Best AI Models in MyClaw

Kimi K3

Moonshot AI

Moonshot AI's 2.8T-parameter flagship model with native vision, a 1M-token context window, long-horizon coding, and agentic knowledge-work capabilities.

Claude Fable 5

Anthropic

Anthropic's most capable generally available model for long-horizon coding, knowledge work, vision, research, and autonomous agents.

Claude Opus 4.8

Anthropic

Anthropic's Claude Opus 4.8 improves on Opus 4.7 across coding, computer use, reasoning, knowledge work, and financial analysis benchmarks.

Claude Sonnet 5

Anthropic

Anthropic's most agentic Sonnet model yet, with strong coding, BrowseComp, OSWorld-Verified, and cost-performance gains over Sonnet 4.6.

Grok 4.5

xAI

xAI's Grok 4.5 model for coding, agentic tasks, knowledge work, fast 80 TPS serving, and cost-efficient engineering workflows.

Meta Muse Spark

Meta

Meta Muse Spark is a native multimodal reasoning model from Meta Superintelligence Labs with tool use, visual chain of thought, and multi-agent Contemplating mode.

GLM-5.2

Z.AI

Z.AI's flagship open-weight model with a solid 1M-token context, 128K maximum output, flexible reasoning effort, and frontier long-horizon coding performance.

GLM-5.1

Z.AI

Z.AI flagship open-weight model for long-horizon coding agents, with 754B parameters, 200K context, 128K max output, and official API pricing.

Kimi K2.6

Moonshot AI

Moonshot AI's multimodal K2 model with 262,144-token context, official CNY token pricing, thinking and non-thinking modes, and strong public benchmark scores for coding, visual, and agent tasks.

MiniMax M3

MiniMax

A frontier open-weight model for coding, tool use, long-context reasoning, and native multimodal agent work.

Qwen 3.5

Alibaba Cloud

Qwen 3.5 model page for benchmark evaluation, Qwen 3.5 vs 3.6 migration checks, and 9B, 27B, and 35B agent workflows.

Gemini 3.5 Flash

Google DeepMind

Google's stable Flash model for frontier agentic coding, long-horizon workflows, multimodal input, and lower-latency production tasks.

Gemini 3.1 Pro

Google DeepMind

Google's preview model for advanced coding, complex reasoning, agent workflows, and multimodal tasks with a 1M-token context window.

Gemma 4

Google DeepMind

Google’s open-weight model family for reasoning, coding, agent workflows, and local multimodal AI across edge devices and workstations.