openclaw models: Model Management Command Guide

Command Overview

The openclaw models command manages all model configurations in OpenClaw, including viewing available models, testing performance, setting parameters, and choosing the default model.

View Model List

openclaw models list

Models:
  Name            Provider    Model ID              Status
  ──────────────────────────────────────────────────────────
  main            openai      gpt-4o                ✓ Active
  fast            openai      gpt-4o-mini           ✓ Active
  local           ollama      llama3.1:8b           ✓ Active
  claude          anthropic   claude-sonnet-4-20250514     ✗ No API key
  code            openai      gpt-4o                ✓ Active

Default model: main

View Available Models

See all models offered by a provider:

# View a specific provider
openclaw models available --provider openai

# View all providers
openclaw models available --all

Available models from openai:
  gpt-4o              128k context    $5.00/$15.00 per 1M tokens
  gpt-4o-mini         128k context    $0.15/$0.60 per 1M tokens
  gpt-4-turbo         128k context    $10.00/$30.00 per 1M tokens
  o1                  200k context    $15.00/$60.00 per 1M tokens

Add a Model Configuration

openclaw models add smart-model \
  --provider openai \
  --model gpt-4o \
  --temperature 0.7 \
  --max-tokens 4096

Update a Model Configuration

openclaw models update main --temperature 0.5
openclaw models update main --max-tokens 8192
openclaw models update main --model gpt-4o-mini

Set the Default Model

openclaw models default fast

Test a Model

# Quick test
openclaw models test main

# Detailed test
openclaw models test main --verbose

Testing model: main (openai/gpt-4o)
  ✓ Connection: successful
  ✓ Response time: 1.2s
  ✓ Output quality: verified
  ✓ Streaming: working
  ✓ Token counting: accurate

  Test conversation:
    User: Hello
    AI: Hello! How can I help you today?

  Stats:
    Prompt tokens: 8
    Completion tokens: 10
    Latency: 1,200ms

Benchmark Testing

openclaw models benchmark main --rounds 10

Benchmark: main (openai/gpt-4o) - 10 rounds
  Avg latency: 1,350ms
  Min latency: 850ms
  Max latency: 2,100ms
  P95 latency: 1,900ms
  Avg tokens/sec: 45
  Success rate: 100%

Comparison Testing

openclaw models compare main fast --prompt "Explain relativity"

View Model Costs

openclaw models cost --period 7d

Model Cost Summary (last 7 days):
  main (gpt-4o):        $12.50  (250K tokens)
  fast (gpt-4o-mini):   $0.85   (180K tokens)
  local (llama3.1):     $0.00   (local)
  ──────────────────────────────────────
  Total:                $13.35

Failover Configuration

# Set a fallback model
openclaw models set-fallback main --fallback fast
openclaw models set-fallback fast --fallback local

View the failover chain:

openclaw models fallback-chain main

Fallback chain for 'main':
  main (openai/gpt-4o)
  → fast (openai/gpt-4o-mini)
  → local (ollama/llama3.1)

Delete a Model Configuration

openclaw models remove old-model

Import and Export

openclaw models export models.json
openclaw models import models.json

Summary

openclaw models provides complete model lifecycle management. From discovering available models and configuring parameters to performance testing and cost monitoring, it helps you make the best choices in a multi-model environment.