Claude · Parsec docs

Parsec serves Claude on the OpenAI chat completions API, so the openai SDK works unchanged: point its base URL at Parsec and use your Parsec key.

Model id
`claude-fable-5-1`	Claude Fable 5.1: Anthropic’s most capable model, for demanding reasoning and long-horizon agentic work
`claude-opus-5-5`	Claude Opus 5.5: long-running agentic coding and knowledge work
`claude-sonnet-5-5`	Claude Sonnet 5.5: the best combination of speed and intelligence

All three have a 1M-token context window and up to 128K output tokens.

Python

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://platform.parseclab.ai/v1",
    api_key=os.environ["PARSEC_API_KEY"],
)
resp = client.chat.completions.create(
    model="claude-sonnet-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarise the plot of Hamlet in two sentences."}],
)
print(resp.choices[0].message.content)

Streaming

Set stream=True; chunks arrive as server-sent events in the OpenAI format.

stream = client.chat.completions.create(
    model="claude-sonnet-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Count to five."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

HTTP

curl https://platform.parseclab.ai/v1/chat/completions \
  -H "Authorization: Bearer $PARSEC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-5-5", "max_tokens": 1024,
       "messages": [{"role": "user", "content": "Hello"}]}'

Usage and limits

Requests go to Anthropic’s OpenAI-compatible endpoint, which accepts the common chat completions fields (messages, max_tokens, temperature, stream, tools). Anthropic-only features that this API can’t express, such as prompt-caching controls, aren’t available here.
Billing follows Anthropic’s token counts, input and output (thinking included), at the prices on the models page.