> ## Documentation Index > Fetch the complete documentation index at: https://docs.laozhang.ai/llms.txt > Use this file to discover all available pages before exploring further. # Claude models are back: Opus 5.5, Sonnet 5.5 > From October 18, 2026, 11 Claude models, including Opus 5.5 and Sonnet 5.5, are back on LaoZhang API: prices, token groups, request examples, and limits. Claude models are available on LaoZhang API again from October 18, 2026, at Anthropic's list prices. Call them with a `default`-group API key in the Anthropic Messages or the OpenAI-compatible format, or point Claude Code at LaoZhang API. * **Published:** October 18, 2026 * **Last verified:** October 18, 2026 * **Status:** active; available in the `default` and `claude_code` token groups ## Key details | Item | Details | | - | - | | Models | 11; see [Models and prices](#models-and-prices) below | | Anthropic Messages endpoint | `POST /v1/messages` | | OpenAI-compatible endpoint | `POST /v1/chat/completions` | | Token groups and billing | `default` and `claude_code`, usage-based (per token) | | Price | Same as Anthropic's list prices | | Context window | 1M tokens (200K for `claude-sonnet-4-5-20250929`) | | Output per response | Up to 32,768 tokens | ## Models and prices Prices from LaoZhang API's public pricing as of October 18, 2026, in US dollars per 1M tokens: | Model ID | Input | Output | | - | -: | -: | | `claude-fable-5-1` | \$10 | \$50 | | `claude-fable-5` | \$10 | \$50 | | `claude-opus-5-5` | \$4 | \$20 | | `claude-opus-5` | \$5 | \$25 | | `claude-opus-4-7` | \$5 | \$25 | | `claude-opus-4-6` | \$5 | \$25 | | `claude-sonnet-5-5` | \$2 | \$10 | | `claude-sonnet-5` | \$2 | \$10 | | `claude-sonnet-4-6` | \$3 | \$15 | | `claude-sonnet-4-5-20250929` | \$3 | \$15 | | `claude-haiku-5-5` | \$0.1 | \$0.5 | * Prompt caching is supported. Cache-read prices are in the [model catalog](/en/models#vendor-anthropic), and cache writes cost 1.25× the input price. * When a `claude-haiku-5-5` prompt exceeds 100,000 tokens, counting cache reads and writes, the whole request is billed at \$0.5 input and \$2.5 output. See [tiered pricing](/en/models#tiered-pricing) in the catalog. * Current prices are in the [model catalog](/en/models) and on the [console pricing page](https://api.laozhang.ai/account/pricing). ## Make a request Create an API key in [Token management](https://api.laozhang.ai/token) with the `default` token group and the Usage first (recommended) or Usage-based billing mode, then export it: ```bash theme={null} export LAOZHANG_API_KEY="YOUR_LAOZHANG_API_KEY" ``` ```bash theme={null} curl https://api.laozhang.ai/v1/messages \ -H "Authorization: Bearer $LAOZHANG_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{ "model": "claude-sonnet-5-5", "max_tokens": 1024, "messages": [ {"role": "user", "content": "Explain a database index in one sentence."} ] }' ``` ```bash theme={null} curl https://api.laozhang.ai/v1/chat/completions \ -H "Authorization: Bearer $LAOZHANG_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "claude-sonnet-5-5", "max_tokens": 1024, "messages": [ {"role": "user", "content": "Explain a database index in one sentence."} ] }' ``` * In the Anthropic Messages format, the answer is in the `content[]` blocks whose `type` is `text`. In the OpenAI-compatible format, it is in `choices[0].message.content`. * For streaming, tool use, and prompt caching, see the [Claude protocol](/en/api-reference/claude) reference. * For a complete Claude Code configuration, see [Claude Code setup with LaoZhang API](/en/scenarios/programming/claude-code). * Check token usage and the charge for each request in [call logs](https://api.laozhang.ai/log). ## Current limits Check these differences from Anthropic's own API before you switch: * Each response is capped at 32,768 output tokens. A larger `max_tokens` is reduced to the cap. * `document` content blocks, such as PDFs, are not supported. Extract the text and send it instead. * Anthropic server tools such as `web_search`, `web_fetch`, and `code_execution` are not supported, and requests that declare them return 400. Claude Code's WebSearch tool doesn't work for the same reason. * `/v1/messages/count_tokens`, Message Batches, and the Files API are not available. See [Claude model limits](/en/api-reference/claude#claude-model-limits) for the full list. ## Who this affects * **Applies to:** projects that call Claude models through LaoZhang API, and anyone using Claude Code or the Anthropic SDKs. Any API key in the `default` or `claude_code` group with the Usage first or Usage-based billing mode can call these models. * **Unchanged:** no existing model changed. Integrations that call `glm-5.2` or `deepseek-v4-pro` over Anthropic Messages keep working as they are. ## FAQ ### Why does claude-haiku-4-5 return a 503? `claude-haiku-4-5-20251001` is not one of the 11 models listed. Use `claude-haiku-5-5` instead. Claude Code runs background tasks on that model by default, so set `ANTHROPIC_DEFAULT_HAIKU_MODEL` as shown in [Claude Code setup with LaoZhang API](/en/scenarios/programming/claude-code). ### What should I do about an occasional 529? A 529 means upstream capacity is busy, which can happen at peak times. Retry after a short wait; the Anthropic SDKs retry 529 automatically by default. ### Do I need an Anthropic account? No. Your LaoZhang API key and base URL are all you need. ## Sources and related links * [Anthropic pricing](https://platform.claude.com/docs/en/about-claude/pricing): official list prices and cache multipliers. * [Model catalog](/en/models#vendor-anthropic): current LaoZhang API prices. * [Console pricing](https://api.laozhang.ai/account/pricing): sign in to see the prices that apply to your account. * [Claude protocol: Anthropic Messages API](/en/api-reference/claude) * [Claude Code setup with LaoZhang API](/en/scenarios/programming/claude-code) * [Latest announcements](/en/changelog) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.