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: `gemini-3.1-flash-lite-preview` Window & Pricing (#12043)

Danny Avilaa2a09b556ada
diff --git a/.env.example b/.env.example
index e19346c4bf..06d509a3ae 100644
--- a/.env.example
+++ b/.env.example
@@ -196,10 +196,10 @@ GOOGLE_KEY=user_provided
# GOOGLE_AUTH_HEADER=true
# Gemini API (AI Studio)
-# 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
+# GOOGLE_MODELS=gemini-3.1-pro-preview,gemini-3.1-pro-preview-customtools,gemini-3.1-flash-lite-preview,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-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_MODELS=gemini-3.1-pro-preview,gemini-3.1-pro-preview-customtools,gemini-3.1-flash-lite-preview,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-001
diff --git a/api/models/tx.js b/api/models/tx.js
index a13143a862..488ae7604e 100644
--- a/api/models/tx.js
+++ b/api/models/tx.js
@@ -201,6 +201,7 @@ const tokenValues = Object.assign(
'gemini-3': { prompt: 2, completion: 12 },
'gemini-3-pro-image': { prompt: 2, completion: 120 },
'gemini-3.1': { prompt: 2, completion: 12 },
+ 'gemini-3.1-flash-lite': { prompt: 0.25, completion: 1.5 },
'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 },
@@ -331,8 +332,10 @@ 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 Pro - cache write: $2.00/1M, cache read: $0.20/1M
'gemini-3.1': { write: 2, read: 0.2 },
+ // Gemini 3.1 Flash-Lite - cache write: $0.25/1M, cache read: $0.025/1M
+ 'gemini-3.1-flash-lite': { write: 0.25, read: 0.025 },
};
/**
diff --git a/api/models/tx.spec.js b/api/models/tx.spec.js
index b58afa9c70..b5c6d1714e 100644
--- a/api/models/tx.spec.js
+++ b/api/models/tx.spec.js
@@ -1347,6 +1347,7 @@ describe('Google Model Tests', () => {
'gemini-3',
'gemini-3.1-pro-preview',
'gemini-3.1-pro-preview-customtools',
+ 'gemini-3.1-flash-lite-preview',
'gemini-2.5-pro',
'gemini-2.5-flash',
'gemini-2.5-flash-lite',
@@ -1393,6 +1394,7 @@ describe('Google Model Tests', () => {
'gemini-3': 'gemini-3',
'gemini-3.1-pro-preview': 'gemini-3.1',
'gemini-3.1-pro-preview-customtools': 'gemini-3.1',
+ 'gemini-3.1-flash-lite-preview': 'gemini-3.1-flash-lite',
'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',
@@ -1478,6 +1480,22 @@ describe('Google Model Tests', () => {
);
});
});
+
+ it('should return correct rates for Gemini 3.1 Flash-Lite', () => {
+ const model = 'gemini-3.1-flash-lite-preview';
+ expect(getMultiplier({ model, tokenType: 'prompt', endpoint: EModelEndpoint.google })).toBe(
+ tokenValues['gemini-3.1-flash-lite'].prompt,
+ );
+ expect(getMultiplier({ model, tokenType: 'completion', endpoint: EModelEndpoint.google })).toBe(
+ tokenValues['gemini-3.1-flash-lite'].completion,
+ );
+ expect(getCacheMultiplier({ model, cacheType: 'write' })).toBe(
+ cacheTokenValues['gemini-3.1-flash-lite'].write,
+ );
+ expect(getCacheMultiplier({ model, cacheType: 'read' })).toBe(
+ cacheTokenValues['gemini-3.1-flash-lite'].read,
+ );
+ });
});
describe('Gemini 3.1 Premium Token Pricing', () => {
diff --git a/packages/api/src/utils/tokens.ts b/packages/api/src/utils/tokens.ts
index faeb8f0f90..b515ed8f75 100644
--- a/packages/api/src/utils/tokens.ts
+++ b/packages/api/src/utils/tokens.ts
@@ -107,6 +107,7 @@ const googleModels = {
'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-3.1-flash-lite': 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.ts
index 4a51844fb8..48d5409962 100644
--- a/packages/data-provider/src/config.ts
+++ b/packages/data-provider/src/config.ts
@@ -1196,6 +1196,7 @@ export const defaultModels = {
// Gemini 3.1 Models
'gemini-3.1-pro-preview',
'gemini-3.1-pro-preview-customtools',
+ 'gemini-3.1-flash-lite-preview',
// Gemini 3 Models
'gemini-3-pro-preview',
'gemini-3-flash-preview',