Open-weight models. Zero data retention.

from openai import OpenAI

client = OpenAI(
    api_key="sk-cor-...",  # Token Factory key
    base_url="https://api.tokenfactory.corvex.cloud/v1",
)

resp = client.chat.completions.create(
    model="zai-org/GLM-5.3",  # or deepseek-ai/DeepSeek-V4-Flash-0731
    messages=[
        {"role": "user", "content": "Summarize this diff."}
    ],
)

print(resp.choices[0].message.content)

curl https://api.tokenfactory.corvex.cloud/v1/chat/completions \
  -H "Authorization: Bearer sk-cor-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "messages": [{"role": "user", "content": "Summarize this diff."}]
  }'

import anthropic

client = anthropic.Anthropic(
    api_key="sk-cor-...",  # Token Factory key
    base_url="https://api.tokenfactory.corvex.cloud",
)

resp = client.messages.create(
    model="zai-org/GLM-5.3",  # or deepseek-ai/DeepSeek-V4-Flash-0731
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Summarize this diff."}
    ],
)

# Models reason before they answer, so the first block is "thinking".
print("".join(b.text for b in resp.content if b.type == "text"))

curl https://api.tokenfactory.corvex.cloud/v1/messages \
  -H "x-api-key: sk-cor-..." \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Summarize this diff."}]
  }'