Skip to content

Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active

🔑 feat: Grok 4 Pricing and Token Limits (#8395)

Danny Avila1e4f1f780c29
diff --git a/api/models/tx.js b/api/models/tx.js
index f3ba38652d..b6d627620a 100644
--- a/api/models/tx.js
+++ b/api/models/tx.js
@@ -135,10 +135,11 @@ const tokenValues = Object.assign(
'grok-2-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-latest': { prompt: 2.0, completion: 10.0 },
'grok-2': { prompt: 2.0, completion: 10.0 },
- 'grok-3-mini-fast': { prompt: 0.4, completion: 4 },
+ 'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
'grok-3-fast': { prompt: 5.0, completion: 25.0 },
'grok-3': { prompt: 3.0, completion: 15.0 },
+ 'grok-4': { prompt: 3.0, completion: 15.0 },
'grok-beta': { prompt: 5.0, completion: 15.0 },
'mistral-large': { prompt: 2.0, completion: 6.0 },
'pixtral-large': { prompt: 2.0, completion: 6.0 },
diff --git a/api/models/tx.spec.js b/api/models/tx.spec.js
index 1c886c1994..114b7b892d 100644
--- a/api/models/tx.spec.js
+++ b/api/models/tx.spec.js
@@ -636,6 +636,15 @@ describe('Grok Model Tests - Pricing', () => {
);
});
+ test('should return correct prompt and completion rates for Grok 4 model', () => {
+ expect(getMultiplier({ model: 'grok-4-0709', tokenType: 'prompt' })).toBe(
+ tokenValues['grok-4'].prompt,
+ );
+ expect(getMultiplier({ model: 'grok-4-0709', tokenType: 'completion' })).toBe(
+ tokenValues['grok-4'].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,
@@ -662,6 +671,15 @@ describe('Grok Model Tests - Pricing', () => {
tokenValues['grok-3-mini-fast'].completion,
);
});
+
+ test('should return correct prompt and completion rates for Grok 4 model with prefixes', () => {
+ expect(getMultiplier({ model: 'xai/grok-4-0709', tokenType: 'prompt' })).toBe(
+ tokenValues['grok-4'].prompt,
+ );
+ expect(getMultiplier({ model: 'xai/grok-4-0709', tokenType: 'completion' })).toBe(
+ tokenValues['grok-4'].completion,
+ );
+ });
});
});
diff --git a/api/utils/tokens.js b/api/utils/tokens.js
index 21608fddc6..a8363db182 100644
--- a/api/utils/tokens.js
+++ b/api/utils/tokens.js
@@ -223,6 +223,7 @@ const xAIModels = {
'grok-3-fast': 131072,
'grok-3-mini': 131072,
'grok-3-mini-fast': 131072,
+ 'grok-4': 256000, // 256K context
};
const aggregateModels = { ...openAIModels, ...googleModels, ...bedrockModels, ...xAIModels };
diff --git a/api/utils/tokens.spec.js b/api/utils/tokens.spec.js
index 4a34746e8b..8a2e8ed11d 100644
--- a/api/utils/tokens.spec.js
+++ b/api/utils/tokens.spec.js
@@ -386,7 +386,7 @@ describe('matchModelName', () => {
});
it('should return the closest matching key for gpt-4-1106 partial matches', () => {
- expect(matchModelName('something/gpt-4-1106')).toBe('gpt-4-1106');
+ expect(matchModelName('gpt-4-1106/something')).toBe('gpt-4-1106');
expect(matchModelName('gpt-4-1106-preview')).toBe('gpt-4-1106');
expect(matchModelName('gpt-4-1106-vision-preview')).toBe('gpt-4-1106');
});
@@ -589,6 +589,10 @@ describe('Grok Model Tests - Tokens', () => {
expect(getModelMaxTokens('grok-3-mini-fast')).toBe(131072);
});
+ test('should return correct tokens for Grok 4 model', () => {
+ expect(getModelMaxTokens('grok-4-0709')).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);
@@ -606,6 +610,8 @@ describe('Grok Model Tests - Tokens', () => {
expect(getModelMaxTokens('xai/grok-3-fast')).toBe(131072);
expect(getModelMaxTokens('xai/grok-3-mini')).toBe(131072);
expect(getModelMaxTokens('xai/grok-3-mini-fast')).toBe(131072);
+ // Grok 4 model
+ expect(getModelMaxTokens('xai/grok-4-0709')).toBe(256000);
});
});
@@ -627,6 +633,8 @@ describe('Grok Model Tests - Tokens', () => {
expect(matchModelName('grok-3-fast')).toBe('grok-3-fast');
expect(matchModelName('grok-3-mini')).toBe('grok-3-mini');
expect(matchModelName('grok-3-mini-fast')).toBe('grok-3-mini-fast');
+ // Grok 4 model
+ expect(matchModelName('grok-4-0709')).toBe('grok-4');
});
test('should match Grok model variations with prefixes', () => {
@@ -646,6 +654,8 @@ describe('Grok Model Tests - Tokens', () => {
expect(matchModelName('xai/grok-3-fast')).toBe('grok-3-fast');
expect(matchModelName('xai/grok-3-mini')).toBe('grok-3-mini');
expect(matchModelName('xai/grok-3-mini-fast')).toBe('grok-3-mini-fast');
+ // Grok 4 model
+ expect(matchModelName('xai/grok-4-0709')).toBe('grok-4');
});
});
});