Anthropic Messages

POST/v1/messages

Use an Anthropic Messages-compatible shape for messages and tool calls.

You can authenticate with x-api-key or a Bearer header. The gateway may forward or translate according to the Provider protocol, so field support still depends on the model route.

Core request fields

Field	Type	Required	Description
`model`	string	Yes	A model ID returned by /v1/models.
`max_tokens`	integer	Yes	Maximum number of tokens to generate.
`messages`	array	Yes	Anthropic-style message list.
`system`	string \| array	No	System instructions.
`stream`	boolean	No	Returns Anthropic SSE events when true.
`tools`	array	No	Anthropic-style tool definitions.

Request examples

curl https://api.noxgate.net/v1/messages \
  -H "x-api-key: sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"YOUR_MODEL_ID","max_tokens":256,"messages":[{"role":"user","content":"Hello"}],"stream":false}'

from anthropic import Anthropic

client = Anthropic(api_key="sk-your-api-key", base_url="https://api.noxgate.net/v1")
message = client.messages.create(
    model="YOUR_MODEL_ID", max_tokens=256,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({ apiKey: "sk-your-api-key", baseURL: "https://api.noxgate.net/v1" });
const message = await client.messages.create({
  model: "YOUR_MODEL_ID", max_tokens: 256,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);

Streaming

Streaming preserves Anthropic Messages event types such as message_start, content_block_delta, and message_stop. Errors may arrive in an error event.

curl https://api.noxgate.net/v1/messages \
  -H "x-api-key: sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"YOUR_MODEL_ID","max_tokens":256,"messages":[{"role":"user","content":"Hello"}],"stream":true}'

Successful response

{"id":"msg_example","type":"message","role":"assistant","model":"YOUR_MODEL_ID","content":[{"type":"text","text":"Hello!"}],"stop_reason":"end_turn","usage":{"input_tokens":8,"output_tokens":3}}