Back
Download for Windows

Leading AI vendors, one-click access Models

Built-in mainstream AI providers, also supports custom addition, all models are clear at a glance, switch anytime, manage freely

groq

groq

Llama 4 Scout

Free

Llama 4 Maverick

Free

Llama 3.3 70B

Free

DeepSeek R1 Distill 70B

Free

Qwen QwQ 32B

Free

Gemma 2 9B

Free

together

together

Llama 4 Scout (Together)

Free

Llama 4 Maverick (Together)

Free

DeepSeek V3.1 (Together)

Free

DeepSeek R1 (Together)

Free

Kimi K2.5 (Together)

Free

GLM-4.7 (Together)

Free

fireworks

fireworks

Llama 4 Scout (Fireworks)

Free

Llama 4 Maverick (Fireworks)

Free

DeepSeek V3 (Fireworks)

Free

openrouter

openrouter

Auto Router

Free

GPT-5.4 (OpenRouter)

Free

Claude Sonnet 4.6 (OpenRouter)

Free

Gemini 2.5 Flash (OpenRouter)

Free

DeepSeek Chat (OpenRouter)

Free

perplexity

perplexity

Sonar Pro

Free

Sonar

Free

Sonar Reasoning Pro

Free

Sonar Reasoning

Free

stepfun

stepfun

Step 3.5 Flash

Free

Step 2 16K

Free

nvidia

nvidia

Llama 3.1 405B (NVIDIA)

Free

Llama 3.3 70B (NVIDIA)

Free

Mistral AI

Mistral AI

European open-weight models with excellent multilingual support and coding capabilities.

codestral-latest

Free

devstral-medium-latest

Free

mistral-medium-latest

Input $0.40/M Output $2.00/M

Google Gemini

Google Gemini

Native multimodal models with 1M+ token context windows and built-in search grounding.

gemini-2.5-flash

Free

gemini-2.5-pro

Free

gemini-3.1-flash

Free

gemini-3.1-pro-preview

Input $2.00/M Output $12.00/M

gemini-3-flash-preview

Input $0.50/M Output $2.00/M

gemini-2.5-flash-lite

Input $0.10/M Output $0.40/M

Zhipu GLM

Zhipu GLM

Zhipu AI's flagship models with strong reasoning, tool calling, and agentic workflows.

glm-5.1

Free

glm-5-turbo

Free

glm-5

Input $0.56/M Output $2.50/M

glm-4.6

Input $1.00/M Output $3.20/M

glm-4.7

Input $0.28/M Output $1.11/M

Alibaba Qwen

Alibaba Qwen

Alibaba Cloud's full-stack model family supporting text, vision, audio, and 1M context.

qwen3-coder-plus

Free

qwen3.6-plus

Free

qwen3-max

Input $1.20/M Output $6.00/M

qwen3.5-plus

Input $0.40/M Output $2.40/M

qwen3.5-flash

Input $0.10/M Output $0.40/M

xAI Grok

xAI Grok

Real-time web-connected models with 2M context window and fast reasoning capabilities.

grok-4

Free

grok-4-fast

Free

grok-3

Free

grok-3-mini

Free

grok-4.20-reasoning

Input $2.00/M Output $6.00/M

grok-4.20-non-reasoning

Input $2.00/M Output $6.00/M

grok-4.20-multi-agent

Input $2.00/M Output $6.00/M

grok-4.1-fast

Input $0.20/M Output $0.50/M

Moonshot Kimi

Moonshot Kimi

Specialist in ultra-long context understanding with 256K window and strong agent abilities.

kimi-k2-instruct

Free

kimi-k2.5

Input $0.56/M Output $2.92/M

kimi-k2-thinking

Input $0.56/M Output $2.22/M

kimi-latest

Input $0.60/M Output $3.00/M

anthropic-vertex

anthropic-vertex

Claude Opus 4.6 (Vertex)

Free

Claude Sonnet 4.6 (Vertex)

Free

arcee

arcee

Trinity Mini 26B

Free

Trinity Large Preview

Free

Trinity Large Thinking

Free

byteplus

byteplus

Seed 1.8

Free

chutes

chutes

DeepSeek V3 TEE

Free

Qwen3 235B TEE

Free

GPT-OSS 120B TEE

Free

huggingface

huggingface

DeepSeek R1 (HF)

Free

DeepSeek V3.1 (HF)

Free

Llama 3.3 70B (HF)

Free

GPT-OSS 120B (HF)

Free

kimi-coding

kimi-coding

Kimi Code

Free

venice

venice

Llama 3.3 70B (Venice)

Free

Hermes 3 405B (Venice)

Free

Qwen3 235B Thinking (Venice)

Free

Qwen3 235B Instruct (Venice)

Free

vercel-ai-gateway

vercel-ai-gateway

Claude Opus 4.6 (Vercel)

Free

GPT 5.4 (Vercel)

Free

GPT 5.4 Pro (Vercel)

Free

synthetic

synthetic

MiniMax M2.5 (Synthetic)

Free

Kimi K2 Thinking (Synthetic)

Free

GLM-4.7 (Synthetic)

Free

DeepSeek R1 (Synthetic)

Free

cloudflare-ai-gateway

cloudflare-ai-gateway

Claude Sonnet 4.5 (CF)

Free

amazon-bedrock

amazon-bedrock

Claude Sonnet 4.6 (Bedrock)

Free

Nova Micro

Free

Nova Lite

Free

amazon-bedrock-mantle

amazon-bedrock-mantle

Claude Sonnet 4.6 (Mantle)

Free

GPT-OSS 120B (Mantle)

Free

DeepSeek V3.2 (Mantle)

Free

Devstral 123B (Mantle)

Free

copilot-proxy

copilot-proxy

GPT-4o (Copilot)

Free

Claude Sonnet 4.6 (Copilot)

Free

github-copilot

github-copilot

GPT-4o (GH Copilot)

Free

GPT-5.2 Codex (GH Copilot)

Free

Claude Sonnet 4.6 (GH Copilot)

Free

kilocode

kilocode

Kilo Auto

Free

GPT-5.4 (Kilocode)

Free

Claude Sonnet 4 (Kilocode)

Free

ollama

ollama

Gemma 4

Free

Llama 3.2

Free

Qwen 3.5 9B

Free

Qwen 3 32B

Free

DeepSeek R1 8B

Free

microsoft-foundry

microsoft-foundry

GPT-5.4 (Foundry)

Free

GPT-4o (Foundry)

Free

litellm

litellm

Claude Opus 4.6 (LiteLLM)

Free

GPT-5.4 (LiteLLM)

Free

vydra

vydra

Vydra Default

Free

Tencent Hunyuan

Tencent Hunyuan

Tencent's deep-thinking model with strong reasoning and enterprise integration.

hunyuan-pro

Free

hunyuan-turbo

Free

hunyuan-lite

Free

Baidu ERNIE

Baidu ERNIE

Baidu's multimodal model with leading Chinese language understanding and generation.

ernie-4.5-8k

Free

ernie-speed-pro-128k

Free

ernie-4.5-turbo

Input $0.11/M Output $0.44/M

OpenAI

OpenAI

The GPT and o-series reasoning models that set the industry standard for AI capabilities.

gpt-5.4-pro

Input $30.00/M Output $180.00/M

gpt-5.4

Input $2.50/M Output $15.00/M

gpt-5.3-codex

Input $3.00/M Output $15.00/M

gpt-5.2

Input $1.75/M Output $14.00/M

gpt-5.2-codex

Input $1.25/M Output $10.00/M

gpt-5

Input $1.25/M Output $10.00/M

o4-mini

Input $1.10/M Output $4.40/M

gpt-5.4-mini

Input $0.75/M Output $4.50/M

gpt-5.4-nano

Input $0.20/M Output $1.25/M

Anthropic Claude

Anthropic Claude

Excels at coding, long-context analysis, and agentic tasks with up to 1M token context.

claude-opus-4-6

Input $5.00/M Output $25.00/M

claude-sonnet-4-6

Input $3.00/M Output $15.00/M

claude-sonnet-4-5

Input $3.00/M Output $15.00/M

claude-haiku-4-5

Input $1.00/M Output $5.00/M

DeepSeek

DeepSeek

Open-source models with exceptional math, coding, and reasoning at ultra-low cost.

DeepSeek-V3(V3.2)

Input $0.28/M Output $0.42/M

DeepSeek-R1(V3.2)

Input $0.28/M Output $0.42/M

MiniMax

MiniMax

Ultra cost-effective MoE architecture models optimized for real-world productivity tasks.

MiniMax-M2.7

Input $0.30/M Output $1.20/M

MiniMax-M2.7-highspeed

Input $0.60/M Output $2.40/M

MiniMax-M2.5

Input $0.20/M Output $1.00/M

MiniMax-01

Input $0.20/M Output $1.10/M

ByteDance Doubao

ByteDance Doubao

ByteDance Seed 2.0 series with deep thinking, multimodal understanding, and tool calling.

doubao-seed-2.0-pro

Input $0.44/M Output $2.22/M

doubao-seed-2.0-code

Input $0.44/M Output $2.22/M

doubao-seed-2.0-lite

Input $0.08/M Output $0.50/M

doubao-seed-2.0-mini

Input $0.03/M Output $0.17/M

Xiaomi MiMo

Xiaomi MiMo

Xiaomi's 1T-parameter agent model with 1M context, deep thinking, and omni-modal understanding.

mimo-v2-pro

Input $1.00/M Output $3.00/M

mimo-v2-omni

Input $0.40/M Output $2.00/M

mimo-v2-flash

Input $0.10/M Output $0.30/M

Footer Logo
PandaNpc

漏 2026 PandaNpc.com