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-5 (balanced performance)
  • OpenAI: openai:gpt-5.5 (latest GPT)
  • OpenRouter: openrouter:z-ai/glm-5.2 (open source)
  • Amazon Bedrock: bedrock:us.anthropic.claude-sonnet-4-5-20250929-v1:0

​
Anthropic

Model IDNameInput ContextOutputCapabilities
anthropic:claude-fable-5Claude Fable 51,000,000128,000Reasoning, Vision, Tools
anthropic:claude-sonnet-5Claude Sonnet 51,000,000128,000Reasoning, Vision, Tools
anthropic:claude-opus-4-8Claude Opus 4.81,000,000128,000Reasoning, Vision, Tools
anthropic:claude-haiku-4-5Claude Haiku 4.5 (latest)200,00064,000Reasoning, Vision, Tools

​
OpenAI

Model IDNameInput ContextOutputCapabilities
openai:gpt-5.5GPT-5.5922,000128,000Reasoning, Vision, Tools
openai:gpt-5.5-proGPT-5.5 Pro922,000128,000Reasoning, Vision, Tools
openai:gpt-5.4-nanoGPT-5.4 nano272,000128,000Reasoning, Vision, Tools
openai:gpt-5.4-miniGPT-5.4 mini272,000128,000Reasoning, Vision, Tools
openai:gpt-5.3-codexGPT-5.3 Codex272,000128,000Reasoning, Vision, Tools
openai:gpt-5.3-codex-sparkGPT-5.3 Codex Spark100,00032,000Reasoning, Vision, Tools
openai:gpt-5.3-chat-latestGPT-5.3 Chat (latest)128,00016,384Vision, Tools
openai:gpt-5.1-codex-maxGPT-5.1 Codex Max272,000128,000Reasoning, Vision, Tools
openai:gpt-5.1-codex-miniGPT-5.1 Codex mini272,000128,000Reasoning, Vision, Tools

​
OpenRouter

Model IDNameInput ContextOutputCapabilities
openrouter:z-ai/glm-5.2GLM-5.21,048,57632,768Reasoning, Tools
openrouter:z-ai/glm-5v-turboGLM-5V-Turbo202,752131,072Reasoning, Vision, Tools
openrouter:x-ai/grok-4.3Grok 4.31,000,0001,000,000Reasoning, Vision, Tools
openrouter:deepseek/deepseek-v4-proDeepSeek V4 Pro1,048,576384,000Reasoning, Tools
openrouter:deepseek/deepseek-v4-flashDeepSeek V4 Flash1,000,00065,536Reasoning, Tools
openrouter:qwen/qwen3.7-maxQwen3.7 Max1,000,00065,536Reasoning, Tools
openrouter:qwen/qwen3.7-plusQwen3.7 Plus1,000,00065,536Reasoning, Vision, Tools
openrouter:google/gemini-3.5-flashGemini 3.5 Flash1,048,57665,536Reasoning, Vision, Tools
openrouter:google/gemini-3.1-pro-previewGemini 3.1 Pro Preview1,048,57665,536Reasoning, Vision, Tools
openrouter:minimax/minimax-m3MiniMax-M3524,288512,000Reasoning, Vision, Tools
openrouter:google/gemini-3-flash-previewGemini 3 Flash Preview1,048,57665,535Reasoning, Vision, Tools
openrouter:moonshotai/kimi-k2.6Kimi K2.6262,144262,144Reasoning, Vision, Tools

​
Amazon Bedrock

Bedrock model IDs are passed through unchanged and are not validated against the static registry. Use any model ID supported by your AWS account and region.
Model ID (example)Notes
bedrock:us.anthropic.claude-sonnet-4-5-20250929-v1:0Claude Sonnet 4.5 (US cross-region inference profile)
bedrock:anthropic.claude-3-5-sonnet-20241022-v2:0Claude 3.5 Sonnet v2
bedrock:anthropic.claude-3-haiku-20240307-v1:0Claude 3 Haiku
bedrock:meta.llama3-70b-instruct-v1:0Llama 3 70B Instruct
bedrock:mistral.mistral-large-2402-v1:0Mistral Large
bedrock:us.amazon.nova-pro-v1:0Amazon Nova Pro
See the Amazon Bedrock model catalog for the full list. Model availability depends on the AWS region and on the model access granted in your account. Authentication uses standard AWS environment variables (AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY / AWS_REGION, optional AWS_SESSION_TOKEN) or AWS_BEARER_TOKEN_BEDROCK. See the Model Configuration guide for details.

​
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-5-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-5
---
Or override via CLI: 
agentuse run agent.agentuse -m openai:gpt-5.5
agentuse run agent.agentuse -m ollama:glm-5-flash:q4_K_M