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: GPT-OSS models Token Limits & Rates

Danny Avilad95d8032cc23
diff --git a/api/models/tx.js b/api/models/tx.js
index b6d627620a..ba7a042185 100644
--- a/api/models/tx.js
+++ b/api/models/tx.js
@@ -1,4 +1,4 @@
-const { matchModelName } = require('../utils');
+const { matchModelName } = require('../utils/tokens');
const defaultRate = 6;
/**
@@ -147,6 +147,9 @@ const tokenValues = Object.assign(
codestral: { prompt: 0.3, completion: 0.9 },
'ministral-8b': { prompt: 0.1, completion: 0.1 },
'ministral-3b': { prompt: 0.04, completion: 0.04 },
+ // GPT-OSS models
+ 'gpt-oss-20b': { prompt: 0.05, completion: 0.2 },
+ 'gpt-oss-120b': { prompt: 0.15, completion: 0.6 },
},
bedrockValues,
);
diff --git a/api/models/tx.spec.js b/api/models/tx.spec.js
index 114b7b892d..393a294828 100644
--- a/api/models/tx.spec.js
+++ b/api/models/tx.spec.js
@@ -311,6 +311,18 @@ describe('getMultiplier', () => {
defaultRate,
);
});
+
+ it('should return correct multipliers for GPT-OSS models', () => {
+ const models = ['gpt-oss-20b', 'gpt-oss-120b'];
+ models.forEach((key) => {
+ const expectedPrompt = tokenValues[key].prompt;
+ const expectedCompletion = tokenValues[key].completion;
+ expect(getMultiplier({ valueKey: key, tokenType: 'prompt' })).toBe(expectedPrompt);
+ expect(getMultiplier({ valueKey: key, tokenType: 'completion' })).toBe(expectedCompletion);
+ expect(getMultiplier({ model: key, tokenType: 'prompt' })).toBe(expectedPrompt);
+ expect(getMultiplier({ model: key, tokenType: 'completion' })).toBe(expectedCompletion);
+ });
+ });
});
describe('AWS Bedrock Model Tests', () => {
diff --git a/api/utils/tokens.js b/api/utils/tokens.js
index 8f2173cbf9..f33a825266 100644
--- a/api/utils/tokens.js
+++ b/api/utils/tokens.js
@@ -234,6 +234,9 @@ const aggregateModels = {
...xAIModels,
// misc.
kimi: 131000,
+ // GPT-OSS
+ 'gpt-oss-20b': 131000,
+ 'gpt-oss-120b': 131000,
};
const maxTokensMap = {
@@ -250,6 +253,8 @@ const modelMaxOutputs = {
o1: 32268, // -500 from max: 32,768
'o1-mini': 65136, // -500 from max: 65,536
'o1-preview': 32268, // -500 from max: 32,768
+ 'gpt-oss-20b': 131000,
+ 'gpt-oss-120b': 131000,
system_default: 1024,
};
@@ -468,10 +473,11 @@ const tiktokenModels = new Set([
]);
module.exports = {
- tiktokenModels,
- maxTokensMap,
inputSchema,
modelSchema,
+ maxTokensMap,
+ tiktokenModels,
+ maxOutputTokensMap,
matchModelName,
processModelData,
getModelMaxTokens,
diff --git a/api/utils/tokens.spec.js b/api/utils/tokens.spec.js
index 2d4f051584..246fee80bf 100644
--- a/api/utils/tokens.spec.js
+++ b/api/utils/tokens.spec.js
@@ -1,5 +1,11 @@
const { EModelEndpoint } = require('librechat-data-provider');
-const { getModelMaxTokens, processModelData, matchModelName, maxTokensMap } = require('./tokens');
+const {
+ maxOutputTokensMap,
+ getModelMaxTokens,
+ processModelData,
+ matchModelName,
+ maxTokensMap,
+} = require('./tokens');
describe('getModelMaxTokens', () => {
test('should return correct tokens for exact match', () => {
@@ -349,6 +355,26 @@ describe('getModelMaxTokens', () => {
expect(getModelMaxTokens('o3')).toBe(o3Tokens);
expect(getModelMaxTokens('openai/o3')).toBe(o3Tokens);
});
+
+ test('should return correct tokens for GPT-OSS models', () => {
+ const expected = maxTokensMap[EModelEndpoint.openAI]['gpt-oss-20b'];
+ ['gpt-oss-20b', 'gpt-oss-120b', 'openai/gpt-oss-20b', 'openai/gpt-oss-120b'].forEach((name) => {
+ expect(getModelMaxTokens(name)).toBe(expected);
+ });
+ });
+
+ test('should return correct max output tokens for GPT-OSS models', () => {
+ const { getModelMaxOutputTokens } = require('./tokens');
+ ['gpt-oss-20b', 'gpt-oss-120b'].forEach((model) => {
+ expect(getModelMaxOutputTokens(model)).toBe(maxOutputTokensMap[EModelEndpoint.openAI][model]);
+ expect(getModelMaxOutputTokens(model, EModelEndpoint.openAI)).toBe(
+ maxOutputTokensMap[EModelEndpoint.openAI][model],
+ );
+ expect(getModelMaxOutputTokens(model, EModelEndpoint.azureOpenAI)).toBe(
+ maxOutputTokensMap[EModelEndpoint.azureOpenAI][model],
+ );
+ });
+ });
});
describe('matchModelName', () => {