> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.beatapi.io/text-api/claude-sonnet-5-5/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.beatapi.io/_mcp/server. # Claude Sonnet 5.5 > Claude Sonnet 5.5 model ID, context and output limits, token pricing, and a Claude Code configuration example on BeatAPI. Claude Sonnet 5.5 is available on BeatAPI under the exact model ID `claude-sonnet-5-5`. It supports coding and agent workflows with a 1M-token context window and up to 128K output tokens. ## Model details | Setting | Value | | ---------------- | ---------------------------------- | | Model ID | `claude-sonnet-5-5` | | Context window | 1,000,000 tokens | | Maximum output | 128,000 tokens | | Default thinking | Adaptive | | Billing | Actual token usage, settled in USD | ## Token pricing Prices are USD per **1 million tokens**, checked on September 30, 2026. | Token type | BeatAPI price | | ---------------------- | ------------: | | Input | \$1.00 | | Output | \$5.00 | | Cached input | \$0.10 | | Cache write, 5 minutes | \$1.25 | | Cache write, 1 hour | \$2.00 | These rates apply across the full 1M context window; there is no long-context premium. Cache rates apply when the corresponding cache usage is reported. Review the [current price table](https://beatapi.io/pricing) before budgeting a workload. ## Configuration example: Claude Code Add these values to the `env` object in your Claude Code `settings.json`. Preserve existing settings, replace the key placeholder, and restart the client. ```json { "env": { "ANTHROPIC_BASE_URL": "https://api.beatapi.io", "ANTHROPIC_AUTH_TOKEN": "", "ANTHROPIC_MODEL": "claude-sonnet-5-5" } } ``` The base URL has no `/v1` suffix. Keep the client's default adaptive thinking and tool configuration. See the [complete Claude Code setup guide](/integrations/claude-code) for installation, configuration, and common commands. ## Account and usage Use your BeatAPI key and account balance. Model availability follows the key's enabled group and current capacity. Dashboard usage logs show the request ID, model, token totals, status, and settled amount. Prices are based on the reported usage of completed requests. Model specifications: [Anthropic Sonnet 5.5 overview](https://platform.claude.com/docs/en/models/sonnet-5-5/overview). > Claude Sonnet 5.5 model ID, context and output limits, token pricing, and a Claude Code configuration example on BeatAPI.