Skip to main content

​
Model Reference

This page lists recommended models for AgentUse, organized by provider.
Note: Other models from these providers may also work. These are the ones we recommend and test against.
Auto-generated: Run pnpm generate:models to update.

​
Quick Reference

Default models:
  • Anthropic: anthropic:claude-sonnet-4-6 (balanced performance)
  • OpenAI: openai:gpt-5.4 (latest GPT)
  • OpenRouter: openrouter:z-ai/glm-4.7 (open source)

​
Anthropic

Model IDNameContextOutputCapabilities
anthropic:claude-opus-4-6Claude Opus 4.6200,000128,000Reasoning, Vision, Tools
anthropic:claude-sonnet-4-6Claude Sonnet 4.6200,00064,000Reasoning, Vision, Tools
anthropic:claude-haiku-4-5Claude Haiku 4.5 (latest)200,00064,000Reasoning, Vision, Tools
anthropic:claude-haiku-4-5-20251001Claude Haiku 4.5200,00064,000Reasoning, Vision, Tools

​
OpenAI

Model IDNameContextOutputCapabilities
openai:gpt-5.4GPT-5.41,050,000128,000Reasoning, Vision, Tools
openai:gpt-5.4-proGPT-5.4 Pro1,050,000128,000Reasoning, Vision, Tools
openai:gpt-5.3-codexGPT-5.3 Codex400,000128,000Reasoning, Vision, Tools
openai:gpt-5.3-codex-sparkGPT-5.3 Codex Spark128,00032,000Reasoning, Vision, Tools
openai:gpt-5.2GPT-5.2400,000128,000Reasoning, Vision, Tools
openai:gpt-5.2-proGPT-5.2 Pro400,000128,000Reasoning, Vision, Tools
openai:gpt-5.2-codexGPT-5.2 Codex400,000128,000Reasoning, Vision, Tools
openai:gpt-5.2-chat-latestGPT-5.2 Chat128,00016,384Reasoning, Vision, Tools
openai:gpt-5.1GPT-5.1400,000128,000Reasoning, Vision, Tools
openai:gpt-5.1-codexGPT-5.1 Codex400,000128,000Reasoning, Vision, Tools
openai:gpt-5.1-codex-maxGPT-5.1 Codex Max400,000128,000Reasoning, Vision, Tools
openai:gpt-5.1-codex-miniGPT-5.1 Codex mini400,000128,000Reasoning, Vision, Tools
openai:gpt-5.1-chat-latestGPT-5.1 Chat128,00016,384Reasoning, Vision, Tools
openai:gpt-5GPT-5400,000128,000Reasoning, Vision, Tools
openai:gpt-5-proGPT-5 Pro400,000272,000Reasoning, Vision, Tools
openai:gpt-5-miniGPT-5 Mini400,000128,000Reasoning, Vision, Tools
openai:gpt-5-nanoGPT-5 Nano400,000128,000Reasoning, Vision, Tools
openai:gpt-5-codexGPT-5-Codex400,000128,000Reasoning, Vision, Tools
openai:gpt-5-chat-latestGPT-5 Chat (latest)400,000128,000Reasoning, Vision

​
OpenRouter

Model IDNameContextOutputCapabilities
openrouter:z-ai/glm-4.7GLM-4.7204,800131,072Reasoning, Tools
openrouter:z-ai/glm-4.7-flashGLM-4.7-Flash200,00065,535Reasoning, Tools
openrouter:z-ai/glm-4.6GLM 4.6200,000128,000Reasoning, Tools
openrouter:z-ai/glm-4.6:exactoGLM 4.6 (exacto)200,000128,000Reasoning, Tools
openrouter:z-ai/glm-4.5GLM 4.5128,00096,000Reasoning, Tools
openrouter:z-ai/glm-4.5vGLM 4.5V64,00016,384Reasoning, Vision, Tools
openrouter:z-ai/glm-4.5-airGLM 4.5 Air128,00096,000Reasoning, Tools
openrouter:z-ai/glm-4.5-air:freeGLM 4.5 Air (free)128,00096,000Reasoning
openrouter:minimax/minimax-m2.1MiniMax M2.1204,800131,072Reasoning, Tools

​
Custom Providers (Local LLMs)

In addition to the built-in providers above, you can connect any OpenAI-compatible endpoint as a custom provider: 
# Add Ollama
agentuse provider add ollama --url http://localhost:11434/v1

# Add LM Studio
agentuse provider add lmstudio --url http://localhost:1234/v1
Then use any model available on those endpoints: 
agentuse run agent.agentuse -m ollama:glm-4.7-flash:q4_K_M
agentuse run agent.agentuse -m ollama:qwen3.5:0.8b
agentuse run agent.agentuse -m lmstudio:qwen/qwen3.5-9b
See Model Configuration for full setup details.

​
Usage

Specify a model in your agent file: 
---
model: anthropic:claude-sonnet-4-6
---
Or override via CLI: 
agentuse run agent.agentuse -m openai:gpt-5.4
agentuse run agent.agentuse -m ollama:glm-4.7-flash:q4_K_M