Skip to main content
The Moonshot V1 models are available through Upmore via the standard Chat Completions API (/v1/chat/completions). Pick the context tier that fits your input length — pricing scales with the tier.

​
Available models

ModelNotes
moonshot-v1-8kShort-form generation, 8k context
moonshot-v1-32kLong-form generation, 32k context
moonshot-v1-128kVery long documents, 128k context
moonshot-v1-8k-vision-previewVision — understands images, 8k context
moonshot-v1-32k-vision-previewVision — understands images, 32k context
moonshot-v1-128k-vision-previewVision — understands images, 128k context

​
Quick example

curl https://api.upmore.net/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshot-v1-8k",
    "messages": [
      { "role": "user", "content": "Write a product description for a mechanical keyboard." }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.upmore.net/v1"
)

response = client.chat.completions.create(
    model="moonshot-v1-8k-vision-preview",
    messages=[
        {"role": "user", "content": [
            {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
            {"type": "text", "text": "Describe this image."}
        ]}
    ]
)

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

​
Parameters

ParameterTypeRequiredDescription
modelstringYesOne of the model IDs from the table above
messagesarrayYesList of { role, content } objects; vision models accept image_url content items
streambooleanNoEnable SSE streaming. Default: false
temperaturefloatNoControls randomness. Default: 1
max_tokensintegerNoMaximum output tokens to generate
stopstring / arrayNoSequences that stop generation

API Reference

View the interactive API playground.