Switching Your Agent's AI Model
Learn how to switch your AI agent's model. Compare pricing, performance, and find the best model for your needs.
Your agent comes pre-configured with a great default model, but you can switch anytime to balance cost, speed, and quality.
Why Switch Models?
| Reason | Details |
|---|---|
| š° Save Credits | Budget models cost 10ā20Ć less. For routine tasks, a cheaper model works just as well. |
| ā” Get More Speed | Flash-tier models respond faster, great for quick back-and-forth conversations. |
| š§ Upgrade Quality | For complex writing or reasoning, premium models like Claude Sonnet deliver noticeably better results. |
How to Switch
1. Just tell your agent
The simplest way ā just say it in chat:
You: switch to openrouter/anthropic/claude-sonnet-4.5
ā Agent switches model and confirms
2. Use the /model command
Send a slash command with the model ID:
/model openrouter/minimax/minimax-m2.5
/model openrouter/moonshotai/kimi-k2.5
/model openrouter/anthropic/claude-sonnet-4.5
3. Browse available models
See all models your agent can use:
/models
ā Lists all available models with current pricing
4. Check current model
Not sure which model you're on?
/status
ā Shows current model and session info
Model Naming Format
OpenClaw uses the openrouter/<author>/<slug> format for all OpenRouter models. For example:
# Anthropic models
openrouter/anthropic/claude-sonnet-4.5
openrouter/anthropic/claude-haiku-4.5
# OpenAI models
openrouter/openai/gpt-4.1-mini
openrouter/openai/gpt-4.1-nano
# Other providers
openrouter/moonshotai/kimi-k2.5
openrouter/z-ai/glm-5
openrouter/minimax/minimax-m2.5
# Auto router ā picks the best model for each prompt
openrouter/openrouter/auto
The openrouter/openrouter/auto option automatically selects the most cost-effective model for each message. Great if you want to let OpenRouter optimize for you. Browse all 300+ models at openrouter.ai/models.
Available Models
All models are accessed via OpenRouter. Prices are per 1M tokens (input / output).
| Model | Provider | Input | Output | ~Msgs/$5 | Notes |
|---|---|---|---|---|---|
| MiniMax M2.5 | MiniMax | $0.30 | $1.20 | ~2,800 | DEFAULT ā Excellent quality at the best price |
| Kimi K2.5 | Moonshot AI | $0.23 | $3.00 | ~1,600 | FALLBACK ā Strong reasoning, cheapest input |
| GLM-5 | Z-AI | $0.30 | $2.55 | ~1,500 | Solid performance at a great value |
| GPT-4.1 Mini | OpenAI | $0.40 | $1.60 | ~2,200 | Reliable for straightforward tasks |
| Claude Sonnet 4.5 | Anthropic | $3.00 | $15.00 | ~240 | PREMIUM ā Complex reasoning & analysis |
| Claude Haiku 4.5 | Anthropic | $1.00 | $5.00 | ~720 | Fast Anthropic model for quick tasks |
| Qwen 3.5 Plus | Qwen | $0.40 | $2.40 | ~1,500 | Strong multilingual capabilities |
Estimates assume ~500 input tokens + ~500 output tokens per message. Real usage varies based on conversation length and response size.
BYOK: Use Any OpenRouter Model
On any plan, you can bring your own OpenRouter API key and access hundreds of additional models ā including GPT-4o, Llama 3, Mistral, and more. Credits are billed directly by OpenRouter at their rates.
ā Pro Tip: Start with the Default
Your agent ships with minimax/minimax-m2.5 as primary and moonshotai/kimi-k2.5 as fallback. This combo is carefully chosen for the best balance of cost and quality. Only switch if you have a specific reason ā like needing premium quality for a complex task.