Providers and models - PrivateClawd

Twelve providers. Which of them you can use depends on whose key pays — see Model and key.

On a key included with your plan, the agent runs through OpenRouter, which is what makes one balance work across model families. Choosing any other provider means supplying a key of your own, and usage on your key is not billed or tracked by us.

The list

Provider	Models in the panel
Anthropic	`claude-sonnet-4.6`, `claude-opus-4.6`, `claude-haiku-4.5`
OpenAI	`gpt-5.6-luna`, `gpt-5.4`, `gpt-5.3-codex`, `gpt-5.2`, `gpt-4.1`
Google Gemini	`gemini-3-flash-preview`, `gemini-3-pro-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`
DeepSeek	`deepseek-chat`, `deepseek-chat-v3.1`, `deepseek-r1`
Groq	`llama-3.3-70b-versatile`, `llama-3.1-8b-instant`
OpenRouter	`openai/gpt-5.6-luna`, `xiaomi/mimo-v2.5`, `z-ai/glm-5.2`, `deepseek/deepseek-v4-pro`, `anthropic/claude-sonnet-4.6`, `openai/gpt-5.3-codex`, `google/gemini-2.5-pro`, `deepseek/deepseek-chat`
Together AI	`meta-llama/llama-4-maverick`, `meta-llama/Llama-3.3-70B-Instruct-Turbo`
Mistral	`mistral-large-latest`, `mistral-medium-latest`, `codestral-latest`
xAI (Grok)	`grok-3`, `grok-3-mini`, `grok-2`
Moonshot (Kimi)	`kimi-k2.5`, `kimi-k2-thinking`
Cerebras	`llama-3.3-70b`, `llama-3.1-8b`
Hugging Face	`meta-llama/Llama-3.3-70B-Instruct`, `meta-llama/Llama-3.1-8B-Instruct`

Recorded on 31 August 2026. Provider and model are both chosen from a list rather than typed, so the dropdown in the panel is what is actually on offer today — this table is a copy of it, and models move faster than documentation.

Changing model

A different model on the same provider takes effect immediately. A different provider, or a different key, needs the agent redeployed. The panel reports which of the two happened rather than guessing — see Model and key.

Last modified on August 31, 2026