MonoClaw

Model Catalog

Free models

ModelProviderContextBest for
minimax/minimax-m2.5:freeMiniMax197KGeneral chat
z-ai/glm-4.5-air:freeZ.AI131KChinese, coding
nvidia/nemotron-3-super-120b-a12b:freeNVIDIA262KReasoning
openai/gpt-oss-120b:freeOpenAI131KGeneral purpose
google/gemma-4-26b-a4b-it:freeGoogle262KLightweight tasks
qwen/qwen3-coder:freeQwen262KCoding
meta-llama/llama-3.3-70b-instruct:freeMeta66KGeneral chat

Paid frontier models

ModelProviderInputOutputContextRecommended
anthropic/claude-opus-4.7Anthropic$5/M$25/M1M✅
google/gemini-3-flash-previewGoogle$0.50/M$3/M1M✅
openai/gpt-5.5OpenAI$5/M$30/M1M✅
google/gemini-3.1-pro-previewGoogle$2/M$12/M1M✅
deepseek/deepseek-v4-proDeepSeek$1.74/M$3.48/M1M
openai/gpt-5.5-proOpenAI$30/M$180/M1M
openai/gpt-5.4OpenAI$2.50/M$15/M1M
deepseek/deepseek-v4-flashDeepSeek$0.14/M$0.28/M1M
openai/gpt-5.4-miniOpenAI$0.75/M$4.50/M400K

Pricing per 1M tokens. Subject to change by providers.

Minimum requirements

Mona requires 64,000 tokens of context minimum. All models listed above meet this requirement.

Local models

See the Local LLMs on Mac guide for self-hosted options.

Configuration

Set your default model:

monoclaw config set model.default "anthropic/claude-sonnet-4"

Set a fallback:

monoclaw config set model.fallback "openai/gpt-5.5"

Model aliases

Create shortcuts:

model:
  aliases:
    fast: "openai/gpt-5.4-mini"
    smart: "anthropic/claude-opus-4.7"
    cheap: "deepseek/deepseek-v4-flash"
    chinese: "z-ai/glm-4.5-air"

Use them:

/model fast