# Anthropic SDK and Claude Code

`POST /v1/messages` takes a request in Anthropic Messages form and answers in it, whole or streamed, so the Anthropic SDK and Claude Code work with a new address and key. The model comes from the same catalogue as on the [OpenAI wire](/docs/model-api-requests) and is chosen by the same `provider` and `models` (see [Routing and caching](/docs/model-api-routing)).

## Address and key

The Anthropic SDK and Claude Code append `/v1/messages` themselves, so they take the address without a path: `https://api.samreshuuu.ru`. The Anthropic SDK sends the Model API key in `x-api-key`, Claude Code in `Authorization: Bearer`; both are accepted. The key is issued in the [developer console](https://platform.samreshuuu.ru).

## Claude Code

```bash
export ANTHROPIC_BASE_URL="https://api.samreshuuu.ru"
export ANTHROPIC_AUTH_TOKEN="$SAMRESHUUU_API_KEY"
export ANTHROPIC_MODEL="deepseek/deepseek-v4.1-flash"
export ANTHROPIC_DEFAULT_OPUS_MODEL="deepseek/deepseek-v4.1-flash"
export ANTHROPIC_DEFAULT_SONNET_MODEL="deepseek/deepseek-v4.1-flash"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="deepseek/deepseek-v4.1-flash"
claude
```

Besides `ANTHROPIC_MODEL`, Claude Code calls the Opus, Sonnet and Haiku tiers itself (Haiku for background tasks) by their Anthropic names. Our catalogue has no such ids, so the snippet sets `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL` and `ANTHROPIC_DEFAULT_HAIKU_MODEL` to a catalogue model id; without them background calls get `model_not_found`. Any of them can be another model from the [Models](/models) page, a cheap one for the Haiku tier for example.

Claude Code sends the `x-claude-code-session-id` header: it keeps the calls of one session in one [cache](/docs/model-api-routing#prompt-caching).

## Messages fields

| Field | What happens to it | Note |
| --- | --- | --- |
| `messages` | passed to the host as sent |  |
| `system` | passed to the host as sent |  |
| `tools` | passed to the host as sent |  |
| `tool_choice` | passed to the host as sent |  |
| `temperature` | passed to the host as sent |  |
| `top_p` | passed to the host as sent |  |
| `top_k` | passed to the host as sent |  |
| `stop_sequences` | passed to the host as sent |  |
| `thinking` | passed to the host as sent |  |
| `output_config` | passed to the host as sent |  |
| `output_format` | passed to the host as sent |  |
| `cache_control` | passed to the host as sent |  |
| `context_management` | passed to the host as sent |  |
| `model` | replaced: read by this API, the host gets this API's value |  |
| `max_tokens` | replaced: read by this API, the host gets this API's value |  |
| `stream` | replaced: read by this API, the host gets this API's value |  |
| `metadata` | replaced: read by this API, the host gets this API's value |  |
| `models` | replaced: read by this API, the host gets this API's value |  |
| `provider` | replaced: read by this API, the host gets this API's value |  |
| `plugins` | replaced: read by this API, the host gets this API's value |  |
| `service_tier` | accepted and dropped |  |
| `mcp_servers` | refused with 400 | mcp_servers and container run on Anthropic's own servers, which this API does not reach. |
| `container` | refused with 400 | mcp_servers and container run on Anthropic's own servers, which this API does not reach. |
| `extra_body` | refused with 400 | extra_body, extra_headers, extra_query and timeout are SDK request options, merged by the SDK before the request is sent; send their fields at the top level of the body. |
| `extra_headers` | refused with 400 | extra_body, extra_headers, extra_query and timeout are SDK request options, merged by the SDK before the request is sent; send their fields at the top level of the body. |
| `extra_query` | refused with 400 | extra_body, extra_headers, extra_query and timeout are SDK request options, merged by the SDK before the request is sent; send their fields at the top level of the body. |
| `timeout` | refused with 400 | extra_body, extra_headers, extra_query and timeout are SDK request options, merged by the SDK before the request is sent; send their fields at the top level of the body. |

How the body travels depends on the host that answers (the host's `wires` in `GET /v1/models`):

- The host speaks Messages itself (`messages` in `wires`). It gets the body fields this API knows, with our `model`, `max_tokens` and conversation key in `metadata.user_id`. `cache_control` marks go through as they are, less the `ttl` and `scope` keys.
- The host speaks only Chat Completions. The body is translated. On top of the table, `top_k`, a top-level `cache_control`, `context_management`, `citations` on text blocks, `signature` of thinking blocks and `redacted_thinking` blocks are not applied, and `document`, `search_result` and `container_upload` blocks and an image with a `file` source are refused with `400`. The text blocks of one message are joined with a blank line, and the thinking of an assistant turn goes before its text and tool calls, the only order a Chat Completions message has.

`tools` and `tool_choice` travel as Anthropic tools (`tool_use`, `tool_result`). You run the tools. Anthropic server tools (`web_search`, `bash`, `text_editor`, `computer` and others), `mcp_servers` and `container` run on Anthropic's servers, which this API does not reach, and are refused with `400`.

## The anthropic-beta header

An `anthropic-beta` value is either passed to a host that speaks Messages or dropped. An unknown value is dropped, not refused: Claude Code adds betas with every release, and a call must not break on them.

| anthropic-beta value | What happens to it |
| --- | --- |
| `claude-code-20250219` | passed to the host as sent |
| `interleaved-thinking-2025-05-14` | passed to the host as sent |
| `fine-grained-tool-streaming-2025-05-14` | passed to the host as sent |
| `token-efficient-tools-2025-02-19` | passed to the host as sent |
| `prompt-caching-2024-07-31` | passed to the host as sent |
| `context-management-2025-06-27` | passed to the host as sent |
| `effort-2025-11-24` | passed to the host as sent |
| `structured-outputs-2025-11-13` | passed to the host as sent |
| `context-1m-2025-08-07` | accepted and dropped |
| `extended-cache-ttl-2025-04-11` | accepted and dropped |
| `fast-mode-2026-02-01` | accepted and dropped |
| `output-128k-2025-02-19` | accepted and dropped |
| `output-300k-2026-03-24` | accepted and dropped |
| `oauth-2025-04-20` | accepted and dropped |
| `prompt-caching-scope-2026-01-05` | accepted and dropped |
| `advanced-tool-use-2025-11-20` | accepted and dropped |
| `files-api-2025-04-14` | accepted and dropped |
| `mcp-client-2025-11-20` | accepted and dropped |
| `code-execution-2025-08-25` | accepted and dropped |
| `web-search-2025-03-05` | accepted and dropped |
| `web-fetch-2025-09-10` | accepted and dropped |
| `computer-use-2025-11-24` | accepted and dropped |
| `skills-2025-10-02` | accepted and dropped |
| `advisor-tool-2026-03-01` | accepted and dropped |

The betas dropped are those that change the price (the long window, the one-hour cache, fast mode, larger output) and the capabilities of Anthropic's servers (files, MCP, code execution, web search, computer use, skills).

## Answer and cost

The answer's `id` reads `msg_…`, as at Anthropic. `usage` has Anthropic's shape: `input_tokens` (only what was not read from the cache), `output_tokens`, `cache_read_input_tokens`, `cache_creation_input_tokens` and the write split by tier in `cache_creation`, without `cost`. The call id `gen-…` comes in the `x-request-id` header, and with it `GET /v1/generation` returns the cost (see [Accounting and cost](/docs/model-api-requests#accounting-and-cost)).

Besides the minute's `x-ratelimit-*` headers, the answer carries Anthropic's `anthropic-ratelimit-requests-*` and `anthropic-ratelimit-tokens-*` with the reset in RFC 3339 (see [Rate limits](/docs/model-api#rate-limits)). An error comes in Anthropic's form: `{"type": "error", "error": {"type", "message"}, "request_id"}`.

## Counting tokens

`POST /v1/messages/count_tokens` takes a Messages body (`model`, `messages`, `system`, `tools`) and answers `{"input_tokens": n}`, counted the way the call's hold is counted. Nothing is charged; the scope is `models:read`. The Anthropic SDK calls it as `client.messages.count_tokens(...)`.
