ClawCloudClawCloud.sh
How it worksModelsPricingCompareGuidesBlog
Log in
DeployDeploy Now
ClawCloud logoClawCloud

Managed OpenClaw AI assistant hosting on dedicated cloud servers.

Deploy now →
Product
ModelsPricingCompare PlansOpenClaw HostingOpenClaw VPSOpenClaw CloudTelegram BotDiscord BotFeishu BotUse CasesFAQ
Resources
GuidesBlogTopicsOpenClawGitHub
Company
ContactTerms of ServicePrivacy Policy
© 2026 ClawCloud. All rights reserved.

100+ curated AI models for every OpenClaw deployment

ClawCloud gives managed OpenClaw instances a curated model catalog that is ready on day one. Pick a plan, connect your channel, then switch models in chat with /modelinstead of rebuilding config every time.

Deploy with curated modelsHow model switching worksSee pricing
Managed catalog
100+

Curated defaults across frontier, budget, and coding-focused models in managed mode.

Provider families
14 groups

OpenAI, Anthropic, Google, DeepSeek, Mistral, Llama, Grok, Qwen, and more.

Backup models
6 free options

Optional Backup Models addon enables supported :free models as a manual recovery path.

Managed mode

One curated catalog, ready at deploy time

Managed mode is the fastest path for most buyers. ClawCloud provisions the API key, applies the curated model list, tracks usage, and lets you move between supported models in chat without touching provider dashboards.

OpenAI

22

GPT-4.1, GPT-5.3 Codex, o3, o4-mini

Anthropic

8

Claude Haiku 4.5, Sonnet 4.6, Opus 4.6

Google

6

Gemini 2.5 Flash, Flash Lite, 3.1 Pro Preview

xAI

6

Grok 3, Grok 4, Grok Code Fast 1

Meta Llama

4

Llama 3.1, Llama 3.3, Llama 4 Maverick, Scout

Mistral

4

Codestral, Devstral, Mistral Large, Mistral Medium

Qwen

4

Qwen3 coder, max, 235B

DeepSeek

3

DeepSeek Chat V3.1, R1, V3.2

Amazon

2

Nova Premier, Nova Pro

Inception

2

Mercury, Mercury Coder

Bytedance Seed

1

Seed 1.6

Cohere

1

Command R+

Moonshot AI

1

Kimi K2.5

NVIDIA

1

Llama 3.1 Nemotron 70B

BYOK mode

Bring your own Anthropic, OpenAI, or Google key if you want direct provider billing. You keep the same dedicated server and dashboard, but your available models come from the provider tied to that key.

Anthropic

8 curated models

Use your Anthropic key for Claude Haiku, Sonnet 4.6, and Opus variants.

OpenAI

22 curated models

Use your OpenAI key for GPT-4.1, GPT-5.x, o-series, and Codex models.

Google

6 curated models

Use your Google key for Gemini 2.5 and Gemini 3.1 preview models.

Backup Models addon

Backup Models is optional. It does not switch automatically. When credits run low, it gives you supported :freemodels you can move to manually in chat so the bot can keep responding.

  • openai/gpt-oss-120b:free
  • google/gemma-3-27b-it:free
  • meta-llama/llama-3.3-70b-instruct:free
  • mistralai/mistral-small-3.1-24b-instruct:free
  • deepseek/deepseek-r1-0528:free
  • qwen/qwen3-coder:free

How model switching works for customers

The sales advantage here is speed: customers do not need to redeploy just to test a different model family. Managed mode keeps the catalog ready and switching happens in chat. That lowers friction for evaluation, cost control, and recovery when a cheaper or free option is good enough.

Test a stronger model for hard prompts without changing server config.
Move to a cheaper model for routine tasks when credits matter more than quality.
Use Backup Models as a manual recovery option instead of leaving the bot offline.

Best next steps

Switch AI models in chatUnderstand credits and recovery optionsBYOK and Backup Models guideDeploy your OpenClaw instance