Providers & models

BetterClaw supports a wide range of model providers. On the LLM tab of an agent's settings you pick a provider, then a specific model within it. A handful of providers are marked (Recommended) at the top of the list.

Recommended providers

• Anthropic — Claude models, led by Claude Fable 5.
• Google Gemini — Gemini Pro and Flash models.
• OpenAI — GPT and o-series models.
• ChatGPT Subscription — sign in with your ChatGPT plan instead of pasting a key. See Using a ChatGPT subscription.
• OpenRouter — a single key for many models across providers, including a free auto-router tier.

Anthropic models

Anthropic leads the list. The current lineup:

• Claude Fable 5 — the flagship, with a native 1M-token context window.
• Claude Opus 4.8, Opus 4.7, Opus 4.6, Opus 4.5.
• Claude Sonnet 5 — the default model, with native 1M context. Also Sonnet 4.6 (256K), Sonnet 4.6 (1M context) for the extended window, and Sonnet 4.5 / 4.4.
• Claude Haiku 4.5, Haiku 4.4, Haiku 4.3 — fastest and cheapest.

More providers

BetterClaw also supports Cerebras, Cloudflare AI Gateway, DeepSeek, Groq, Hugging Face, Kilocode, Kimi Coding, MiniMax, Mistral, Model Studio (Alibaba), Moonshot AI, NVIDIA, Ollama Cloud, OpenCode, Qianfan, Together AI, Venice, Vercel AI Gateway, Volcengine (Doubao), xAI (Grok), Xiaomi, and Z.AI (GLM).

The exact list of providers and models is shown in the picker when you configure an agent — it's the source of truth.

Custom provider

If your provider isn't listed, choose Custom. You then supply:

• a Model ID (e.g. my-provider/model-name), and
• the API key env var name your model client reads the key from (SCREAMING_SNAKE_CASE, e.g. MY_PROVIDER_API_KEY).

This is the path for self-hosted or bring-your-own endpoints.

Choosing a model

Each provider exposes several models trading off capability, speed, and cost. Larger models (Opus, Pro, GPT) are the most capable; smaller "mini" / "flash" / "haiku" variants are faster and cheaper. Providers with a curated list also offer a Custom model option so you can enter any model id the provider exposes. You can switch models later without re-entering your key.