Anthropic Messages - CometAPI Documentation

POST

messages

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.cometapi.com",
    api_key="<COMETAPI_KEY>",
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system="You are a helpful assistant.",
    messages=[
        {"role": "user", "content": "Hello, world"}
    ],
)

print(message.content[0].text)

{
  "id": "<string>",
  "content": [
    {
      "text": "<string>",
      "thinking": "<string>",
      "signature": "<string>",
      "id": "<string>",
      "name": "<string>",
      "input": {}
    }
  ],
  "model": "<string>",
  "stop_sequence": "<string>",
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 123,
      "ephemeral_1h_input_tokens": 123
    }
  }
}

CometAPI ondersteunt de Anthropic Messages API native en geeft je directe toegang tot Claude-modellen met alle Anthropic-specifieke functies. Gebruik dit endpoint voor Claude-exclusieve mogelijkheden zoals extended thinking, prompt caching en effort control.

Zowel x-api-key als Authorization: Bearer headers worden ondersteund voor authenticatie. De officiële Anthropic SDK’s gebruiken standaard x-api-key.

Snelle start

Om de officiële Anthropic SDK met CometAPI te gebruiken, stel je de base URL in:

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.cometapi.com",
    api_key="<COMETAPI_KEY>",
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)

Extended thinking inschakelen

Schakel Claude’s stapsgewijze redenering in met de parameter thinking. De response bevat thinking content blocks die Claude’s interne redenering tonen vóór het uiteindelijke antwoord.

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=16000,
    thinking={
        "type": "enabled",
        "budget_tokens": 10000,
    },
    messages=[
        {"role": "user", "content": "Prove that there are infinitely many primes."}
    ],
)

for block in message.content:
    if block.type == "thinking":
        print(f"Thinking: {block.thinking[:200]}...")
    elif block.type == "text":
        print(f"Answer: {block.text}")

Thinking vereist een minimum budget_tokens van 1,024. Thinking tokens tellen mee voor je limiet van max_tokens — stel max_tokens hoog genoeg in om zowel thinking als de response te kunnen bevatten.

Prompts cachen

Om latency en kosten bij volgende requests te verlagen, cache je grote system prompts of conversatieprefixen. Voeg cache_control toe aan content blocks die gecachet moeten worden:

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system=[
        {
            "type": "text",
            "text": "You are an expert code reviewer. [Long detailed instructions...]",
            "cache_control": {"type": "ephemeral"},
        }
    ],
    messages=[{"role": "user", "content": "Review this code..."}],
)

Cachegebruik wordt gerapporteerd in het veld usage van de response:

cache_creation_input_tokens — tokens die naar de cache zijn geschreven (gefactureerd tegen een hoger tarief)
cache_read_input_tokens — tokens die uit de cache zijn gelezen (gefactureerd tegen een verlaagd tarief)

Prompt caching vereist minimaal 1,024 tokens in het gecachete content block. Content die korter is dan dit wordt niet gecachet.

Responses streamen

Om responses te streamen met Server-Sent Events (SSE), stel je stream: true in. Events komen in deze volgorde binnen:

message_start — bevat de metadata van het bericht en het initiële usage
content_block_start — markeert het begin van elk content block
content_block_delta — incrementele tekstchunks (text_delta)
content_block_stop — markeert het einde van elk content block
message_delta — definitieve stop_reason en volledige usage
message_stop — geeft het einde van de stream aan

with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=256,
    messages=[{"role": "user", "content": "Hello"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Inspanning beheren

Om te bepalen hoeveel inspanning Claude levert bij het genereren van een response, gebruik je output_config.effort:

message = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=4096,
    messages=[
        {"role": "user", "content": "Summarize this briefly."}
    ],
    output_config={"effort": "low"},  # "low", "medium", or "high"
)

Servertools gebruiken

Claude ondersteunt server-side tools die draaien op de infrastructuur van Anthropic:

Web Fetch
Web Search

Content ophalen en analyseren van URL’s:

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Analyze the content at https://arxiv.org/abs/1512.03385"}
    ],
    tools=[
        {"type": "web_fetch_20250910", "name": "web_fetch", "max_uses": 5}
    ],
)

Zoek op het web naar realtime-informatie:

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "What are the latest developments in AI?"}
    ],
    tools=[
        {"type": "web_search_20250305", "name": "web_search", "max_uses": 5}
    ],
)

Voorbeeld van een response

Een typische response van het Anthropic-endpoint van CometAPI:

{
  "id": "msg_bdrk_01UjHdmSztrL7QYYm7CKBDFB",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello!"
    }
  ],
  "model": "claude-sonnet-4-6",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 19,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 0,
      "ephemeral_1h_input_tokens": 0
    },
    "output_tokens": 4
  }
}

Vergelijken met een OpenAI-compatibel endpoint

Functie	Anthropic Messages (`/v1/messages`)	OpenAI-Compatible (`/v1/chat/completions`)
Extended thinking	`thinking`-parameter met `budget_tokens`	Niet beschikbaar
Prompt caching	`cache_control` op content blocks	Niet beschikbaar
Inspanningsbeheer	`output_config.effort`	Niet beschikbaar
Web fetch/search	Servertools (`web_fetch`, `web_search`)	Niet beschikbaar
Auth-header	`x-api-key` of `Bearer`	Alleen `Bearer`
Response-indeling	Anthropic-indeling (`content` blocks)	OpenAI-indeling (`choices`, `message`)
Models	Alleen Claude	Multi-provider (GPT, Claude, Gemini, etc.)

Autorisaties

x-api-key

string

header

vereist

Your CometAPI key passed via the x-api-key header. Authorization: Bearer <key> is also supported.

Headers

anthropic-version

string

standaard:2023-06-01

The Anthropic API version to use. Defaults to 2023-06-01.

Voorbeeld:

"2023-06-01"

anthropic-beta

string

Comma-separated list of beta features to enable. Examples: max-tokens-3-5-sonnet-2024-07-15, pdfs-2024-09-25, output-128k-2025-02-19.

Body

application/json

model

string

vereist

The Claude model to use. See the Models page for current Claude model IDs.

Voorbeeld:

"claude-sonnet-4-6"

messages

object[]

vereist

The conversation messages. Must alternate between user and assistant roles. Each message's content can be a string or an array of content blocks (text, image, document, tool_use, tool_result). There is a limit of 100,000 messages per request.

Show child attributes

max_tokens

integer

vereist

The maximum number of tokens to generate. The model may stop before reaching this limit. When using thinking, the thinking tokens count towards this limit.

Vereist bereik: x >= 1

Voorbeeld:

1024

system

System prompt providing context and instructions to Claude. Can be a plain string or an array of content blocks (useful for prompt caching).

temperature

number

standaard:1

Controls randomness in the response. Range: 0.0–1.0. Use lower values for analytical tasks and higher values for creative tasks. Defaults to 1.0.

Vereist bereik: 0 <= x <= 1

top_p

number

Nucleus sampling threshold. Only tokens with cumulative probability up to this value are considered. Range: 0.0–1.0. Use either temperature or top_p, not both.

Vereist bereik: 0 <= x <= 1

top_k

integer

Only sample from the top K most probable tokens. Recommended for advanced use cases only.

Vereist bereik: x >= 0

stream

boolean

standaard:false

If true, stream the response incrementally using Server-Sent Events (SSE). Events include message_start, content_block_start, content_block_delta, content_block_stop, message_delta, and message_stop.

stop_sequences

string[]

Custom strings that cause the model to stop generating when encountered. The stop sequence is not included in the response.

thinking

object

Enable extended thinking — Claude's step-by-step reasoning process. When enabled, the response includes thinking content blocks before the answer. Requires a minimum budget_tokens of 1,024.

Show child attributes

tools

object[]

Tools the model may use. Supports client-defined functions, web search (web_search_20250305), web fetch (web_fetch_20250910), code execution (code_execution_20250522), and more.

Show child attributes

tool_choice

object

Controls how the model uses tools.

Show child attributes

metadata

object

Request metadata for tracking and analytics.

Show child attributes

output_config

object

Configuration for output behavior.

Show child attributes

service_tier

enum<string>

The service tier to use. auto tries priority capacity first, standard_only uses only standard capacity.

Beschikbare opties:

auto,

standard_only

Respons

200 - application/json

Successful response. When stream is true, the response is a stream of SSE events.

string

Unique identifier for this message (e.g., msg_01XFDUDYJgAACzvnptvVoYEL).

type

enum<string>

Always message.

Beschikbare opties:

message

role

enum<string>

Always assistant.

Beschikbare opties:

assistant

content

object[]

The response content blocks. May include text, thinking, tool_use, and other block types.

Show child attributes

model

string

The specific model version that generated this response (e.g., claude-sonnet-4-6).

stop_reason

enum<string>

Why the model stopped generating.

Beschikbare opties:

end_turn,

max_tokens,

stop_sequence,

tool_use,

pause_turn

stop_sequence

string | null

The stop sequence that caused the model to stop, if applicable.

usage

object

Token usage statistics.

Show child attributes

Responses

Gemini Generating Content

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.cometapi.com",
    api_key="<COMETAPI_KEY>",
)

message = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system="You are a helpful assistant.",
    messages=[
        {"role": "user", "content": "Hello, world"}
    ],
)

print(message.content[0].text)

{
  "id": "<string>",
  "content": [
    {
      "text": "<string>",
      "thinking": "<string>",
      "signature": "<string>",
      "id": "<string>",
      "name": "<string>",
      "input": {}
    }
  ],
  "model": "<string>",
  "stop_sequence": "<string>",
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 123,
      "ephemeral_1h_input_tokens": 123
    }
  }
}

Documentation Index

​Snelle start

​Extended thinking inschakelen

​Prompts cachen

​Responses streamen

​Inspanning beheren

​Servertools gebruiken

​Voorbeeld van een response

​Vergelijken met een OpenAI-compatibel endpoint

Autorisaties

Headers

Body

Respons

Snelle start

Extended thinking inschakelen

Prompts cachen

Responses streamen

Inspanning beheren

Servertools gebruiken

Voorbeeld van een response

Vergelijken met een OpenAI-compatibel endpoint