Claude Messages

Create a native Claude message with content blocks and stop reasons.

200

{
  "type": "message",
  "id": "msg_example",
  "role": "assistant",
  "stop_reason": "end_turn",
  "content": [
    {
      "type": "text",
      "text": "Hello."
    }
  ]
}

POST /v1/messages

Send the gateway token through x-api-key and set anthropic-version explicitly. Native requests include model and messages; the example explicitly supplies max_tokens, with system instructions at top-level system. The schema preserves the gateway’s optional budget behavior; actual native provider requests should supply a model-supported budget.

Read nonstreaming content[] and check stop_reason. Values other than end_turn require appropriate handling: tool_use is not a final text answer and max_tokens may indicate truncation. With stream: true, use Claude SSE rather than a Chat / Responses event parser.

The native Claude guide and complete TypeScript example include environment variables, run commands, and failure behavior. Only common text fields are expanded here; native extensions and conversion paths depend on channel support. /v1/messages/count_tokens is not enabled.

Verified revision: d851a5faa49a00abaafd27bf91b311506fbfbc52. Source files are recorded in this operation’s x-source-files.

The Python native SSE and tool-loop example offers text and tool modes, preserving native result association and signatures.

阅读中文

Native cache and reasoning controls

The project DTO represents request-level and content-block cache_control, plus top-level thinking, output_config, and context_management. Actual support, TTLs, budgets, and modes depend on the channel and model. Claude context_management is a protocol-specific object and is not copied directly during Responses conversion; identical names do not imply equivalent semantics.

Native cache usage may contain usage.cache_read_input_tokens and cache_creation_input_tokens. Caching, reasoning, and compaction state do not automatically increase the model’s context window. Preserve thinking / signature / redacted_thinking continuation items according to the native protocol.

Added fields verified against revision 30a6d88a4.

Prompt caching · Reasoning · Context management

Authorizations

ClaudeApiKeyBearerAuth

x-api-key · string · header · required

网关令牌 / Gateway token

Headers

anthropic-version · string · default: 2023-06-01

适配器缺省版本；建议显式发送 / Adapter fallback version; send explicitly.

Body

application/json

model · string · required

Minimum string length: 1

Example:

"YOUR_MODEL_ID"

messages · object[] · required

Minimum array length: 1

Show child attributes

max_tokens · integer

输出预算，实际范围依赖模型；调用原生供应商时应显式设置 / Output budget; model limits apply. Set explicitly for native provider requests.

Required range: 0 <= x <= 1073741823

Example:

256

system · string object[]

stream · boolean · default: false

tools · object[]

Show child attributes

cache_control · object

原生缓存控制；依赖渠道，TTL 与断点限制不能跨供应商假定一致 / Native cache control; channel dependent, TTL and breakpoint limits vary

Example:

{ "type": "ephemeral" }

thinking · object

原生推理配置；模式与预算由目标模型决定 / Native reasoning configuration; target model determines modes and budgets

output_config · object

原生输出配置，包含条件支持的 effort / Native output configuration, including conditional effort support

context_management · object

Claude 专用上下文编辑对象；Claude 转 Responses 不直接复制 / Claude-specific context editing; not copied directly into Responses

Response

200

application/json

检查原生完成状态及内容 / Check native completion status and content.

id · string

type · string

role · string

model · string

stop_reason · string | null

content · object[]

Show child attributes

usage · object

Show child attributes