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

Danny Avilad7ce19e15aba
diff --git a/api/models/tx.js b/api/models/tx.js
index 328f2c2d4d..4ea93e1a1e 100644
--- a/api/models/tx.js
+++ b/api/models/tx.js
@@ -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 },
diff --git a/api/models/tx.spec.js b/api/models/tx.spec.js
index b70f9572d0..75a8fa1922 100644
--- a/api/models/tx.spec.js
+++ b/api/models/tx.spec.js
@@ -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,
+ );
+ });
});
});
diff --git a/api/utils/tokens.spec.js b/api/utils/tokens.spec.js
index c4589c610e..a169c31622 100644
--- a/api/utils/tokens.spec.js
+++ b/api/utils/tokens.spec.js
@@ -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');
});
});
});
diff --git a/client/src/hooks/Conversations/useExportConversation.ts b/client/src/hooks/Conversations/useExportConversation.ts
index 25758f54b0..6b5d53e65e 100644
--- a/client/src/hooks/Conversations/useExportConversation.ts
+++ b/client/src/hooks/Conversations/useExportConversation.ts
@@ -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 = () => {
diff --git a/packages/api/src/utils/tokens.ts b/packages/api/src/utils/tokens.ts
index 5271d69f1d..7dda247cc1 100644
--- a/packages/api/src/utils/tokens.ts
+++ b/packages/api/src/utils/tokens.ts
@@ -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 = {