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 Z.AI GLM Context Window & Pricing (#9979)

Danny Avilac9103a17083d
diff --git a/api/models/tx.js b/api/models/tx.js
index 062ebecf26..282d58c8fc 100644
--- a/api/models/tx.js
+++ b/api/models/tx.js
@@ -157,6 +157,14 @@ const tokenValues = Object.assign(
'gpt-oss-20b': { prompt: 0.05, completion: 0.2 },
'gpt-oss:120b': { prompt: 0.15, completion: 0.6 },
'gpt-oss-120b': { prompt: 0.15, completion: 0.6 },
+ // GLM models (Zhipu AI)
+ glm4: { prompt: 0.1, completion: 0.1 },
+ 'glm-4': { prompt: 0.1, completion: 0.1 },
+ 'glm-4-32b': { prompt: 0.1, completion: 0.1 },
+ 'glm-4.5': { prompt: 0.35, completion: 1.55 },
+ 'glm-4.5v': { prompt: 0.6, completion: 1.8 },
+ 'glm-4.5-air': { prompt: 0.14, completion: 0.86 },
+ 'glm-4.6': { prompt: 0.5, completion: 1.75 },
},
bedrockValues,
);
diff --git a/api/models/tx.spec.js b/api/models/tx.spec.js
index 7594ce3295..3cbce34295 100644
--- a/api/models/tx.spec.js
+++ b/api/models/tx.spec.js
@@ -404,6 +404,18 @@ describe('getMultiplier', () => {
expect(getMultiplier({ model: key, tokenType: 'completion' })).toBe(expectedCompletion);
});
});
+
+ it('should return correct multipliers for GLM models', () => {
+ const models = ['glm-4.6', 'glm-4.5v', 'glm-4.5-air', 'glm-4.5', 'glm-4-32b', 'glm-4', 'glm4'];
+ 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', () => {
@@ -782,6 +794,110 @@ describe('Grok Model Tests - Pricing', () => {
});
});
+describe('GLM Model Tests', () => {
+ it('should return expected value keys for GLM models', () => {
+ expect(getValueKey('glm-4.6')).toBe('glm-4.6');
+ expect(getValueKey('glm-4.5')).toBe('glm-4.5');
+ expect(getValueKey('glm-4.5v')).toBe('glm-4.5v');
+ expect(getValueKey('glm-4.5-air')).toBe('glm-4.5-air');
+ expect(getValueKey('glm-4-32b')).toBe('glm-4-32b');
+ expect(getValueKey('glm-4')).toBe('glm-4');
+ expect(getValueKey('glm4')).toBe('glm4');
+ });
+
+ it('should match GLM model variations with provider prefixes', () => {
+ expect(getValueKey('z-ai/glm-4.6')).toBe('glm-4.6');
+ expect(getValueKey('z-ai/glm-4.5')).toBe('glm-4.5');
+ expect(getValueKey('z-ai/glm-4.5-air')).toBe('glm-4.5-air');
+ expect(getValueKey('z-ai/glm-4.5v')).toBe('glm-4.5v');
+ expect(getValueKey('z-ai/glm-4-32b')).toBe('glm-4-32b');
+
+ expect(getValueKey('zai/glm-4.6')).toBe('glm-4.6');
+ expect(getValueKey('zai/glm-4.5')).toBe('glm-4.5');
+ expect(getValueKey('zai/glm-4.5-air')).toBe('glm-4.5-air');
+ expect(getValueKey('zai/glm-4.5v')).toBe('glm-4.5v');
+
+ expect(getValueKey('zai-org/GLM-4.6')).toBe('glm-4.6');
+ expect(getValueKey('zai-org/GLM-4.5')).toBe('glm-4.5');
+ expect(getValueKey('zai-org/GLM-4.5-Air')).toBe('glm-4.5-air');
+ expect(getValueKey('zai-org/GLM-4.5V')).toBe('glm-4.5v');
+ expect(getValueKey('zai-org/GLM-4-32B-0414')).toBe('glm-4-32b');
+ });
+
+ it('should match GLM model variations with suffixes', () => {
+ expect(getValueKey('glm-4.6-fp8')).toBe('glm-4.6');
+ expect(getValueKey('zai-org/GLM-4.6-FP8')).toBe('glm-4.6');
+ expect(getValueKey('zai-org/GLM-4.5-Air-FP8')).toBe('glm-4.5-air');
+ });
+
+ it('should prioritize more specific GLM model patterns', () => {
+ expect(getValueKey('glm-4.5-air-something')).toBe('glm-4.5-air');
+ expect(getValueKey('glm-4.5-something')).toBe('glm-4.5');
+ expect(getValueKey('glm-4.5v-something')).toBe('glm-4.5v');
+ });
+
+ it('should return correct multipliers for all GLM models', () => {
+ expect(getMultiplier({ model: 'glm-4.6', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4.6'].prompt,
+ );
+ expect(getMultiplier({ model: 'glm-4.6', tokenType: 'completion' })).toBe(
+ tokenValues['glm-4.6'].completion,
+ );
+
+ expect(getMultiplier({ model: 'glm-4.5v', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4.5v'].prompt,
+ );
+ expect(getMultiplier({ model: 'glm-4.5v', tokenType: 'completion' })).toBe(
+ tokenValues['glm-4.5v'].completion,
+ );
+
+ expect(getMultiplier({ model: 'glm-4.5-air', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4.5-air'].prompt,
+ );
+ expect(getMultiplier({ model: 'glm-4.5-air', tokenType: 'completion' })).toBe(
+ tokenValues['glm-4.5-air'].completion,
+ );
+
+ expect(getMultiplier({ model: 'glm-4.5', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4.5'].prompt,
+ );
+ expect(getMultiplier({ model: 'glm-4.5', tokenType: 'completion' })).toBe(
+ tokenValues['glm-4.5'].completion,
+ );
+
+ expect(getMultiplier({ model: 'glm-4-32b', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4-32b'].prompt,
+ );
+ expect(getMultiplier({ model: 'glm-4-32b', tokenType: 'completion' })).toBe(
+ tokenValues['glm-4-32b'].completion,
+ );
+
+ expect(getMultiplier({ model: 'glm-4', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4'].prompt,
+ );
+ expect(getMultiplier({ model: 'glm-4', tokenType: 'completion' })).toBe(
+ tokenValues['glm-4'].completion,
+ );
+
+ expect(getMultiplier({ model: 'glm4', tokenType: 'prompt' })).toBe(tokenValues['glm4'].prompt);
+ expect(getMultiplier({ model: 'glm4', tokenType: 'completion' })).toBe(
+ tokenValues['glm4'].completion,
+ );
+ });
+
+ it('should return correct multipliers for GLM models with provider prefixes', () => {
+ expect(getMultiplier({ model: 'z-ai/glm-4.6', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4.6'].prompt,
+ );
+ expect(getMultiplier({ model: 'zai/glm-4.5-air', tokenType: 'completion' })).toBe(
+ tokenValues['glm-4.5-air'].completion,
+ );
+ expect(getMultiplier({ model: 'zai-org/GLM-4.5V', tokenType: 'prompt' })).toBe(
+ tokenValues['glm-4.5v'].prompt,
+ );
+ });
+});
+
describe('Claude Model Tests', () => {
it('should return correct prompt and completion rates for Claude 4 models', () => {
expect(getMultiplier({ model: 'claude-sonnet-4', tokenType: 'prompt' })).toBe(
diff --git a/api/package.json b/api/package.json
index 98964f5cb0..b856fc0925 100644
--- a/api/package.json
+++ b/api/package.json
@@ -48,7 +48,7 @@
"@langchain/google-genai": "^0.2.13",
"@langchain/google-vertexai": "^0.2.13",
"@langchain/textsplitters": "^0.1.0",
- "@librechat/agents": "^2.4.82",
+ "@librechat/agents": "^2.4.83",
"@librechat/api": "*",
"@librechat/data-schemas": "*",
"@microsoft/microsoft-graph-client": "^3.0.7",
diff --git a/api/utils/tokens.spec.js b/api/utils/tokens.spec.js
index 20dad79894..162827767f 100644
--- a/api/utils/tokens.spec.js
+++ b/api/utils/tokens.spec.js
@@ -409,6 +409,64 @@ describe('getModelMaxTokens', () => {
});
});
+ test('should return correct tokens for GLM models', () => {
+ expect(getModelMaxTokens('glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
+ expect(getModelMaxTokens('glm-4.5v')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5v']);
+ expect(getModelMaxTokens('glm-4.5-air')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
+ );
+ expect(getModelMaxTokens('glm-4.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5']);
+ expect(getModelMaxTokens('glm-4-32b')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4-32b']);
+ expect(getModelMaxTokens('glm-4')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4']);
+ expect(getModelMaxTokens('glm4')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm4']);
+ });
+
+ test('should return correct tokens for GLM models with provider prefixes', () => {
+ expect(getModelMaxTokens('z-ai/glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
+ expect(getModelMaxTokens('z-ai/glm-4.5')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5']);
+ expect(getModelMaxTokens('z-ai/glm-4.5-air')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
+ );
+ expect(getModelMaxTokens('z-ai/glm-4.5v')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
+ );
+ expect(getModelMaxTokens('z-ai/glm-4-32b')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4-32b'],
+ );
+
+ expect(getModelMaxTokens('zai/glm-4.6')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
+ expect(getModelMaxTokens('zai/glm-4.5-air')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
+ );
+ expect(getModelMaxTokens('zai/glm-4.5v')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.5v']);
+
+ expect(getModelMaxTokens('zai-org/GLM-4.6')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.6'],
+ );
+ expect(getModelMaxTokens('zai-org/GLM-4.5')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5'],
+ );
+ expect(getModelMaxTokens('zai-org/GLM-4.5-Air')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
+ );
+ expect(getModelMaxTokens('zai-org/GLM-4.5V')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5v'],
+ );
+ expect(getModelMaxTokens('zai-org/GLM-4-32B-0414')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4-32b'],
+ );
+ });
+
+ test('should return correct tokens for GLM models with suffixes', () => {
+ expect(getModelMaxTokens('glm-4.6-fp8')).toBe(maxTokensMap[EModelEndpoint.openAI]['glm-4.6']);
+ expect(getModelMaxTokens('zai-org/GLM-4.6-FP8')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.6'],
+ );
+ expect(getModelMaxTokens('zai-org/GLM-4.5-Air-FP8')).toBe(
+ maxTokensMap[EModelEndpoint.openAI]['glm-4.5-air'],
+ );
+ });
+
test('should return correct max output tokens for GPT-5 models', () => {
const { getModelMaxOutputTokens } = require('@librechat/api');
['gpt-5', 'gpt-5-mini', 'gpt-5-nano'].forEach((model) => {
@@ -865,3 +923,91 @@ describe('Kimi Model Tests', () => {
});
});
});
+
+describe('GLM Model Tests (Zhipu AI)', () => {
+ describe('getModelMaxTokens', () => {
+ test('should return correct tokens for GLM models', () => {
+ expect(getModelMaxTokens('glm-4.6')).toBe(200000);
+ expect(getModelMaxTokens('glm-4.5v')).toBe(66000);
+ expect(getModelMaxTokens('glm-4.5-air')).toBe(131000);
+ expect(getModelMaxTokens('glm-4.5')).toBe(131000);
+ expect(getModelMaxTokens('glm-4-32b')).toBe(128000);
+ expect(getModelMaxTokens('glm-4')).toBe(128000);
+ expect(getModelMaxTokens('glm4')).toBe(128000);
+ });
+
+ test('should handle partial matches for GLM models with provider prefixes', () => {
+ expect(getModelMaxTokens('z-ai/glm-4.6')).toBe(200000);
+ expect(getModelMaxTokens('z-ai/glm-4.5')).toBe(131000);
+ expect(getModelMaxTokens('z-ai/glm-4.5-air')).toBe(131000);
+ expect(getModelMaxTokens('z-ai/glm-4.5v')).toBe(66000);
+ expect(getModelMaxTokens('z-ai/glm-4-32b')).toBe(128000);
+
+ expect(getModelMaxTokens('zai/glm-4.6')).toBe(200000);
+ expect(getModelMaxTokens('zai/glm-4.5')).toBe(131000);
+ expect(getModelMaxTokens('zai/glm-4.5-air')).toBe(131000);
+ expect(getModelMaxTokens('zai/glm-4.5v')).toBe(66000);
+
+ expect(getModelMaxTokens('zai-org/GLM-4.6')).toBe(200000);
+ expect(getModelMaxTokens('zai-org/GLM-4.5')).toBe(131000);
+ expect(getModelMaxTokens('zai-org/GLM-4.5-Air')).toBe(131000);
+ expect(getModelMaxTokens('zai-org/GLM-4.5V')).toBe(66000);
+ expect(getModelMaxTokens('zai-org/GLM-4-32B-0414')).toBe(128000);
+ });
+
+ test('should handle GLM model variations with suffixes', () => {
+ expect(getModelMaxTokens('glm-4.6-fp8')).toBe(200000);
+ expect(getModelMaxTokens('zai-org/GLM-4.6-FP8')).toBe(200000);
+ expect(getModelMaxTokens('zai-org/GLM-4.5-Air-FP8')).toBe(131000);
+ });
+
+ test('should prioritize more specific GLM patterns', () => {
+ expect(getModelMaxTokens('glm-4.5-air-custom')).toBe(131000);
+ expect(getModelMaxTokens('glm-4.5-custom')).toBe(131000);
+ expect(getModelMaxTokens('glm-4.5v-custom')).toBe(66000);
+ });
+ });
+
+ describe('matchModelName', () => {
+ test('should match exact GLM model names', () => {
+ expect(matchModelName('glm-4.6')).toBe('glm-4.6');
+ expect(matchModelName('glm-4.5v')).toBe('glm-4.5v');
+ expect(matchModelName('glm-4.5-air')).toBe('glm-4.5-air');
+ expect(matchModelName('glm-4.5')).toBe('glm-4.5');
+ expect(matchModelName('glm-4-32b')).toBe('glm-4-32b');
+ expect(matchModelName('glm-4')).toBe('glm-4');
+ expect(matchModelName('glm4')).toBe('glm4');
+ });
+
+ test('should match GLM model variations with provider prefixes', () => {
+ expect(matchModelName('z-ai/glm-4.6')).toBe('glm-4.6');
+ expect(matchModelName('z-ai/glm-4.5')).toBe('glm-4.5');
+ expect(matchModelName('z-ai/glm-4.5-air')).toBe('glm-4.5-air');
+ expect(matchModelName('z-ai/glm-4.5v')).toBe('glm-4.5v');
+ expect(matchModelName('z-ai/glm-4-32b')).toBe('glm-4-32b');
+
+ expect(matchModelName('zai/glm-4.6')).toBe('glm-4.6');
+ expect(matchModelName('zai/glm-4.5')).toBe('glm-4.5');
+ expect(matchModelName('zai/glm-4.5-air')).toBe('glm-4.5-air');
+ expect(matchModelName('zai/glm-4.5v')).toBe('glm-4.5v');
+
+ expect(matchModelName('zai-org/GLM-4.6')).toBe('glm-4.6');
+ expect(matchModelName('zai-org/GLM-4.5')).toBe('glm-4.5');
+ expect(matchModelName('zai-org/GLM-4.5-Air')).toBe('glm-4.5-air');
+ expect(matchModelName('zai-org/GLM-4.5V')).toBe('glm-4.5v');
+ expect(matchModelName('zai-org/GLM-4-32B-0414')).toBe('glm-4-32b');
+ });
+
+ test('should match GLM model variations with suffixes', () => {
+ expect(matchModelName('glm-4.6-fp8')).toBe('glm-4.6');
+ expect(matchModelName('zai-org/GLM-4.6-FP8')).toBe('glm-4.6');
+ expect(matchModelName('zai-org/GLM-4.5-Air-FP8')).toBe('glm-4.5-air');
+ });
+
+ test('should handle case-insensitive matching for GLM models', () => {
+ expect(matchModelName('zai-org/GLM-4.6')).toBe('glm-4.6');
+ expect(matchModelName('zai-org/GLM-4.5V')).toBe('glm-4.5v');
+ expect(matchModelName('zai-org/GLM-4-32B-0414')).toBe('glm-4-32b');
+ });
+ });
+});
diff --git a/package-lock.json b/package-lock.json
index 0a3784fcd7..06ad223183 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -64,7 +64,7 @@
"@langchain/google-genai": "^0.2.13",
"@langchain/google-vertexai": "^0.2.13",
"@langchain/textsplitters": "^0.1.0",
- "@librechat/agents": "^2.4.82",
+ "@librechat/agents": "^2.4.83",
"@librechat/api": "*",
"@librechat/data-schemas": "*",
"@microsoft/microsoft-graph-client": "^3.0.7",
@@ -21522,9 +21522,9 @@
}
},
"node_modules/@librechat/agents": {
- "version": "2.4.82",
- "resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-2.4.82.tgz",
- "integrity": "sha512-KNz8L1H/IXE3hnOU27ElsGy+oWpZ7oYnrLXIoJUyoy/qWlAUzKkzbOHp4hkLIK3xB21ncVuSqKS0542W6MQkKQ==",
+ "version": "2.4.83",
+ "resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-2.4.83.tgz",
+ "integrity": "sha512-xOspD4jegd7wpjWQhOieOso2LrXsNRyHNYEIIuCuk2eUZkxJU+1Rny0XzukhenTOG8P4bpne9XoVxxxZ0W5duA==",
"license": "MIT",
"dependencies": {
"@langchain/anthropic": "^0.3.26",
@@ -51336,7 +51336,7 @@
"@azure/storage-blob": "^12.27.0",
"@keyv/redis": "^4.3.3",
"@langchain/core": "^0.3.62",
- "@librechat/agents": "^2.4.82",
+ "@librechat/agents": "^2.4.83",
"@librechat/data-schemas": "*",
"@modelcontextprotocol/sdk": "^1.17.1",
"axios": "^1.12.1",
diff --git a/packages/api/package.json b/packages/api/package.json
index 2a38366b41..a983aca87a 100644
--- a/packages/api/package.json
+++ b/packages/api/package.json
@@ -80,7 +80,7 @@
"@azure/storage-blob": "^12.27.0",
"@keyv/redis": "^4.3.3",
"@langchain/core": "^0.3.62",
- "@librechat/agents": "^2.4.82",
+ "@librechat/agents": "^2.4.83",
"@librechat/data-schemas": "*",
"@modelcontextprotocol/sdk": "^1.17.1",
"axios": "^1.12.1",
diff --git a/packages/api/src/utils/tokens.ts b/packages/api/src/utils/tokens.ts
index f75a5b9de2..d527836642 100644
--- a/packages/api/src/utils/tokens.ts
+++ b/packages/api/src/utils/tokens.ts
@@ -262,6 +262,14 @@ const aggregateModels = {
'gpt-oss-20b': 131000,
'gpt-oss:120b': 131000,
'gpt-oss-120b': 131000,
+ // GLM models (Zhipu AI)
+ glm4: 128000,
+ 'glm-4': 128000,
+ 'glm-4-32b': 128000,
+ 'glm-4.5': 131000,
+ 'glm-4.5-air': 131000,
+ 'glm-4.5v': 66000,
+ 'glm-4.6': 200000,
};
export const maxTokensMap = {
@@ -317,9 +325,10 @@ export function findMatchingPattern(
tokensMap: Record<string, number> | EndpointTokenConfig,
): string | null {
const keys = Object.keys(tokensMap);
+ const lowerModelName = modelName.toLowerCase();
for (let i = keys.length - 1; i >= 0; i--) {
const modelKey = keys[i];
- if (modelName.includes(modelKey)) {
+ if (lowerModelName.includes(modelKey)) {
return modelKey;
}
}