Qwen3.8 Max

文字使用中

qwen3.8-max

Alibaba's flagship 2.4-trillion-parameter Qwen mixture-of-experts model with a 1M-token context, multimodal input, and controllable reasoning.

Claude Opus 5

文字使用中

claude-opus-5

Anthropic's flagship Opus model for demanding reasoning, coding, and long-horizon agentic work.

Gemini 3.5 Flash Lite

文字使用中

gemini-3.5-flash-lite

A high-efficiency Gemini model with upgraded agentic capabilities, suited for focused subagent tasks in multi-agent workflows.

Kimi K3

文字使用中

kimi-k3

Kimi K3 is Moonshot AI's open-weight flagship model for complex coding, knowledge work, and long-horizon agentic workflows.

GPT-5.6 Sol

文字使用中

gpt-5.6-sol

The flagship GPT-5.6 model for complex reasoning, coding, and long-running agentic workflows.

GPT-5.6 Luna

文字使用中

gpt-5.6-luna

A fast, cost-efficient GPT-5.6 model for chat, classification, and lightweight agentic workflows.

GPT-5.6 Terra

文字使用中

gpt-5.6-terra

A balanced GPT-5.6 model for everyday coding, reasoning, and agentic tasks.

Claude Sonnet 5

文字使用中

claude-sonnet-5

Anthropic's frontier Sonnet model for coding, agents, and professional knowledge work.

GLM 5.2

文字使用中

glm-5.2

A large-scale GLM reasoning model for long-horizon agents, software engineering, and tool use.

Kimi K2.7 Code

文字使用中

kimi-k2.7-code

A coding-focused Kimi model built for reliable end-to-end programming tasks over long contexts.

Claude Fable 5

文字使用中

claude-fable-5

An Anthropic model designed for autonomous knowledge work and end-to-end coding tasks.

Qwen3.7 Plus

文字使用中

qwen3.7-plus

A cost-effective Qwen3.7 model for general-purpose, coding, and agentic workloads.

Claude Opus 4.8

文字使用中

claude-opus-4.8

Anthropic's most capable generally available Opus model for demanding professional and agentic work.

Qwen3.7 Max

文字使用中

qwen3.7-max

Alibaba's flagship Qwen3.7 model for coding, productivity, and agent-centric workloads.

Gemini 3.5 Flash

文字使用中

gemini-3.5-flash

A high-efficiency Gemini model that targets strong coding and reasoning at Flash-tier speed and cost.

Gemini 3.1 Flash Lite

文字使用中

gemini-3.1-flash-lite

Google's high-efficiency Gemini model for low-latency, high-volume workloads and lightweight agents.

Qwen3.6 35B A3B

文字使用中

qwen3.6-35b-a3b

An open-weight Qwen mixture-of-experts model designed for efficient multimodal reasoning.

Qwen3.6 27B

文字使用中

qwen3.6-27b

A dense 27-billion-parameter Qwen model for general-purpose and multimodal tasks.

GPT-5.5

文字使用中

gpt-5.5

OpenAI's frontier model for complex professional workloads, with an emphasis on reliability and token efficiency.

DeepSeek V4 Flash

文字使用中

deepseek-v4-flash

An efficiency-focused DeepSeek mixture-of-experts model for fast inference and long-context work.

DeepSeek V4 Pro

文字使用中

deepseek-v4-pro

A large-scale DeepSeek mixture-of-experts model for advanced reasoning, coding, and agent workflows.

Kimi K2.6

文字使用中

kimi-k2.6

A Kimi model designed for long-horizon coding, interface generation, and multi-agent orchestration.

Claude Opus 4.7

文字使用中

claude-opus-4.7

An Opus model built for long-running, asynchronous agents and complex coding workflows.

GLM 5.1

文字使用中

glm-5.1

A GLM model focused on stronger coding performance and sustained long-horizon execution.

Qwen3.6 Plus

文字使用中

qwen3.6-plus

A scalable Qwen model combining efficient attention with sparse expert routing for high-performance inference.

GPT-5.4 Mini

文字使用中

gpt-5.4-mini

An efficient GPT-5.4 model optimized for high-throughput reasoning, coding, and agent workloads.

GPT-5.4 Nano

文字使用中

gpt-5.4-nano

The lightest GPT-5.4 variant, optimized for speed-critical, high-volume tasks.

GPT-5.4

文字使用中

gpt-5.4

OpenAI's frontier model combining general-purpose reasoning with advanced coding and agent capabilities.

Qwen3.5-Flash

文字使用中

qwen3.5-flash

An efficient Qwen Flash model combining linear attention with sparse mixture-of-experts routing.

Gemini 3.1 Pro Preview

文字使用中

gemini-3.1-pro-preview

Google's frontier Gemini reasoning model for complex software engineering and agentic workflows.

Claude Sonnet 4.6

文字使用中

claude-sonnet-4.6

A high-capability Sonnet model for iterative development, complex codebases, and professional workflows.

GLM 5

文字使用中

glm-5

Z.ai's flagship open GLM model for complex systems design and long-horizon agent workflows.

Claude Opus 4.6

文字使用中

claude-opus-4.6

An Opus model designed for advanced coding and long-running professional workflows.

Kimi K2.5

文字使用中

kimi-k2.5

A Kimi model focused on visual coding and coordinated agent workflows.

GLM 4.7 Flash

文字使用中

glm-4.7-flash

An efficient GLM model balancing coding performance, long-horizon planning, and inference cost.

GLM 4.7

文字使用中

glm-4.7

A flagship GLM model with improved programming and more stable multi-step reasoning.

Gemini 3 Flash Preview

文字使用中

gemini-3-flash-preview

A high-speed Gemini reasoning model for agentic workflows, multi-turn chat, and coding assistance.

GPT-5.2

文字使用中

gpt-5.2

A frontier GPT-5 model focused on stronger agentic execution and long-context performance.

DeepSeek V3.2

文字使用中

deepseek-v3.2

A DeepSeek model balancing computational efficiency with reasoning and agentic tool use.

Claude Opus 4.5

文字使用中

claude-opus-4.5

Anthropic's Opus 4.5 frontier model for complex software engineering, agents, and long-horizon computer use.

Kimi K2 Thinking

文字使用中

kimi-k2-thinking

An open Kimi reasoning model designed for agentic, long-horizon problem solving.

Claude Haiku 4.5

文字使用中

claude-haiku-4.5

Anthropic's fast, efficient Haiku model for responsive applications and high-volume workloads.

GLM 4.6

文字使用中

glm-4.6

A long-context GLM model designed to handle more complex reasoning and coding workloads.

Claude Sonnet 4.5

文字使用中

claude-sonnet-4.5

Anthropic's Sonnet 4.5 model optimized for real-world agents and coding workflows.

Qwen3 Next 80B A3B Instruct

文字使用中

qwen3-next-80b-a3b-instruct

An instruction-tuned Qwen chat model optimized for fast, stable responses across reasoning, coding, and multilingual tasks.

Kimi K2 0905

文字使用中

kimi-k2-0905

The September update to Kimi K2, a mixture-of-experts model built for agentic intelligence.

DeepSeek V3.1

文字使用中

deepseek-v3.1

A hybrid DeepSeek reasoning model that supports both thinking and direct-response modes.

GPT-5

文字使用中

gpt-5

OpenAI's advanced GPT-5 model for complex reasoning, coding, and instruction-following workloads.

GPT-5 Mini

文字使用中

gpt-5-mini

A compact GPT-5 model for lighter-weight reasoning with lower latency and cost.

Gemini 2.5 Flash Lite

文字使用中

gemini-2.5-flash-lite

A lightweight Gemini reasoning model optimized for low latency, high throughput, and cost efficiency.

Qwen3 235B A22B Instruct 2507

文字使用中

qwen3-235b-a22b-instruct-2507

A multilingual Qwen mixture-of-experts model tuned for instruction following and text generation.

Gemini 2.5 Flash

文字使用中

gemini-2.5-flash

Google's workhorse Gemini model for advanced reasoning, coding, mathematics, and scientific tasks.

Gemini 2.5 Pro

文字使用中

gemini-2.5-pro

A high-capability Gemini model for advanced reasoning, coding, mathematics, and scientific work.

R1 0528

文字使用中

r1-0528

A May 2025 update to DeepSeek R1 focused on open reasoning and complex problem solving.

DeepSeek V3 0324

文字使用中

deepseek-v3-0324

A March 2025 update to DeepSeek's flagship mixture-of-experts chat model.

GPT-4o mini

文字使用中

gpt-4o-mini

A compact GPT-4o model designed for fast, affordable general-purpose and multimodal tasks.

GPT-4o

文字使用中

gpt-4o

OpenAI's versatile, high-intelligence flagship model for general-purpose text and vision tasks.