dka/LibreChat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

🤖 feat: Latest Grok Model Pricing & Context Rates (#10727)

Browse Source 
* 🤖 feat: Latest Grok Model Pricing & Context Rates

- Introduced 'grok-4-fast', 'grok-4-1-fast', and 'grok-code-fast' models with their respective prompt and completion rates.
- Enhanced unit tests to validate prompt and completion rates for the new models, including variations with prefixes.
- Updated token limits for the new models in the tokens utility, ensuring accurate handling in tests.

* 🔧 refactor: Optimize JSON Export Logic in useExportConversation Hook

Updated the export logic to create a Blob from the JSON string before downloading, improving compatibility and performance for file downloads. This change enhances the handling of deeply nested exports while maintaining the file size reduction achieved in previous updates.
This commit is contained in:
Danny Avila
2025-11-30 17:10:26 -05:00
committed by GitHub
parent 2ccaf6be6d
commit d7ce19e15a
5 changed files with 103 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
api/models/tx.js
View File

@@ -173,6 +173,9 @@ const tokenValues = Object.assign(
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
'grok-4': { prompt: 3.0, completion: 15.0 },
'grok-4-fast': { prompt: 0.2, completion: 0.5 },
'grok-4-1-fast': { prompt: 0.2, completion: 0.5 }, // covers reasoning & non-reasoning variants
'grok-code-fast': { prompt: 0.2, completion: 1.5 },
codestral: { prompt: 0.3, completion: 0.9 },
'ministral-3b': { prompt: 0.04, completion: 0.04 },
'ministral-8b': { prompt: 0.1, completion: 0.1 },

66
api/models/tx.spec.js
View File

@@ -1205,6 +1205,39 @@ describe('Grok Model Tests - Pricing', () => {
);
});
test('should return correct prompt and completion rates for Grok 4 Fast model', () => {
expect(getMultiplier({ model: 'grok-4-fast', tokenType: 'prompt' })).toBe(
tokenValues['grok-4-fast'].prompt,
);
expect(getMultiplier({ model: 'grok-4-fast', tokenType: 'completion' })).toBe(
tokenValues['grok-4-fast'].completion,
);
});
test('should return correct prompt and completion rates for Grok 4.1 Fast models', () => {
expect(getMultiplier({ model: 'grok-4-1-fast-reasoning', tokenType: 'prompt' })).toBe(
tokenValues['grok-4-1-fast'].prompt,
);
expect(getMultiplier({ model: 'grok-4-1-fast-reasoning', tokenType: 'completion' })).toBe(
tokenValues['grok-4-1-fast'].completion,
);
expect(getMultiplier({ model: 'grok-4-1-fast-non-reasoning', tokenType: 'prompt' })).toBe(
tokenValues['grok-4-1-fast'].prompt,
);
expect(getMultiplier({ model: 'grok-4-1-fast-non-reasoning', tokenType: 'completion' })).toBe(
tokenValues['grok-4-1-fast'].completion,
);
});
test('should return correct prompt and completion rates for Grok Code Fast model', () => {
expect(getMultiplier({ model: 'grok-code-fast-1', tokenType: 'prompt' })).toBe(
tokenValues['grok-code-fast'].prompt,
);
expect(getMultiplier({ model: 'grok-code-fast-1', tokenType: 'completion' })).toBe(
tokenValues['grok-code-fast'].completion,
);
});
test('should return correct prompt and completion rates for Grok 3 models with prefixes', () => {
expect(getMultiplier({ model: 'xai/grok-3', tokenType: 'prompt' })).toBe(
tokenValues['grok-3'].prompt,
@@ -1240,6 +1273,39 @@ describe('Grok Model Tests - Pricing', () => {
tokenValues['grok-4'].completion,
);
});
test('should return correct prompt and completion rates for Grok 4 Fast model with prefixes', () => {
expect(getMultiplier({ model: 'xai/grok-4-fast', tokenType: 'prompt' })).toBe(
tokenValues['grok-4-fast'].prompt,
);
expect(getMultiplier({ model: 'xai/grok-4-fast', tokenType: 'completion' })).toBe(
tokenValues['grok-4-fast'].completion,
);
});
test('should return correct prompt and completion rates for Grok 4.1 Fast models with prefixes', () => {
expect(getMultiplier({ model: 'xai/grok-4-1-fast-reasoning', tokenType: 'prompt' })).toBe(
tokenValues['grok-4-1-fast'].prompt,
);
expect(getMultiplier({ model: 'xai/grok-4-1-fast-reasoning', tokenType: 'completion' })).toBe(
tokenValues['grok-4-1-fast'].completion,
);
expect(getMultiplier({ model: 'xai/grok-4-1-fast-non-reasoning', tokenType: 'prompt' })).toBe(
tokenValues['grok-4-1-fast'].prompt,
);
expect(
getMultiplier({ model: 'xai/grok-4-1-fast-non-reasoning', tokenType: 'completion' }),
).toBe(tokenValues['grok-4-1-fast'].completion);
});
test('should return correct prompt and completion rates for Grok Code Fast model with prefixes', () => {
expect(getMultiplier({ model: 'xai/grok-code-fast-1', tokenType: 'prompt' })).toBe(
tokenValues['grok-code-fast'].prompt,
);
expect(getMultiplier({ model: 'xai/grok-code-fast-1', tokenType: 'completion' })).toBe(
tokenValues['grok-code-fast'].completion,
);
});
});
});

28
api/utils/tokens.spec.js
View File

@@ -778,6 +778,16 @@ describe('Grok Model Tests - Tokens', () => {
expect(getModelMaxTokens('grok-4-0709')).toBe(256000);
});
test('should return correct tokens for Grok 4 Fast and Grok 4.1 Fast models', () => {
expect(getModelMaxTokens('grok-4-fast')).toBe(2000000);
expect(getModelMaxTokens('grok-4-1-fast-reasoning')).toBe(2000000);
expect(getModelMaxTokens('grok-4-1-fast-non-reasoning')).toBe(2000000);
});
test('should return correct tokens for Grok Code Fast model', () => {
expect(getModelMaxTokens('grok-code-fast-1')).toBe(256000);
});
test('should handle partial matches for Grok models with prefixes', () => {
// Vision models should match before general models
expect(getModelMaxTokens('xai/grok-2-vision-1212')).toBe(32768);
@@ -797,6 +807,12 @@ describe('Grok Model Tests - Tokens', () => {
expect(getModelMaxTokens('xai/grok-3-mini-fast')).toBe(131072);
// Grok 4 model
expect(getModelMaxTokens('xai/grok-4-0709')).toBe(256000);
// Grok 4 Fast and 4.1 Fast models
expect(getModelMaxTokens('xai/grok-4-fast')).toBe(2000000);
expect(getModelMaxTokens('xai/grok-4-1-fast-reasoning')).toBe(2000000);
expect(getModelMaxTokens('xai/grok-4-1-fast-non-reasoning')).toBe(2000000);
// Grok Code Fast model
expect(getModelMaxTokens('xai/grok-code-fast-1')).toBe(256000);
});
});
@@ -820,6 +836,12 @@ describe('Grok Model Tests - Tokens', () => {
expect(matchModelName('grok-3-mini-fast')).toBe('grok-3-mini-fast');
// Grok 4 model
expect(matchModelName('grok-4-0709')).toBe('grok-4');
// Grok 4 Fast and 4.1 Fast models
expect(matchModelName('grok-4-fast')).toBe('grok-4-fast');
expect(matchModelName('grok-4-1-fast-reasoning')).toBe('grok-4-1-fast');
expect(matchModelName('grok-4-1-fast-non-reasoning')).toBe('grok-4-1-fast');
// Grok Code Fast model
expect(matchModelName('grok-code-fast-1')).toBe('grok-code-fast');
});
test('should match Grok model variations with prefixes', () => {
@@ -841,6 +863,12 @@ describe('Grok Model Tests - Tokens', () => {
expect(matchModelName('xai/grok-3-mini-fast')).toBe('grok-3-mini-fast');
// Grok 4 model
expect(matchModelName('xai/grok-4-0709')).toBe('grok-4');
// Grok 4 Fast and 4.1 Fast models
expect(matchModelName('xai/grok-4-fast')).toBe('grok-4-fast');
expect(matchModelName('xai/grok-4-1-fast-reasoning')).toBe('grok-4-1-fast');
expect(matchModelName('xai/grok-4-1-fast-non-reasoning')).toBe('grok-4-1-fast');
// Grok Code Fast model
expect(matchModelName('xai/grok-code-fast-1')).toBe('grok-code-fast');
});
});
});

4
client/src/hooks/Conversations/useExportConversation.ts
View File

@@ -366,7 +366,9 @@ export default function useExportConversation({
}
/** Use JSON.stringify without indentation to minimize file size for deeply nested recursive exports */
download(JSON.stringify(data), `${filename}.json`, 'application/json');
const jsonString = JSON.stringify(data);
const blob = new Blob([jsonString], { type: 'application/json;charset=utf-8' });
download(blob, `${filename}.json`, 'application/json');
};
const exportConversation = () => {

3
packages/api/src/utils/tokens.ts
View File

@@ -280,6 +280,9 @@ const xAIModels = {
'grok-3-mini': 131072,
'grok-3-mini-fast': 131072,
'grok-4': 256000, // 256K context
'grok-4-fast': 2000000, // 2M context
'grok-4-1-fast': 2000000, // 2M context (covers reasoning & non-reasoning variants)
'grok-code-fast': 256000, // 256K context
};
const aggregateModels = {