Refresh MiniMax M3 model params#1374
Conversation
|
📝 WalkthroughWalkthroughThis PR adds the "MiniMax-M3" model to the minimax and minimax-cn provider model lists, updates registry doc URLs from quickstart to API reference overview, extends a resolver test, and updates provider documentation with new pricing and models tables. ChangesMiniMax-M3 Model Addition
Estimated code review effort: 1 (Trivial) | ~5 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ 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 |
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@packages/core/src/registries/model-provider-registry.generated.ts`:
- Around line 322-328: The generated MiniMax China provider metadata is out of
sync with the runtime registry. Update the `minimax-cn` entry in
`model-provider-registry.generated.ts` to match `model-provider-registry.ts`,
including the transport package and base URL used by the `minimax-cn` provider
definition. Keep the `id`, `name`, `env`, and other shared fields aligned, and
ensure the generated registry reflects the same `@ai-sdk/openai-compatible` and
`/v1` configuration as the runtime source.
In `@website/models-docs/providers/minimax-cn.md`:
- Around line 39-43: The MiniMax-M3 pricing table is incomplete and only
reflects one rate set, so update the pricing details in the MiniMax provider
docs to include the full split for the ≤512K and 512K~1M tiers. Use the existing
pricing section in the MiniMax docs and the MiniMax-M3 row to add the missing
tiered input/output/cache rates so long-context costs are represented
accurately.
In `@website/models-docs/providers/minimax.md`:
- Around line 41-45: The MiniMax-M3 pricing table is incomplete because it only
lists a single rate set and omits the separate ≤512K and 512K~1M tiers, so
update the pricing section in minimax.md to reflect the full M3 split shown on
the MiniMax pay-as-you-go page. Keep the existing MiniMax-M3 row structure, but
add the distinct tiered pricing entries with the correct input/output/cache
values so long-context usage is represented accurately.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 7d71f729-2073-4a1a-addd-7fda9a4c49e8
📒 Files selected for processing (6)
packages/core/src/registries/model-provider-registry-minimax.spec.tspackages/core/src/registries/model-provider-registry.generated.tspackages/core/src/registries/model-provider-registry.tspackages/core/src/registries/model-provider-types.generated.tswebsite/models-docs/providers/minimax-cn.mdwebsite/models-docs/providers/minimax.md
| "minimax-cn": { | ||
| id: "minimax-cn", | ||
| name: "MiniMax (China)", | ||
| npm: "@ai-sdk/anthropic", | ||
| api: "https://api.minimaxi.com/anthropic/v1", | ||
| env: ["MINIMAX_API_KEY"], | ||
| doc: "https://platform.minimaxi.com/docs/guides/quickstart", | ||
| doc: "https://platform.minimaxi.com/docs/api-reference/api-overview", |
There was a problem hiding this comment.
🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win
Align the generated MiniMax China entry with the runtime registry.
model-provider-registry.generated.ts still routes minimax-cn through @ai-sdk/anthropic and /anthropic/v1, but model-provider-registry.ts now uses @ai-sdk/openai-compatible and /v1. That leaves the generated metadata and runtime registry out of sync, so consumers can resolve the same provider through different transports. Please regenerate or update this entry so both files agree.
Suggested alignment
- npm: "`@ai-sdk/anthropic`",
- api: "https://api.minimaxi.com/anthropic/v1",
+ npm: "`@ai-sdk/openai-compatible`",
+ api: "https://api.minimaxi.com/v1",📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| "minimax-cn": { | |
| id: "minimax-cn", | |
| name: "MiniMax (China)", | |
| npm: "@ai-sdk/anthropic", | |
| api: "https://api.minimaxi.com/anthropic/v1", | |
| env: ["MINIMAX_API_KEY"], | |
| doc: "https://platform.minimaxi.com/docs/guides/quickstart", | |
| doc: "https://platform.minimaxi.com/docs/api-reference/api-overview", | |
| "minimax-cn": { | |
| id: "minimax-cn", | |
| name: "MiniMax (China)", | |
| npm: "`@ai-sdk/openai-compatible`", | |
| api: "https://api.minimaxi.com/v1", | |
| env: ["MINIMAX_API_KEY"], | |
| doc: "https://platform.minimaxi.com/docs/api-reference/api-overview", |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@packages/core/src/registries/model-provider-registry.generated.ts` around
lines 322 - 328, The generated MiniMax China provider metadata is out of sync
with the runtime registry. Update the `minimax-cn` entry in
`model-provider-registry.generated.ts` to match `model-provider-registry.ts`,
including the transport package and base URL used by the `minimax-cn` provider
definition. Keep the `id`, `name`, `env`, and other shared fields aligned, and
ensure the generated registry reflects the same `@ai-sdk/openai-compatible` and
`/v1` configuration as the runtime source.
| ## Pricing | ||
|
|
||
| | Model | Input | Output | Cache read | Cache write | | ||
| |---|---:|---:|---:|---:| | ||
| | MiniMax-M3 | $0.60 / 1M tokens | $2.40 / 1M tokens | $0.12 / 1M tokens | Not listed | |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
Document the full M3 pricing split.
The current MiniMax pay-as-you-go page lists separate ≤512K and 512K~1M M3 pricing tiers, but this table only shows one rate set, so long-context usage will be underquoted. (platform.minimax.io)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@website/models-docs/providers/minimax-cn.md` around lines 39 - 43, The
MiniMax-M3 pricing table is incomplete and only reflects one rate set, so update
the pricing details in the MiniMax provider docs to include the full split for
the ≤512K and 512K~1M tiers. Use the existing pricing section in the MiniMax
docs and the MiniMax-M3 row to add the missing tiered input/output/cache rates
so long-context costs are represented accurately.
| ## Pricing | ||
|
|
||
| | Model | Input | Output | Cache read | Cache write | | ||
| |---|---:|---:|---:|---:| | ||
| | MiniMax-M3 | $0.60 / 1M tokens | $2.40 / 1M tokens | $0.12 / 1M tokens | Not listed | |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟠 Major | ⚡ Quick win
Document the full M3 pricing split.
The current MiniMax pay-as-you-go page lists separate ≤512K and 512K~1M M3 pricing tiers, but this table only shows one rate set, so long-context usage will be underquoted. (platform.minimax.io)
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@website/models-docs/providers/minimax.md` around lines 41 - 45, The
MiniMax-M3 pricing table is incomplete because it only lists a single rate set
and omits the separate ≤512K and 512K~1M tiers, so update the pricing section in
minimax.md to reflect the full M3 split shown on the MiniMax pay-as-you-go page.
Keep the existing MiniMax-M3 row structure, but add the distinct tiered pricing
entries with the correct input/output/cache values so long-context usage is
represented accurately.
|
Thank you so much @octo-patch |
2 participants
Reason: MiniMax provider docs and generated registry stop at M2.x/M2.7; add M3 and refresh pricing/context/base URL.
Summary
Test plan
git add -A -N && git diff HEAD | grep -E "$SECRET_RE"pnpm --dir /root/octopatch-4/work/repos/VoltAgent_voltagent install --frozen-lockfile(failed because the default pnpm required Node 22.13 while the runner has Node 20.20.2)corepack prepare pnpm@8.10.5 --activate && pnpm --dir /root/octopatch-4/work/repos/VoltAgent_voltagent install --frozen-lockfile --registry=https://registry.npmjs.org --reporter=append-only(failed with ENOSPC during dependency linking)Summary by cubic
Adds MiniMax-M3 to the MiniMax model registry for
minimaxandminimax-cn, updates tests, and makes M3 the default in docs. Refreshes provider doc links to the current API reference and updates pricing/context details.Written for commit 8703987. Summary will update on new commits.
Summary by CodeRabbit
New Features
Documentation
Tests