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: Add Gemini 2.5 Default Models & Pricing (#9892)

linnil10b2fde73e370
diff --git a/.env.example b/.env.example
index 1f300f2554..d4007651fb 100644
--- a/.env.example
+++ b/.env.example
@@ -163,10 +163,10 @@ 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-preview-06-17,gemini-2.0-flash,gemini-2.0-flash-lite
+# GOOGLE_MODELS=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-preview-06-17,gemini-2.0-flash-001,gemini-2.0-flash-lite-001
+# 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_TITLE_MODEL=gemini-2.0-flash-lite-001
diff --git a/api/models/tx.js b/api/models/tx.js
index 0fcf60022b..769492a643 100644
--- a/api/models/tx.js
+++ b/api/models/tx.js
@@ -124,7 +124,8 @@ const tokenValues = Object.assign(
'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
'gemini-2.0': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
- 'gemini-2.5-flash': { prompt: 0.15, completion: 3.5 },
+ 'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 },
+ 'gemini-2.5-flash-lite': { prompt: 0.075, completion: 0.4 },
'gemini-2.5': { prompt: 0, completion: 0 }, // Free for a period of time
'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
diff --git a/api/models/tx.spec.js b/api/models/tx.spec.js
index d315d58622..dd3c543417 100644
--- a/api/models/tx.spec.js
+++ b/api/models/tx.spec.js
@@ -571,6 +571,9 @@ describe('getCacheMultiplier', () => {
describe('Google Model Tests', () => {
const googleModels = [
+ 'gemini-2.5-pro',
+ 'gemini-2.5-flash',
+ 'gemini-2.5-flash-lite',
'gemini-2.5-pro-preview-05-06',
'gemini-2.5-flash-preview-04-17',
'gemini-2.5-exp',
@@ -611,6 +614,9 @@ describe('Google Model Tests', () => {
it('should map to the correct model keys', () => {
const expected = {
+ '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',
'gemini-2.5-pro-preview-05-06': 'gemini-2.5-pro',
'gemini-2.5-flash-preview-04-17': 'gemini-2.5-flash',
'gemini-2.5-exp': 'gemini-2.5',
diff --git a/api/utils/tokens.spec.js b/api/utils/tokens.spec.js
index 338322e0e2..527129ec8c 100644
--- a/api/utils/tokens.spec.js
+++ b/api/utils/tokens.spec.js
@@ -262,6 +262,15 @@ describe('getModelMaxTokens', () => {
expect(getModelMaxTokens('gemini-1.5-pro-preview-0409', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-1.5'],
);
+ expect(getModelMaxTokens('gemini-2.5-pro', EModelEndpoint.google)).toBe(
+ maxTokensMap[EModelEndpoint.google]['gemini-2.5-pro'],
+ );
+ expect(getModelMaxTokens('gemini-2.5-flash', EModelEndpoint.google)).toBe(
+ maxTokensMap[EModelEndpoint.google]['gemini-2.5-flash'],
+ );
+ expect(getModelMaxTokens('gemini-2.5-flash-lite', EModelEndpoint.google)).toBe(
+ maxTokensMap[EModelEndpoint.google]['gemini-2.5-flash-lite'],
+ );
expect(getModelMaxTokens('gemini-pro-vision', EModelEndpoint.google)).toBe(
maxTokensMap[EModelEndpoint.google]['gemini-pro-vision'],
);
diff --git a/packages/api/src/utils/tokens.ts b/packages/api/src/utils/tokens.ts
index 57923467a1..b53305278d 100644
--- a/packages/api/src/utils/tokens.ts
+++ b/packages/api/src/utils/tokens.ts
@@ -91,6 +91,7 @@ const googleModels = {
'gemini-2.5': 1000000, // 1M input tokens, 64k output tokens
'gemini-2.5-pro': 1000000,
'gemini-2.5-flash': 1000000,
+ 'gemini-2.5-flash-lite': 1000000,
'gemini-2.0': 2000000,
'gemini-2.0-flash': 1000000,
'gemini-2.0-flash-lite': 1000000,
diff --git a/packages/data-provider/src/config.ts b/packages/data-provider/src/config.ts
index df6eed9e00..f9da141ba8 100644
--- a/packages/data-provider/src/config.ts
+++ b/packages/data-provider/src/config.ts
@@ -1017,18 +1017,13 @@ export const defaultModels = {
[EModelEndpoint.assistants]: [...sharedOpenAIModels, 'chatgpt-4o-latest'],
[EModelEndpoint.agents]: sharedOpenAIModels, // TODO: Add agent models (agentsModels)
[EModelEndpoint.google]: [
+ // Gemini 2.5 Models
+ 'gemini-2.5-pro',
+ 'gemini-2.5-flash',
+ 'gemini-2.5-flash-lite',
// Gemini 2.0 Models
'gemini-2.0-flash-001',
- 'gemini-2.0-flash-exp',
'gemini-2.0-flash-lite',
- 'gemini-2.0-pro-exp-02-05',
- // Gemini 1.5 Models
- 'gemini-1.5-flash-001',
- 'gemini-1.5-flash-002',
- 'gemini-1.5-pro-001',
- 'gemini-1.5-pro-002',
- // Gemini 1.0 Models
- 'gemini-1.0-pro-001',
],
[EModelEndpoint.anthropic]: sharedAnthropicModels,
[EModelEndpoint.openAI]: [
@@ -1111,6 +1106,7 @@ export const visionModels = [
'gemini-exp',
'gemini-1.5',
'gemini-2',
+ 'gemini-2.5',
'gemini-3',
'moondream',
'llama3.2-vision',