Skip to main content

OrbiGPU — Unified OpenAI-compatible API gateway for 100+ LLM models. Official SDK coming in v0.1.0.

Project description

OrbiGPU

Unified OpenAI-compatible API gateway for 100+ LLM models from 15+ providers.

Official website: https://orbigpu.com

Status

v0.0.1 is a reserved placeholder. The full Python SDK will be released in v0.1.0+.

Coming in v0.1.0

  • OpenAI-compatible OrbiGPU() and AsyncOrbiGPU() clients
  • Drop-in replacement for openai.OpenAI — just change base_url
  • Access 100+ models from OpenAI, Anthropic, DeepSeek, Google, Groq, Zhipu, and more
  • $10 free credits on signup at orbigpu.com

Quickstart (available in v0.1.0+)

from orbigpu import OrbiGPU

client = OrbiGPU(api_key="sk-your-key-from-orbigpu-dot-com")
response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello"}],
)

License

MIT © OrbiGPU

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

orbigpu-0.0.1.tar.gz (2.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

orbigpu-0.0.1-py3-none-any.whl (3.0 kB view details)

Uploaded Python 3

File details

Details for the file orbigpu-0.0.1.tar.gz.

File metadata

  • Download URL: orbigpu-0.0.1.tar.gz
  • Upload date:
  • Size: 2.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for orbigpu-0.0.1.tar.gz
Algorithm Hash digest
SHA256 3968455977300623bb59fa91e6f1610b80dfe12f041f379d1df39003d691672f
MD5 0aee113a72db464c3b25bf8ff6c16664
BLAKE2b-256 8e86edb192fb31c2dc3bcfb91c178d28ad461ff04b2659be557aaa6546f90200

See more details on using hashes here.

File details

Details for the file orbigpu-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: orbigpu-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 3.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for orbigpu-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0ea74d67243f16100eebdb89b84afc102514e0b41da81de90be55f17c870c54f
MD5 c7dc6c5e801a3221cf786ec609f3809e
BLAKE2b-256 784808968f87d239e78ae37a125c2cd284ed68208c3d615f24d3c2c5abf2a14b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page