mirror of
https://github.com/lobehub/lobe-chat.git
synced 2026-06-16 20:46:08 +00:00
🐛 fix: Support Grok thinking models in AiHubMix (#8713)
* 🐛 fix: 添加对 xai 模型的支持到 baseRuntimeMap 和 LobeAiHubMixAI * 添加 GLM-4.5V 视觉语言模型到 siliconcloud * update Qwen * fix lint * 更新 Qwen VL Plus 模型配置，调整部署名称和上下文窗口令牌数，优化定价策略 --------- Co-authored-by: Arvin Xu <arvinx@foxmail.com>
This commit is contained in:
sxjeru
@@ -4,6 +4,7 @@ import { LobeCloudflareAI } from '../cloudflare';
|
||||
import { LobeFalAI } from '../fal';
|
||||
import { LobeGoogleAI } from '../google';
|
||||
import { LobeOpenAI } from '../openai';
|
||||
import { LobeXAI } from '../xai';
|
||||
|
||||
export const baseRuntimeMap = {
|
||||
anthropic: LobeAnthropicAI,
|
||||
@@ -12,4 +13,5 @@ export const baseRuntimeMap = {
|
||||
fal: LobeFalAI,
|
||||
google: LobeGoogleAI,
|
||||
openai: LobeOpenAI,
|
||||
xai: LobeXAI,
|
||||
};
|
||||
|
||||
@@ -65,6 +65,13 @@ export const LobeAiHubMixAI = createRouterRuntime({
|
||||
),
|
||||
options: { baseURL: urlJoin(baseURL, '/gemini') },
|
||||
},
|
||||
{
|
||||
apiType: 'xai',
|
||||
models: LOBE_DEFAULT_MODEL_LIST.map((m) => m.id).filter(
|
||||
(id) => detectModelProvider(id) === 'xai',
|
||||
),
|
||||
options: { baseURL: urlJoin(baseURL, '/v1') },
|
||||
},
|
||||
{
|
||||
apiType: 'openai',
|
||||
options: {
|
||||
|
||||
+78
-14
@@ -519,21 +519,61 @@ const qwenChatModels: AIChatModelCard[] = [
|
||||
search: true,
|
||||
},
|
||||
config: {
|
||||
deploymentName: 'qwen-plus-2025-07-14',
|
||||
deploymentName: 'qwen-plus-2025-07-28',
|
||||
},
|
||||
contextWindowTokens: 131_072,
|
||||
contextWindowTokens: 1_000_000,
|
||||
description: '通义千问超大规模语言模型增强版，支持中文、英文等不同语言输入。',
|
||||
displayName: 'Qwen Plus',
|
||||
enabled: true,
|
||||
id: 'qwen-plus',
|
||||
maxOutput: 16_384,
|
||||
maxOutput: 32_768,
|
||||
organization: 'Qwen',
|
||||
pricing: {
|
||||
currency: 'CNY',
|
||||
units: [
|
||||
{ name: 'textInput_cacheRead', rate: 0.32, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textInput', rate: 0.8, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textOutput', rate: 8, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{
|
||||
lookup: {
|
||||
prices: {
|
||||
'[0, 128_000]': 0.8 * 0.4,
|
||||
'[128_000, 256_000]': 2.4 * 0.4,
|
||||
'[256_000, infinity]': 4.8 * 0.4,
|
||||
},
|
||||
pricingParams: ['textInputRange'],
|
||||
},
|
||||
name: 'textInput_cacheRead',
|
||||
strategy: 'lookup',
|
||||
unit: 'millionTokens',
|
||||
},
|
||||
{
|
||||
lookup: {
|
||||
prices: {
|
||||
'[0, 128_000]': 0.8,
|
||||
'[128_000, 256_000]': 2.4,
|
||||
'[256_000, infinity]': 4.8,
|
||||
},
|
||||
pricingParams: ['textInputRange'],
|
||||
},
|
||||
name: 'textInput',
|
||||
strategy: 'lookup',
|
||||
unit: 'millionTokens',
|
||||
},
|
||||
{
|
||||
lookup: {
|
||||
prices: {
|
||||
'[0, 128_000]_[false]': 2,
|
||||
'[0, 128_000]_[true]': 8,
|
||||
'[128_000, 256_000]_[false]': 20,
|
||||
|
||||
'[128_000, 256_000]_[true]': 24,
|
||||
'[256_000, infinity]_[false]': 48,
|
||||
'[256_000, infinity]_[true]': 64,
|
||||
},
|
||||
pricingParams: ['textInputRange', 'thinkingMode'],
|
||||
},
|
||||
name: 'textOutput',
|
||||
strategy: 'lookup',
|
||||
unit: 'millionTokens',
|
||||
},
|
||||
],
|
||||
},
|
||||
releasedAt: '2025-07-14',
|
||||
@@ -643,7 +683,7 @@ const qwenChatModels: AIChatModelCard[] = [
|
||||
vision: true,
|
||||
},
|
||||
config: {
|
||||
deploymentName: 'qwen-vl-plus-2025-01-25',
|
||||
deploymentName: 'qwen-vl-plus-2025-08-15',
|
||||
},
|
||||
contextWindowTokens: 131_072,
|
||||
description:
|
||||
@@ -655,9 +695,9 @@ const qwenChatModels: AIChatModelCard[] = [
|
||||
pricing: {
|
||||
currency: 'CNY',
|
||||
units: [
|
||||
{ name: 'textInput_cacheRead', rate: 0.6, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textInput', rate: 1.5, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textOutput', rate: 4.5, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textInput_cacheRead', rate: 0.8 * 0.4, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textInput', rate: 0.8, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textOutput', rate: 2, strategy: 'fixed', unit: 'millionTokens' },
|
||||
],
|
||||
},
|
||||
type: 'chat',
|
||||
@@ -667,7 +707,7 @@ const qwenChatModels: AIChatModelCard[] = [
|
||||
vision: true,
|
||||
},
|
||||
config: {
|
||||
deploymentName: 'qwen-vl-max-2025-04-08',
|
||||
deploymentName: 'qwen-vl-max-2025-08-13',
|
||||
},
|
||||
contextWindowTokens: 131_072,
|
||||
description:
|
||||
@@ -679,9 +719,9 @@ const qwenChatModels: AIChatModelCard[] = [
|
||||
pricing: {
|
||||
currency: 'CNY',
|
||||
units: [
|
||||
{ name: 'textInput_cacheRead', rate: 1.2, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textInput', rate: 3, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textOutput', rate: 9, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textInput_cacheRead', rate: 1.6 * 0.4, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textInput', rate: 1.6, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textOutput', rate: 4, strategy: 'fixed', unit: 'millionTokens' },
|
||||
],
|
||||
},
|
||||
type: 'chat',
|
||||
@@ -1304,6 +1344,30 @@ const qwenChatModels: AIChatModelCard[] = [
|
||||
];
|
||||
|
||||
const qwenImageModels: AIImageModelCard[] = [
|
||||
{
|
||||
description:
|
||||
'Qwen-Image 是一款通用图像生成模型，支持多种艺术风格，尤其擅长复杂文本渲染，特别是中英文文本渲染。模型支持多行布局、段落级文本生成以及细粒度细节刻画，可实现复杂的图文混合布局设计。',
|
||||
displayName: 'Qwen Image',
|
||||
enabled: true,
|
||||
id: 'qwen-image',
|
||||
organization: 'Qwen',
|
||||
parameters: {
|
||||
prompt: {
|
||||
default: '',
|
||||
},
|
||||
seed: { default: null },
|
||||
size: {
|
||||
default: '1328*1328',
|
||||
enum: ['1664*928', '1472*1140', '1328*1328', '1140*1472', '928*1664'],
|
||||
},
|
||||
},
|
||||
pricing: {
|
||||
currency: 'CNY',
|
||||
units: [{ name: 'imageGeneration', rate: 0.25, strategy: 'fixed', unit: 'image' }],
|
||||
},
|
||||
releasedAt: '2025-08-13',
|
||||
type: 'image',
|
||||
},
|
||||
{
|
||||
description:
|
||||
'万相2.2极速版，当前最新模型。在创意性、稳定性、写实质感上全面升级，生成速度快，性价比高。',
|
||||
|
||||
@@ -61,6 +61,27 @@ const siliconcloudChatModels: AIChatModelCard[] = [
|
||||
releasedAt: '2025-07-31',
|
||||
type: 'chat',
|
||||
},
|
||||
{
|
||||
abilities: {
|
||||
functionCall: true,
|
||||
reasoning: true,
|
||||
vision: true,
|
||||
},
|
||||
contextWindowTokens: 65_536,
|
||||
description:
|
||||
'GLM-4.5V 是由智谱 AI（Zhipu AI）发布的最新一代视觉语言模型（VLM）该模型基于拥有 106B 总参数和 12B 激活参数的旗舰文本模型 GLM-4.5-Air 构建，采用了混合专家（MoE）架构，旨在以更低的推理成本实现卓越性能 GLM-4.5V 在技术上延续了 GLM-4.1V-Thinking 的路线，并引入了三维旋转位置编码（3D-RoPE）等创新，显著增强了对三维空间关系的感知与推理能力。通过在预训练、监督微调和强化学习阶段的优化，该模型具备了处理图像、视频、长文档等多种视觉内容的能力，在 41 个公开的多模态基准测试中达到了同级别开源模型的顶尖水平此外，模型还新增了“思考模式”开关，允许用户在快速响应和深度推理之间灵活选择，以平衡效率与效果。',
|
||||
displayName: 'GLM-4.5V',
|
||||
id: 'zai-org/GLM-4.5V',
|
||||
pricing: {
|
||||
currency: 'CNY',
|
||||
units: [
|
||||
{ name: 'textInput', rate: 1, strategy: 'fixed', unit: 'millionTokens' },
|
||||
{ name: 'textOutput', rate: 6, strategy: 'fixed', unit: 'millionTokens' },
|
||||
],
|
||||
},
|
||||
releasedAt: '2025-08-11',
|
||||
type: 'chat',
|
||||
},
|
||||
{
|
||||
abilities: {
|
||||
functionCall: true,
|
||||
|
||||
Reference in New Issue
Block a user