Anthropic Claude¶
Backend.AI GO integrates with Anthropic's Claude series of models, known for their advanced reasoning capabilities, long context windows, and nuanced writing style.
Supported Models¶
You can use the following model families through the Anthropic API:
-
Claude Opus 4.8: Anthropic's most capable model, designed for highly complex tasks and deep reasoning.
-
Claude Sonnet 4.6: A balance of speed and high-level reasoning for everyday work.
-
Claude Haiku 4.5: Near-instant responsiveness, perfect for simple tasks and high-volume processing.
Getting an API Key¶
To use Claude models in Backend.AI GO, you need an API key from the Claude Platform.
-
Visit the Claude Platform.
-
Create an account and set up your billing information.
-
Navigate to the API Keys section.
-
Create a new key and copy it safely.
Setup in Backend.AI GO¶
-
Go to the Providers tab in the sidebar.
-
Click Add provider and select Anthropic.
-
Paste your API Key.
-
Backend.AI GO will automatically fetch the list of available models. In the model selection step, the known Claude defaults are pre-checked; adjust the selection if needed and click Finish, and the chosen models appear in the chat model selector without opening the provider card. You can also adjust the selection later in your library.
The Anthropic list is a short built-in one, so current Claude models may be missing from it. Add a missing model by its ID, either in the model selection step or later on the provider card; see Adding a Model by Its ID.
Key Features¶
Long Context Windows¶
Claude models are famous for their large context windows (up to 200,000 tokens), allowing you to upload and discuss very long documents or entire codebases.
Thinking Blocks¶
Backend.AI GO's chat interface is optimized to display Claude's internal "thinking" or reasoning traces (for supported versions), providing better transparency into how the model reached its conclusion.
Note: Using Anthropic models requires an active internet connection and will incur costs based on Anthropic's pricing.