This release is a pre-release and may not be stable for production use.
Swarmauri Hyperbolic LLM
swarmauri_llm_hyperbolic preserves Hyperbolic chat and vision imports and the
retired HyperbolicAudioTTS name. The old .xyz/v1 API was decommissioned.
The current Hyperbolic inference service documents text and vision, with new
endpoints and credentials; it does not document a compatible audio replacement.
HyperbolicAudioTTS now warns and raises a local retirement error on construction
or execution. No audio request is sent. Select a standalone TTS adapter from the
SDK migration guide.
The chat and vision implementations have not been migrated or live-verified in this TTS update. Their presence here does not establish current availability. See Hyperbolic's migration notice.
Features
HyperbolicModelfor sync, async, streaming, and batch chat completion workflows.HyperbolicVisionModelfor image-plus-text prompts against Hyperbolic VLMs.HyperbolicAudioTTSas an import-compatible retired type; it does not call the decommissioned audio API.- Model discovery through Hyperbolic's
/modelsendpoint. - Generation controls including
temperature,max_tokens,top_p,top_k, andstop. - Optional usage metadata handling on chat responses when available.
- Compatibility with Python 3.10, 3.11, 3.12, 3.13, and 3.14.
Installation
uv add swarmauri_llm_hyperbolic
pip install swarmauri_llm_hyperbolic
Prerequisites
Create a Hyperbolic API key in the Hyperbolic app and pass it to the model
constructor as api_key=....
Usage
from swarmauri_llm_hyperbolic import HyperbolicModel
from swarmauri_standard.conversations.Conversation import Conversation
from swarmauri_standard.messages.HumanMessage import HumanMessage
conversation = Conversation()
conversation.add_message(HumanMessage(content="Summarize this deployment risk."))
model = HyperbolicModel(api_key="HYPERBOLIC_API_KEY")
result = model.predict(conversation=conversation, max_tokens=200)
print(result.get_last().content)
Streaming Chat
from swarmauri_llm_hyperbolic import HyperbolicModel
from swarmauri_standard.conversations.Conversation import Conversation
from swarmauri_standard.messages.HumanMessage import HumanMessage
conversation = Conversation()
conversation.add_message(HumanMessage(content="List three API gateway checks."))
model = HyperbolicModel(api_key="HYPERBOLIC_API_KEY")
for token in model.stream(conversation=conversation):
print(token, end="")
Vision-Language Prompt
from swarmauri_llm_hyperbolic import HyperbolicVisionModel
from swarmauri_standard.conversations.Conversation import Conversation
from swarmauri_standard.messages.HumanMessage import HumanMessage
conversation = Conversation()
conversation.add_message(
HumanMessage(
content=[
{"type": "text", "text": "Describe the image."},
{"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}},
]
)
)
model = HyperbolicVisionModel(api_key="HYPERBOLIC_API_KEY")
result = model.predict(conversation=conversation)
print(result.get_last().content)
Text To Speech (retired)
Do not construct HyperbolicAudioTTS or HyperbolicTTS: the legacy API was decommissioned. Imports remain, but use emits a warning and raises a local migration error. See the SDK guide and Hyperbolic's migration notice.
Related Packages
- swarmauri_llm_deepinfra
- swarmauri_llm_groq
- swarmauri_llm_mistral
- swarmauri_llm_openai
- swarmauri_llm_perplexity
- OpenAI TTS (Play.ht replacement)
Foundational Swarmauri Packages
Provider Documentation
- Hyperbolic quick start
- Hyperbolic text generation APIs
- Hyperbolic vision-language APIs
- Hyperbolic supported models
Best Practices
- Store Hyperbolic API keys in environment variables or a secrets manager.
- Confirm model availability and provider capability flags before production deployment.
- Use
HyperbolicVisionModelonly for image-aware prompts; plain chat is simpler withHyperbolicModel. - Use explicit output paths for TTS generation so generated audio files are easy to manage.
- Prefer newer Swarmauri VLM and TTS imports for new projects when available.
License
Apache-2.0
The audio retirement does not redirect API keys or rewrite the other LLM/VLM components. Those legacy integrations need their own provider migration and verification; this update does not claim their current hosted availability.
Metadata
Release files for swarmauri_llm_hyperbolic 0.11.0.dev4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| swarmauri_llm_hyperbolic-0.11.0.dev4.tar.gz | 12.7 kB | Without provenance | Details for swarmauri_llm_hyperbolic-0.11.0.dev4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| swarmauri_llm_hyperbolic-0.11.0.dev4-py3-none-any.whl | Python 3 | none | any | Details for swarmauri_llm_hyperbolic-0.11.0.dev4-py3-none-any.whl |
Total release size: 25.4 kB
Release files / swarmauri_llm_hyperbolic-0.11.0.dev4.tar.gz
| Download URL | swarmauri_llm_hyperbolic-0.11.0.dev4.tar.gz |
|---|---|
| Size | 12.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
89753d8c89ed819934e21912c4e133ec840ea97603bbc1ae826a9aba8be96742
|
|
BLAKE2b-256 checksum How to use checksums |
8ae6a208bb7eb175275cc73115421132ce6e71921865dee27c04dc5941864cae
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / swarmauri_llm_hyperbolic-0.11.0.dev4-py3-none-any.whl
| Download URL | swarmauri_llm_hyperbolic-0.11.0.dev4-py3-none-any.whl |
|---|---|
| Size | 12.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8e0a032fef87580483e134318be50b77fa78f1585ab379082bb4a1682f2957a7
|
|
BLAKE2b-256 checksum How to use checksums |
91e66deac710c559984b4303f9f56be3e0ee9233bc8e93643c297e6652347453
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for swarmauri_llm_hyperbolic 0.11.0.dev4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.