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
TypeScript aianthropicartifactsawsazurechatgptchatgpt-cloneclaudeclonedeepseekgeminigooglegpt-5librechatmcpo1openairesponses-apivisionwebui
🤖 feat: Gemini 3.1 Pricing and Context Window (#11884)
Danny Avila7a1d2969b840
diff --git a/.env.example b/.env.exampleindex a6ff6157ce..50229b1997 100644--- a/.env.example+++ b/.env.example@@ -193,10 +193,10 @@ GOOGLE_KEY=user_provided# GOOGLE_AUTH_HEADER=true# Gemini API (AI Studio)-# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash,gemini-2.0-flash-lite+# GOOGLE_MODELS=gemini-3.1-pro-preview,gemini-3.1-pro-preview-customtools,gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash,gemini-2.0-flash-lite# Vertex AI-# GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash-001,gemini-2.0-flash-lite-001+# GOOGLE_MODELS=gemini-3.1-pro-preview,gemini-3.1-pro-preview-customtools,gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite,gemini-2.0-flash-001,gemini-2.0-flash-lite-001# GOOGLE_TITLE_MODEL=gemini-2.0-flash-lite-001diff --git a/api/models/Transaction.spec.js b/api/models/Transaction.spec.jsindex 4b478d4dc3..545c7b2755 100644--- a/api/models/Transaction.spec.js+++ b/api/models/Transaction.spec.js@@ -823,6 +823,139 @@ describe('Premium Token Pricing Integration Tests', () => {expect(updatedBalance.tokenCredits).toBeCloseTo(initialBalance - expectedTotalCost, 0);});+ test('spendTokens should apply standard pricing for gemini-3.1-pro-preview below threshold', async () => {+ const userId = new mongoose.Types.ObjectId();+ const initialBalance = 100000000;+ await Balance.create({ user: userId, tokenCredits: initialBalance });++ const model = 'gemini-3.1-pro-preview';+ const promptTokens = 100000;+ const completionTokens = 500;++ const txData = {+ user: userId,+ conversationId: 'test-gemini31-below',+ model,+ context: 'test',+ endpointTokenConfig: null,+ balance: { enabled: true },+ };++ await spendTokens(txData, { promptTokens, completionTokens });++ const standardPromptRate = tokenValues['gemini-3.1'].prompt;+ const standardCompletionRate = tokenValues['gemini-3.1'].completion;+ const expectedCost =+ promptTokens * standardPromptRate + completionTokens * standardCompletionRate;++ const updatedBalance = await Balance.findOne({ user: userId });+ expect(updatedBalance.tokenCredits).toBeCloseTo(initialBalance - expectedCost, 0);+ });++ test('spendTokens should apply premium pricing for gemini-3.1-pro-preview above threshold', async () => {+ const userId = new mongoose.Types.ObjectId();+ const initialBalance = 100000000;+ await Balance.create({ user: userId, tokenCredits: initialBalance });++ const model = 'gemini-3.1-pro-preview';+ const promptTokens = 250000;+ const completionTokens = 500;++ const txData = {+ user: userId,+ conversationId: 'test-gemini31-above',+ model,+ context: 'test',+ endpointTokenConfig: null,+ balance: { enabled: true },+ };++ await spendTokens(txData, { promptTokens, completionTokens });++ const premiumPromptRate = premiumTokenValues['gemini-3.1'].prompt;+ const premiumCompletionRate = premiumTokenValues['gemini-3.1'].completion;+ const expectedCost =+ promptTokens * premiumPromptRate + completionTokens * premiumCompletionRate;++ const updatedBalance = await Balance.findOne({ user: userId });+ expect(updatedBalance.tokenCredits).toBeCloseTo(initialBalance - expectedCost, 0);+ });++ test('spendTokens should apply standard pricing for gemini-3.1-pro-preview at exactly the threshold', async () => {+ const userId = new mongoose.Types.ObjectId();+ const initialBalance = 100000000;+ await Balance.create({ user: userId, tokenCredits: initialBalance });++ const model = 'gemini-3.1-pro-preview';+ const promptTokens = premiumTokenValues['gemini-3.1'].threshold;+ const completionTokens = 500;++ const txData = {+ user: userId,+ conversationId: 'test-gemini31-exact',+ model,+ context: 'test',+ endpointTokenConfig: null,+ balance: { enabled: true },+ };++ await spendTokens(txData, { promptTokens, completionTokens });++ const standardPromptRate = tokenValues['gemini-3.1'].prompt;+ const standardCompletionRate = tokenValues['gemini-3.1'].completion;+ const expectedCost =+ promptTokens * standardPromptRate + completionTokens * standardCompletionRate;++ const updatedBalance = await Balance.findOne({ user: userId });+ expect(updatedBalance.tokenCredits).toBeCloseTo(initialBalance - expectedCost, 0);+ });++ test('spendStructuredTokens should apply premium pricing for gemini-3.1 when total input exceeds threshold', async () => {+ const userId = new mongoose.Types.ObjectId();+ const initialBalance = 100000000;+ await Balance.create({ user: userId, tokenCredits: initialBalance });++ const model = 'gemini-3.1-pro-preview';+ const txData = {+ user: userId,+ conversationId: 'test-gemini31-structured-premium',+ model,+ context: 'message',+ endpointTokenConfig: null,+ balance: { enabled: true },+ };++ const tokenUsage = {+ promptTokens: {+ input: 200000,+ write: 10000,+ read: 5000,+ },+ completionTokens: 1000,+ };++ const totalInput =+ tokenUsage.promptTokens.input + tokenUsage.promptTokens.write + tokenUsage.promptTokens.read;++ await spendStructuredTokens(txData, tokenUsage);++ const premiumPromptRate = premiumTokenValues['gemini-3.1'].prompt;+ const premiumCompletionRate = premiumTokenValues['gemini-3.1'].completion;+ const writeMultiplier = getCacheMultiplier({ model, cacheType: 'write' });+ const readMultiplier = getCacheMultiplier({ model, cacheType: 'read' });++ const expectedPromptCost =+ tokenUsage.promptTokens.input * premiumPromptRate ++ tokenUsage.promptTokens.write * writeMultiplier ++ tokenUsage.promptTokens.read * readMultiplier;+ const expectedCompletionCost = tokenUsage.completionTokens * premiumCompletionRate;+ const expectedTotalCost = expectedPromptCost + expectedCompletionCost;++ const updatedBalance = await Balance.findOne({ user: userId });+ expect(totalInput).toBeGreaterThan(premiumTokenValues['gemini-3.1'].threshold);+ expect(updatedBalance.tokenCredits).toBeCloseTo(initialBalance - expectedTotalCost, 0);+ });+test('non-premium models should not be affected by inputTokenCount regardless of prompt size', async () => {const userId = new mongoose.Types.ObjectId();const initialBalance = 100000000;diff --git a/api/models/spendTokens.spec.js b/api/models/spendTokens.spec.jsindex c076d29700..dfeec5ee83 100644--- a/api/models/spendTokens.spec.js+++ b/api/models/spendTokens.spec.js@@ -878,6 +878,135 @@ describe('spendTokens', () => {expect(result.completion.completion).toBeCloseTo(-expectedCompletionCost, 0);});+ it('should charge standard rates for gemini-3.1-pro-preview when prompt tokens are below threshold', async () => {+ const initialBalance = 100000000;+ await Balance.create({+ user: userId,+ tokenCredits: initialBalance,+ });++ const model = 'gemini-3.1-pro-preview';+ const promptTokens = 100000;+ const completionTokens = 500;++ const txData = {+ user: userId,+ conversationId: 'test-gemini31-standard-pricing',+ model,+ context: 'test',+ balance: { enabled: true },+ };++ await spendTokens(txData, { promptTokens, completionTokens });++ const expectedCost =+ promptTokens * tokenValues['gemini-3.1'].prompt ++ completionTokens * tokenValues['gemini-3.1'].completion;++ const balance = await Balance.findOne({ user: userId });+ expect(balance.tokenCredits).toBeCloseTo(initialBalance - expectedCost, 0);+ });++ it('should charge premium rates for gemini-3.1-pro-preview when prompt tokens exceed threshold', async () => {+ const initialBalance = 100000000;+ await Balance.create({+ user: userId,+ tokenCredits: initialBalance,+ });++ const model = 'gemini-3.1-pro-preview';+ const promptTokens = 250000;+ const completionTokens = 500;++ const txData = {+ user: userId,+ conversationId: 'test-gemini31-premium-pricing',+ model,+ context: 'test',+ balance: { enabled: true },+ };++ await spendTokens(txData, { promptTokens, completionTokens });++ const expectedCost =+ promptTokens * premiumTokenValues['gemini-3.1'].prompt ++ completionTokens * premiumTokenValues['gemini-3.1'].completion;++ const balance = await Balance.findOne({ user: userId });+ expect(balance.tokenCredits).toBeCloseTo(initialBalance - expectedCost, 0);+ });++ it('should charge premium rates for gemini-3.1-pro-preview-customtools when prompt tokens exceed threshold', async () => {+ const initialBalance = 100000000;+ await Balance.create({+ user: userId,+ tokenCredits: initialBalance,+ });++ const model = 'gemini-3.1-pro-preview-customtools';+ const promptTokens = 250000;+ const completionTokens = 500;++ const txData = {+ user: userId,+ conversationId: 'test-gemini31-customtools-premium',+ model,+ context: 'test',+ balance: { enabled: true },+ };++ await spendTokens(txData, { promptTokens, completionTokens });++ const expectedCost =+ promptTokens * premiumTokenValues['gemini-3.1'].prompt ++ completionTokens * premiumTokenValues['gemini-3.1'].completion;++ const balance = await Balance.findOne({ user: userId });+ expect(balance.tokenCredits).toBeCloseTo(initialBalance - expectedCost, 0);+ });++ it('should charge premium rates for structured gemini-3.1 tokens when total input exceeds threshold', async () => {+ const initialBalance = 100000000;+ await Balance.create({+ user: userId,+ tokenCredits: initialBalance,+ });++ const model = 'gemini-3.1-pro-preview';+ const txData = {+ user: userId,+ conversationId: 'test-gemini31-structured-premium',+ model,+ context: 'test',+ balance: { enabled: true },+ };++ const tokenUsage = {+ promptTokens: {+ input: 200000,+ write: 10000,+ read: 5000,+ },+ completionTokens: 1000,+ };++ const result = await spendStructuredTokens(txData, tokenUsage);++ const premiumPromptRate = premiumTokenValues['gemini-3.1'].prompt;+ const premiumCompletionRate = premiumTokenValues['gemini-3.1'].completion;+ const writeRate = getCacheMultiplier({ model, cacheType: 'write' });+ const readRate = getCacheMultiplier({ model, cacheType: 'read' });++ const expectedPromptCost =+ tokenUsage.promptTokens.input * premiumPromptRate ++ tokenUsage.promptTokens.write * writeRate ++ tokenUsage.promptTokens.read * readRate;+ const expectedCompletionCost = tokenUsage.completionTokens * premiumCompletionRate;++ expect(result.prompt.prompt).toBeCloseTo(-expectedPromptCost, 0);+ expect(result.completion.completion).toBeCloseTo(-expectedCompletionCost, 0);+ });+it('should not apply premium pricing to non-premium models regardless of prompt size', async () => {const initialBalance = 100000000;await Balance.create({diff --git a/api/models/tx.js b/api/models/tx.jsindex 9a6305ec5c..a13143a862 100644--- a/api/models/tx.js+++ b/api/models/tx.js@@ -200,6 +200,7 @@ const tokenValues = Object.assign('gemini-2.5-flash-image': { prompt: 0.15, completion: 30 },'gemini-3': { prompt: 2, completion: 12 },'gemini-3-pro-image': { prompt: 2, completion: 120 },+ 'gemini-3.1': { prompt: 2, completion: 12 },'gemini-pro-vision': { prompt: 0.5, completion: 1.5 },grok: { prompt: 2.0, completion: 10.0 }, // Base pattern defaults to grok-2'grok-beta': { prompt: 5.0, completion: 15.0 },@@ -330,6 +331,8 @@ const cacheTokenValues = {'kimi-k2-0711-preview': { write: 0.6, read: 0.15 },'kimi-k2-thinking': { write: 0.6, read: 0.15 },'kimi-k2-thinking-turbo': { write: 1.15, read: 0.15 },+ // Gemini 3.1 models - cache read: $0.20/1M (<=200k), cache write: standard input price+ 'gemini-3.1': { write: 2, read: 0.2 },};/**@@ -340,6 +343,7 @@ const cacheTokenValues = {const premiumTokenValues = {'claude-opus-4-6': { threshold: 200000, prompt: 10, completion: 37.5 },'claude-sonnet-4-6': { threshold: 200000, prompt: 6, completion: 22.5 },+ 'gemini-3.1': { threshold: 200000, prompt: 4, completion: 18 },};/**diff --git a/api/models/tx.spec.js b/api/models/tx.spec.jsindex df1bec8619..b58afa9c70 100644--- a/api/models/tx.spec.js+++ b/api/models/tx.spec.js@@ -1345,6 +1345,8 @@ describe('getCacheMultiplier', () => {describe('Google Model Tests', () => {const googleModels = ['gemini-3',+ 'gemini-3.1-pro-preview',+ 'gemini-3.1-pro-preview-customtools','gemini-2.5-pro','gemini-2.5-flash','gemini-2.5-flash-lite',@@ -1389,6 +1391,8 @@ describe('Google Model Tests', () => {it('should map to the correct model keys', () => {const expected = {'gemini-3': 'gemini-3',+ 'gemini-3.1-pro-preview': 'gemini-3.1',+ 'gemini-3.1-pro-preview-customtools': 'gemini-3.1','gemini-2.5-pro': 'gemini-2.5-pro','gemini-2.5-flash': 'gemini-2.5-flash','gemini-2.5-flash-lite': 'gemini-2.5-flash-lite',@@ -1432,6 +1436,174 @@ describe('Google Model Tests', () => {).toBe(tokenValues[expected].completion);});});++ it('should return correct prompt and completion rates for Gemini 3.1', () => {+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview',+ tokenType: 'prompt',+ endpoint: EModelEndpoint.google,+ }),+ ).toBe(tokenValues['gemini-3.1'].prompt);+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview',+ tokenType: 'completion',+ endpoint: EModelEndpoint.google,+ }),+ ).toBe(tokenValues['gemini-3.1'].completion);+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview-customtools',+ tokenType: 'prompt',+ endpoint: EModelEndpoint.google,+ }),+ ).toBe(tokenValues['gemini-3.1'].prompt);+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview-customtools',+ tokenType: 'completion',+ endpoint: EModelEndpoint.google,+ }),+ ).toBe(tokenValues['gemini-3.1'].completion);+ });++ it('should return correct cache rates for Gemini 3.1', () => {+ ['gemini-3.1-pro-preview', 'gemini-3.1-pro-preview-customtools'].forEach((model) => {+ expect(getCacheMultiplier({ model, cacheType: 'write' })).toBe(+ cacheTokenValues['gemini-3.1'].write,+ );+ expect(getCacheMultiplier({ model, cacheType: 'read' })).toBe(+ cacheTokenValues['gemini-3.1'].read,+ );+ });+ });+});++describe('Gemini 3.1 Premium Token Pricing', () => {+ const premiumKey = 'gemini-3.1';+ const premiumEntry = premiumTokenValues[premiumKey];+ const { threshold } = premiumEntry;+ const belowThreshold = threshold - 1;+ const aboveThreshold = threshold + 1;+ const wellAboveThreshold = threshold * 2;++ it('should have premium pricing defined for gemini-3.1', () => {+ expect(premiumEntry).toBeDefined();+ expect(premiumEntry.threshold).toBeDefined();+ expect(premiumEntry.prompt).toBeDefined();+ expect(premiumEntry.completion).toBeDefined();+ expect(premiumEntry.prompt).toBeGreaterThan(tokenValues[premiumKey].prompt);+ expect(premiumEntry.completion).toBeGreaterThan(tokenValues[premiumKey].completion);+ });++ it('should return null from getPremiumRate when inputTokenCount is below or at threshold', () => {+ expect(getPremiumRate(premiumKey, 'prompt', belowThreshold)).toBeNull();+ expect(getPremiumRate(premiumKey, 'completion', belowThreshold)).toBeNull();+ expect(getPremiumRate(premiumKey, 'prompt', threshold)).toBeNull();+ });++ it('should return premium rate from getPremiumRate when inputTokenCount exceeds threshold', () => {+ expect(getPremiumRate(premiumKey, 'prompt', aboveThreshold)).toBe(premiumEntry.prompt);+ expect(getPremiumRate(premiumKey, 'completion', aboveThreshold)).toBe(premiumEntry.completion);+ expect(getPremiumRate(premiumKey, 'prompt', wellAboveThreshold)).toBe(premiumEntry.prompt);+ });++ it('should return null from getPremiumRate when inputTokenCount is undefined or null', () => {+ expect(getPremiumRate(premiumKey, 'prompt', undefined)).toBeNull();+ expect(getPremiumRate(premiumKey, 'prompt', null)).toBeNull();+ });++ it('should return standard rate from getMultiplier when inputTokenCount is below threshold', () => {+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview',+ tokenType: 'prompt',+ inputTokenCount: belowThreshold,+ }),+ ).toBe(tokenValues[premiumKey].prompt);+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview',+ tokenType: 'completion',+ inputTokenCount: belowThreshold,+ }),+ ).toBe(tokenValues[premiumKey].completion);+ });++ it('should return premium rate from getMultiplier when inputTokenCount exceeds threshold', () => {+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview',+ tokenType: 'prompt',+ inputTokenCount: aboveThreshold,+ }),+ ).toBe(premiumEntry.prompt);+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview',+ tokenType: 'completion',+ inputTokenCount: aboveThreshold,+ }),+ ).toBe(premiumEntry.completion);+ });++ it('should return standard rate from getMultiplier when inputTokenCount is exactly at threshold', () => {+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview',+ tokenType: 'prompt',+ inputTokenCount: threshold,+ }),+ ).toBe(tokenValues[premiumKey].prompt);+ });++ it('should apply premium pricing to customtools variant above threshold', () => {+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview-customtools',+ tokenType: 'prompt',+ inputTokenCount: aboveThreshold,+ }),+ ).toBe(premiumEntry.prompt);+ expect(+ getMultiplier({+ model: 'gemini-3.1-pro-preview-customtools',+ tokenType: 'completion',+ inputTokenCount: aboveThreshold,+ }),+ ).toBe(premiumEntry.completion);+ });++ it('should use standard rate when inputTokenCount is not provided', () => {+ expect(getMultiplier({ model: 'gemini-3.1-pro-preview', tokenType: 'prompt' })).toBe(+ tokenValues[premiumKey].prompt,+ );+ expect(getMultiplier({ model: 'gemini-3.1-pro-preview', tokenType: 'completion' })).toBe(+ tokenValues[premiumKey].completion,+ );+ });++ it('should apply premium pricing through getMultiplier with valueKey path', () => {+ const valueKey = getValueKey('gemini-3.1-pro-preview');+ expect(valueKey).toBe(premiumKey);+ expect(getMultiplier({ valueKey, tokenType: 'prompt', inputTokenCount: aboveThreshold })).toBe(+ premiumEntry.prompt,+ );+ expect(+ getMultiplier({ valueKey, tokenType: 'completion', inputTokenCount: aboveThreshold }),+ ).toBe(premiumEntry.completion);+ });++ it('should apply standard pricing through getMultiplier with valueKey path when below threshold', () => {+ const valueKey = getValueKey('gemini-3.1-pro-preview');+ expect(getMultiplier({ valueKey, tokenType: 'prompt', inputTokenCount: belowThreshold })).toBe(+ tokenValues[premiumKey].prompt,+ );+ expect(+ getMultiplier({ valueKey, tokenType: 'completion', inputTokenCount: belowThreshold }),+ ).toBe(tokenValues[premiumKey].completion);+ });});describe('Grok Model Tests - Pricing', () => {diff --git a/api/utils/tokens.spec.js b/api/utils/tokens.spec.jsindex 18905d6d18..efbd962a8c 100644--- a/api/utils/tokens.spec.js+++ b/api/utils/tokens.spec.js@@ -279,6 +279,12 @@ describe('getModelMaxTokens', () => {expect(getModelMaxTokens('gemini-3', EModelEndpoint.google)).toBe(maxTokensMap[EModelEndpoint.google]['gemini-3'],);+ expect(getModelMaxTokens('gemini-3.1-pro-preview', EModelEndpoint.google)).toBe(+ maxTokensMap[EModelEndpoint.google]['gemini-3.1'],+ );+ expect(getModelMaxTokens('gemini-3.1-pro-preview-customtools', EModelEndpoint.google)).toBe(+ maxTokensMap[EModelEndpoint.google]['gemini-3.1'],+ );expect(getModelMaxTokens('gemini-2.5-pro', EModelEndpoint.google)).toBe(maxTokensMap[EModelEndpoint.google]['gemini-2.5-pro'],);diff --git a/packages/api/src/utils/tokens.ts b/packages/api/src/utils/tokens.tsindex a824afa489..faeb8f0f90 100644--- a/packages/api/src/utils/tokens.ts+++ b/packages/api/src/utils/tokens.ts@@ -106,6 +106,7 @@ const googleModels = {'gemini-exp': 2000000,'gemini-3': 1000000, // 1M input tokens, 64k output tokens'gemini-3-pro-image': 1000000,+ 'gemini-3.1': 1000000, // 1M input tokens, 64k output tokens'gemini-2.5': 1000000, // 1M input tokens, 64k output tokens'gemini-2.5-pro': 1000000,'gemini-2.5-flash': 1000000,diff --git a/packages/data-provider/src/config.ts b/packages/data-provider/src/config.tsindex 360cce69ba..82d477e54e 100644--- a/packages/data-provider/src/config.ts+++ b/packages/data-provider/src/config.ts@@ -1192,6 +1192,9 @@ export const defaultModels = {[EModelEndpoint.assistants]: [...sharedOpenAIModels, 'chatgpt-4o-latest'],[EModelEndpoint.agents]: sharedOpenAIModels, // TODO: Add agent models (agentsModels)[EModelEndpoint.google]: [+ // Gemini 3.1 Models+ 'gemini-3.1-pro-preview',+ 'gemini-3.1-pro-preview-customtools',// Gemini 2.5 Models'gemini-2.5-pro','gemini-2.5-flash',