Dokumentacja referencyjna API
Przewodniki integracji
Cennik i rozliczenia
Anthropic Messages
Używaj interfejsu Anthropic Messages API przez CometAPI, aby uzyskać dostęp do modeli Claude z extended thinking, prompt caching, tool use, web search/fetch, streaming i effort control.
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>",
"type": "message",
"role": "assistant",
"content": [
{
"type": "text",
"text": "<string>",
"thinking": "<string>",
"signature": "<string>",
"id": "<string>",
"name": "<string>",
"input": {}
}
],
"model": "<string>",
"stop_reason": "end_turn",
"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
}
}
}Przegląd
CometAPI natywnie obsługuje Anthropic Messages API, dając bezpośredni dostęp do modeli Claude ze wszystkimi funkcjami specyficznymi dla Anthropic. Używaj tego endpointu do możliwości dostępnych wyłącznie w Claude, takich jak extended thinking, prompt caching i effort control.Szybki start
Użyj oficjalnego SDK Anthropic — wystarczy ustawić base URL na CometAPI: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)
x-api-key, jak i Authorization: Bearer. Oficjalne SDK Anthropic domyślnie używają x-api-key.Extended Thinking
Włącz rozumowanie Claude krok po kroku za pomocą parametruthinking. Odpowiedź zawiera bloki treści thinking, pokazujące wewnętrzne rozumowanie Claude przed końcową odpowiedzią.
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}")
budget_tokens równej 1,024. Tokens thinking wliczają się do limitu max_tokens — ustaw max_tokens wystarczająco wysoko, aby pomieścić zarówno thinking, jak i odpowiedź.Prompt Caching
Buforuj duże systemowe prompty lub prefiksy konwersacji, aby zmniejszyć opóźnienia i koszty w kolejnych żądaniach. Dodajcache_control do bloków treści, które mają być buforowane:
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..."}],
)
usage odpowiedzi:
cache_creation_input_tokens— tokens zapisane do cache (rozliczane według wyższej stawki)cache_read_input_tokens— tokens odczytane z cache (rozliczane według obniżonej stawki)
Streaming
Strumieniuj odpowiedzi za pomocą Server-Sent Events (SSE), ustawiającstream: true. Zdarzenia przychodzą w tej kolejności:
message_start— zawiera metadane wiadomości i początkowe użyciecontent_block_start— oznacza początek każdego bloku contentcontent_block_delta— przyrostowe fragmenty tekstu (text_delta)content_block_stop— oznacza koniec każdego bloku contentmessage_delta— końcowystop_reasoni pełneusagemessage_stop— sygnalizuje koniec strumienia
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="")
Kontrola wysiłku
Kontroluj, ile wysiłku Claude wkłada w generowanie odpowiedzi, za pomocąoutput_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"
)
Narzędzia serwerowe
Claude obsługuje narzędzia po stronie serwera uruchamiane w infrastrukturze Anthropic:- Web Fetch
- Web Search
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}
],
)
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}
],
)
Przykład odpowiedzi
Typowa odpowiedź z endpointu Anthropic w 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
}
}
Kluczowe różnice względem endpointu zgodnego z OpenAI
| Funkcja | Anthropic Messages (/v1/messages) | OpenAI-Compatible (/v1/chat/completions) |
|---|---|---|
| Extended thinking | parametr thinking z budget_tokens | Niedostępne |
| Prompt caching | cache_control na blokach content | Niedostępne |
| Kontrola wysiłku | output_config.effort | Niedostępne |
| Web fetch/search | Narzędzia serwerowe (web_fetch, web_search) | Niedostępne |
| Nagłówek uwierzytelniania | x-api-key lub Bearer | Tylko Bearer |
| Format odpowiedzi | format Anthropic (content blocks) | format OpenAI (choices, message) |
| Modele | Tylko Claude | Wielu dostawców (GPT, Claude, Gemini itp.) |
Autoryzacje
Your CometAPI key passed via the x-api-key header. Authorization: Bearer <key> is also supported.
Nagłówki
The Anthropic API version to use. Defaults to 2023-06-01.
"2023-06-01"
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.
Treść
The Claude model to use. See the Models page for current Claude model IDs.
"claude-sonnet-4-6"
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
Show child attributes
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.
x >= 11024
System prompt providing context and instructions to Claude. Can be a plain string or an array of content blocks (useful for prompt caching).
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.
0 <= x <= 1Nucleus 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.
0 <= x <= 1Only sample from the top K most probable tokens. Recommended for advanced use cases only.
x >= 0If 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.
Custom strings that cause the model to stop generating when encountered. The stop sequence is not included in the response.
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
Show child attributes
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
Show child attributes
Controls how the model uses tools.
Show child attributes
Show child attributes
Request metadata for tracking and analytics.
Show child attributes
Show child attributes
Configuration for output behavior.
Show child attributes
Show child attributes
The service tier to use. auto tries priority capacity first, standard_only uses only standard capacity.
auto, standard_only Odpowiedź
Successful response. When stream is true, the response is a stream of SSE events.
Unique identifier for this message (e.g., msg_01XFDUDYJgAACzvnptvVoYEL).
Always message.
message Always assistant.
assistant The response content blocks. May include text, thinking, tool_use, and other block types.
Show child attributes
Show child attributes
The specific model version that generated this response (e.g., claude-sonnet-4-6).
Why the model stopped generating.
end_turn, max_tokens, stop_sequence, tool_use, pause_turn The stop sequence that caused the model to stop, if applicable.
Token usage statistics.
Show child attributes
Show child attributes
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>",
"type": "message",
"role": "assistant",
"content": [
{
"type": "text",
"text": "<string>",
"thinking": "<string>",
"signature": "<string>",
"id": "<string>",
"name": "<string>",
"input": {}
}
],
"model": "<string>",
"stop_reason": "end_turn",
"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
}
}
}