Skip to content
NexInferNexInfer Docs
English

Anthropic Messages

When support is released, Claude Code and the Anthropic SDK should use the native Messages protocol. Do not configure an Anthropic client with the OpenAI /v1 base URL.

Endpoint and authentication

Section titled “Endpoint and authentication”
POST https://api.nexinfer.com/v1/messages
Terminal window
curl https://api.nexinfer.com/v1/messages \
  -H "x-api-key: $NEXINFER_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "YOUR_CLAUDE_MODEL_ID",
    "max_tokens": 256,
    "messages": [{"role":"user","content":"Reply with OK."}]
  }'

max_tokens is required by the Messages API. The selected model must be within the key’s allowed scope.

System instructions

Section titled “System instructions”

Messages uses a top-level system field. Do not add a role: "system" entry to the messages array:

{
  "model": "YOUR_CLAUDE_MODEL_ID",
  "max_tokens": 256,
  "system": "Answer concisely.",
  "messages": [{"role":"user","content":"Explain health checks."}]
}

NexInfer does not intentionally inject or override the system prompt.

Streaming

Section titled “Streaming”

Set "stream": true to receive SSE. Handle Anthropic event types such as message_start, content_block_delta, message_delta, and message_stop; do not parse them as OpenAI streaming chunks.

Tool use

Section titled “Tool use”

Declare tools and their input schemas in tools. When Claude returns a tool_use content block, execute the tool and send a matching tool_result in a later user message.

{
  "name": "get_weather",
  "description": "Get weather for a city",
  "input_schema": {
    "type": "object",
    "properties": {"city": {"type": "string"}},
    "required": ["city"]
  }
}

Always validate model-generated tool arguments. Add confirmation and idempotency controls for operations with side effects.

Prompt caching

Section titled “Prompt caching”

Models with prompt-caching support can accept cache_control on system, message content, tool definitions, and other supported blocks. Availability, minimum cacheable content, and billing depend on the model and model provider.

NexInfer does not intentionally remove cache_control; this does not imply identical caching support across every Claude model.

Extended thinking

Section titled “Extended thinking”

Models that provide the capability can accept a thinking configuration. Its constraints interact with max_tokens, tool use, and model versions; follow Anthropic’s requirements for the selected model.

NexInfer does not intentionally change thinking or reduce its configured level. Unsupported combinations may still return a model-provider 400.

Troubleshooting

Section titled “Troubleshooting”
  • 400: check max_tokens, top-level system, content blocks, and model capabilities.
  • 401/403: check x-api-key, model permission, and the base URL.
  • Stream parsing failure: use Anthropic SSE event types, not OpenAI chunk shapes.
  • Broken tool loop: verify that tool_use.id matches tool_result.tool_use_id.

Official references: Messages API · Streaming · Tool use · Prompt caching · Extended thinking