Claude API
Use Anthropic Claude through SandBase: Opus for the hardest reasoning, Sonnet for everyday coding and agents, Haiku for speed, and Fable for autonomous technical work.
Explore the model lineup
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, classification, compaction, subagents, and browser use. It succeeds Claude Haiku 4.5 with ...
Claude Sonnet 5.5
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features and fixing bugs, with a ...
Claude Opus 5.5
Claude Opus 5.5 is the most powerful model in the Claude 5 family from Anthropic. It excels at complex reasoning, analysis, and creative tasks with superior accuracy and nuance. It supports text, imag...
Claude Fable 5.1
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...
Claude Opus 5
Claude Opus 5 is the most powerful model in the Claude 5 family from Anthropic. It excels at complex reasoning, analysis, and creative tasks with superior accuracy and nuance. It supports text, image,...
Claude Sonnet 5
Claude Sonnet 5 is a Sonnet-class model for high-quality coding, agentic workflows, reasoning, vision, structured outputs, and tool use.
Claude Fable 5
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token ...
Claude Opus 4.8
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context windo...
Claude Sonnet 4.6
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, ...
Claude Haiku 4.5
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s perfor...
Claude Fable 5.2
Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infea...
Model lineup
Context window and positioning from each provider.
| Model | Context | Positioning |
|---|---|---|
| Claude Opus 4.8 | 1000K | Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family |
| Claude Sonnet 4.6 | 1000K | Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work |
| Claude Opus 5 | 1000K | Claude Opus 5 is the most powerful model in the Claude 5 family from Anthropic |
| Claude Fable 5 | 1000K | Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding |
| Claude Haiku 4.5 | 200K | Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of… |
| Claude Sonnet 5 | 1000K | Claude Sonnet 5 is a Sonnet-class model for high-quality coding, agentic workflows, reasoning, vision, structured outputs, and tool use |
| Claude Opus 5.5 | 1000K | Claude Opus 5.5 is the most powerful model in the Claude 5 family from Anthropic |
| Claude Fable 5.1 | 1000K | Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and… |
| Claude Sonnet 5.5 | 1000K | Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade |
| Claude Haiku 5.5 | 1000K | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, classification, compaction, subagents,… |
| Claude Fable 5.2 | 1000K | Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision |
Every current Claude model, one key
SandBase serves Anthropic's Claude models on both the native Messages API (POST /v1/messages) and the OpenAI-compatible POST /v1/chat/completions. Existing Anthropic SDK code works by changing the base URL and key.
The lineup
- Opus (5.5, 5, 4.8): the most capable Claude models for complex reasoning, analysis and long agentic work.
- Sonnet (5.5, 5, 4.6): strong at coding, agents, tool use and structured output, at a lower price than Opus.
- Haiku (5.5, 4.5): small and fast for summarisation, classification, sub-agents and high volume.
- Fable (5.2, 5.1, 5): Anthropic's Mythos-class line for autonomous knowledge work and demanding technical tasks.
Most current Claude models have a 1M-token context window. Older versions are on the Anthropic vendor page. Compare Claude with other providers on Best LLMs for Coding.
Start using Claude API on SandBase
Switch models by changing one field.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Send a chat request
Call the OpenAI-compatible Chat Completions API with model anthropic/claude-sonnet-5.5. Any OpenAI SDK works with base URL https://api.sandbase.ai/v1.
TERMINALcurl https://api.sandbase.ai/v1/chat/completions \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "anthropic/claude-sonnet-5.5", "messages": [{"role": "user", "content": "Explain vector databases in two sentences."}]}' - 03
Or use the Messages API
Claude models are also served on the native Anthropic Messages API.
TERMINALcurl https://api.sandbase.ai/v1/messages \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "anthropic/claude-sonnet-5.5", "max_tokens": 1024, "messages": [{"role": "user", "content": "Explain vector databases in two sentences."}]}' - 04
Connect your AI tools
Use the same key in Claude Code, Codex, Cursor and other clients. See Use in AI tools for setup.
Questions, answered
Can I use the Anthropic SDK with SandBase?
Yes. Point the SDK base URL at https://api.sandbase.ai and use your SandBase key. Both Bearer and x-api-key headers are accepted, and anthropic-version is set by default.
Which Claude model should I use?
Sonnet for most coding and agent work, Opus for the hardest reasoning, Haiku for speed and cost, and Fable for long autonomous technical tasks.
What is the context window?
1M tokens on current Opus, Sonnet, Haiku 5.5 and Fable models; 200K on Haiku 4.5.
Does prompt caching work?
Yes. Cache reads and writes are billed at Anthropic’s cache multipliers; see each model page for prices.
Can I use Claude in Claude Code or other tools?
Yes. See Use in AI tools for setup with Claude Code, Codex, Cursor and other clients.
Build with Claude API.
One key, consistent APIs, and usage-based pricing across every model on this page.