Anthropic Messages

POST /v1/messages is compatible with the Anthropic Messages API. Use it when your code already runs on the Anthropic SDK, or with tools that speak the Anthropic format, such as Claude Code. It serves Claude models only. For every other chat model use /v1/chat/completions.

Models

Model id	Price
`claude-opus-5.5`	$5.40 / $27.00 per 1M tokens
`claude-sonnet-5`	$3.24 / $16.20 per 1M tokens
`claude-fable-5.1`	$10.80 / $54.00 per 1M tokens

A non-Claude model id on this endpoint is rejected with an error.

Request

http

POST https://jantaris.com/v1/messages
x-api-key: sk-jt-...
anthropic-version: 2023-06-01
Content-Type: application/json

The anthropic-version: 2023-06-01 header is required. The official SDKs send it automatically. The key can go in x-api-key or Authorization: Bearer (Authentication).

Field	Type	Required	Description
`model`	string	yes	Claude model id
`max_tokens`	integer	yes	Upper limit for generated tokens
`messages`	array	yes	Alternating `user` and `assistant` turns in Anthropic format
`system`	string or array	no	System prompt
`stream`	boolean	no	`true` returns Server-Sent Events in Anthropic format
`temperature`	number	no	Sampling temperature
`tools`	array	no	Tool definitions in Anthropic format

Basic call

bash

curl https://jantaris.com/v1/messages \
  -H "x-api-key: $JANTARIS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5.5",
    "max_tokens": 1024,
    "system": "You are a concise code reviewer.",
    "messages": [{"role": "user", "content": "Review: def add(a, b): return a - b"}]
  }'

python

# pip install anthropic
import os
from anthropic import Anthropic

client = Anthropic(base_url="https://jantaris.com", api_key=os.environ["JANTARIS_API_KEY"])

msg = client.messages.create(
    model="claude-opus-5.5",
    max_tokens=1024,
    system="You are a concise code reviewer.",
    messages=[{"role": "user", "content": "Review: def add(a, b): return a - b"}],
)
print(msg.content[0].text)
print(msg.usage)

javascript

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

const client = new Anthropic({ baseURL: "https://jantaris.com", apiKey: process.env.JANTARIS_API_KEY });

const msg = await client.messages.create({
  model: "claude-opus-5.5",
  max_tokens: 1024,
  system: "You are a concise code reviewer.",
  messages: [{ role: "user", content: "Review: def add(a, b): return a - b" }],
});
console.log(msg.content[0].text);

Note the base URL for the Anthropic SDK: https://jantaris.com, without /v1. The SDK appends /v1/messages itself.

Response

json

{
  "id": "msg_...",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-5.5",
  "content": [{ "type": "text", "text": "The function subtracts instead of adding..." }],
  "stop_reason": "end_turn",
  "usage": { "input_tokens": 31, "output_tokens": 57 }
}

Streaming

With stream: true the response is a stream of Anthropic events (message_start, content_block_delta, message_stop and others).

bash

curl -N https://jantaris.com/v1/messages \
  -H "x-api-key: $JANTARIS_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-5", "max_tokens": 512, "stream": true, "messages": [{"role": "user", "content": "Explain SSE in two sentences."}]}'

python

with client.messages.stream(
    model="claude-sonnet-5",
    max_tokens=512,
    messages=[{"role": "user", "content": "Explain SSE in two sentences."}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

javascript

const stream = client.messages.stream({
  model: "claude-sonnet-5",
  max_tokens: 512,
  messages: [{ role: "user", content: "Explain SSE in two sentences." }],
});
stream.on("text", (text) => process.stdout.write(text));
await stream.finalMessage();

Tool use

Tools follow the Anthropic format: name, description, input_schema. The model answers with a tool_use block, you reply with a tool_result block.

python

tools = [{
    "name": "get_order_status",
    "description": "Returns the shipping status of an order",
    "input_schema": {
        "type": "object",
        "properties": {"order_id": {"type": "string"}},
        "required": ["order_id"],
    },
}]

messages = [{"role": "user", "content": "Where is order A-1042?"}]
first = client.messages.create(model="claude-sonnet-5", max_tokens=1024, tools=tools, messages=messages)

if first.stop_reason == "tool_use":
    call = next(b for b in first.content if b.type == "tool_use")
    result = {"order_id": call.input["order_id"], "status": "shipped"}  # your code here
    messages += [
        {"role": "assistant", "content": first.content},
        {"role": "user", "content": [{"type": "tool_result", "tool_use_id": call.id, "content": str(result)}]},
    ]
    final = client.messages.create(model="claude-sonnet-5", max_tokens=1024, tools=tools, messages=messages)
    print(final.content[0].text)

Errors

Errors on this endpoint use the Anthropic format, so the Anthropic SDK raises its usual exceptions:

json

{ "type": "error", "error": { "type": "authentication_error", "message": "Invalid API key." } }

HTTP status codes are the same as elsewhere in the API. The default rate limit is 600 requests per minute per key. See Errors.

Which endpoint to pick

You use	Endpoint
Anthropic SDK, Claude Code	`/v1/messages`
OpenAI SDK, Cursor, Cline, Continue, n8n, Make	`/v1/chat/completions`
Claude from the OpenAI SDK	`/v1/chat/completions` with `model: "claude-..."`