 and
M2.7-highspeed as previous-generation options.

Update the provider unit tests to use M3 as the default and verify
that M3, M2.7, and M2.7-highspeed all resolve through the
@ai-sdk/openai-compatible adapter.

Signed-off-by: Octopus <octopus@github.com>
@changeset-bot
Copy link
Copy Markdown

changeset-bot Bot commented Jun 2, 2026

🦋 Changeset detected

Latest commit: 3fa3c24

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package
Name Type
@voltagent/core Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai Bot commented Jun 2, 2026

Review Change Stack

📝 Walkthrough

Walkthrough

This PR updates the MiniMax provider default from MiniMax-M2.7 to MiniMax-M3 across tests, provider documentation (standard and China), and a changeset entry; supported model lists are reduced to MiniMax-M3, MiniMax-M2.7, and MiniMax-M2.7-highspeed.

Changes

MiniMax-M3 Default Model Update

Layer / File(s) Summary
Release notes for MiniMax-M3 addition
.changeset/MiniMax-m3-update.md
Changeset entry documents the @voltagent/core patch release adding MiniMax-M3 and switching the default model.
Registry test updates for MiniMax-M3 default
packages/core/src/registries/model-provider-registry-minimax.spec.ts
Registry tests now resolve minimax to MiniMax-M3 in basic loading, China provider, MINIMAX_BASE_URL override, and missing MINIMAX_API_KEY failure; tested variant list changed to MiniMax-M3, MiniMax-M2.7, and MiniMax-M2.7-highspeed.
Provider documentation updates for MiniMax-M3
website/models-docs/providers/minimax-cn.md, website/models-docs/providers/minimax.md
Quick-start examples now use minimax-cn/MiniMax-M3 and minimax/MiniMax-M3; model tables trimmed to MiniMax-M3, MiniMax-M2.7, and MiniMax-M2.7-highspeed.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

  • VoltAgent/voltagent#1167: Related updates to MiniMax provider tests and documentation concerning MiniMax model-resolution and defaults.

Poem

🐰 A little rabbit hops with glee,
M3 now leads the MiniMax marquee,
Tests and docs in tidy rows,
A gentle change the garden knows.

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The PR title directly reflects the main changes: adding MiniMax-M3 documentation and updating the minimax default model across all modified files.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
Description check ✅ Passed The pull request description is comprehensive and follows the template structure with clear sections covering current behavior, new behavior, testing details, and implementation notes.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link
Copy Markdown
Contributor

@cubic-dev-ai cubic-dev-ai Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No issues found across 4 files

Re-trigger cubic

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant