Skip to content

Add MiniMax-M3 and MiniMax-M2.7 input token limits #25

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
octo-patch wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add MiniMax-M3 and MiniMax-M2.7 input token limits #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions packages/core/src/core/tokenLimits.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,6 +190,22 @@ describe('tokenLimit', () => {
});
});

describe('MiniMax', () => {
it('should return the correct limit for MiniMax-M3', () => {
expect(tokenLimit('MiniMax-M3')).toBe(1_000_000);
expect(tokenLimit('minimax-m3')).toBe(1_000_000);
expect(tokenLimit('minimax-m3-20250101')).toBe(1_000_000);
});
it('should return the correct limit for MiniMax-M2.7', () => {
expect(tokenLimit('MiniMax-M2.7')).toBe(204_800);
expect(tokenLimit('minimax-m2.7')).toBe(204_800);
});
it('should not fall back to the default for MiniMax models', () => {
expect(tokenLimit('MiniMax-M3')).not.toBe(DEFAULT_TOKEN_LIMIT);
expect(tokenLimit('MiniMax-M2.7')).not.toBe(DEFAULT_TOKEN_LIMIT);
});
});

describe('Other models', () => {
it('should return the correct limit for deepseek-r1', () => {
expect(tokenLimit('deepseek-r1')).toBe(131072);
Expand Down
10 changes: 10 additions & 0 deletions packages/core/src/core/tokenLimits.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,9 @@ const LIMITS = {
'1m': 1_048_576,
'2m': 2_097_152,
'10m': 10_485_760, // 10 million tokens
// MiniMax vendor-declared exact context windows (decimal, not power-of-two)
'minimax-m3': 1_000_000, // MiniMax-M3: 1,000,000 tokens (1M decimal)
'minimax-m2.7': 204_800, // MiniMax-M2.7: 204,800 tokens
// Output token limits (typically much smaller than input limits)
'4k': 4_096,
'8k': 8_192,
Expand Down Expand Up @@ -141,6 +144,13 @@ const PATTERNS: Array<[RegExp, TokenCount]> = [
// Generic vision-model: same as qwen-vl-max (128K token context)
[/^vision-model$/, LIMITS['128k']],

// -------------------
// MiniMax
// -------------------
// MiniMax-M3: 1,000,000-token context window (vendor-declared decimal).
[/^minimax-m2\.7.*$/, LIMITS['minimax-m2.7']], // more specific (dotted) first
[/^minimax-m3.*$/, LIMITS['minimax-m3']],

// -------------------
// ByteDance Seed-OSS (512K)
// -------------------
Expand Down