langchain-telnyx
An integration package connecting Telnyx AI Inference and LangChain.
Telnyx provides OpenAI-compatible LLMs hosted on its own GPU infrastructure. See the Available Models page for the full list.
Installation
pip install langchain-telnyx
Chat Models
from langchain_telnyx import ChatTelnyx
chat = ChatTelnyx(model="moonshotai/Kimi-K2.6")
response = chat.invoke("Hello!")
Embeddings
from langchain_telnyx import TelnyxEmbeddings
embeddings = TelnyxEmbeddings(model="thenlper/gte-large")
vectors = embeddings.embed_query("Hello world")
Configuration
Set the TELNYX_API_KEY environment variable with your Telnyx API key, or pass it via the api_key parameter.
Get an API key at telnyx.com.
By default, langchain-telnyx uses the following OpenAI-compatible base URL:
https://api.telnyx.com/v2/ai/openai
You can override it either with the base_url parameter or with the TELNYX_API_BASE environment variable.
Example:
from langchain_telnyx import ChatTelnyx
chat = ChatTelnyx(
api_key="YOUR_API_KEY",
base_url="https://api.telnyx.com/v2/ai/openai",
model="moonshotai/Kimi-K2.6",
)
Supported Models
See Available Models — Telnyx Docs for the full, up-to-date list.
Chat Models
| Model ID | Parameters | Context | Best For |
|---|---|---|---|
moonshotai/Kimi-K2.6 |
1.0T | 256K | Highest intelligence, voice AI (Recommended) |
zai-org/GLM-5.1-FP8 |
753.9B | 202K | Reasoning, function calling |
MiniMaxAI/MiniMax-M2.7 |
— | 2M | Cheapest, high intelligence |
Embedding Models
| Model ID | Dimensions | Best For |
|---|---|---|
thenlper/gte-large |
1024 | Text embeddings |
Examples
You can find runnable smoke examples in examples/:
examples/chat_basic.pyexamples/embeddings_basic.pyexamples/chat_with_env.py
To run them from a local clone:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -U pip
python -m pip install -e .
export TELNYX_API_KEY="your-api-key"
python examples/chat_basic.py
python examples/chat_with_env.py
python examples/embeddings_basic.py
Development
Run tests from a local clone:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -U pip
python -m pip install pytest pytest-asyncio langchain-core langchain-openai openai
python -m pytest -q
If you already have the virtual environment ready:
source .venv/bin/activate
python -m pytest -q
License
MIT
Metadata
Release files for langchain-telnyx 1.0.0
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 |
|---|---|---|---|---|
| langchain_telnyx-1.0.0.tar.gz | 6.0 kB | Without provenance | Details for langchain_telnyx-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| langchain_telnyx-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for langchain_telnyx-1.0.0-py3-none-any.whl |
Total release size: 11.1 kB
Release files / langchain_telnyx-1.0.0.tar.gz
| Download URL | langchain_telnyx-1.0.0.tar.gz |
|---|---|
| Size | 6.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
430e20ad41c955e4253954bfc830eb32213e6d69b41e3ed5e28b04bfc9f240b0
|
|
BLAKE2b-256 checksum How to use checksums |
da64b3479e79f7b6d26377a0ba7915a644aff7e6826aac6b9e23910a750fee38
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.9.13 {"installer":{"name":"uv","version":"0.9.13"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / langchain_telnyx-1.0.0-py3-none-any.whl
| Download URL | langchain_telnyx-1.0.0-py3-none-any.whl |
|---|---|
| Size | 5.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c87901490a66fe248ef01402dddb06e3c9fa236ee0d3334f9139f5913e0e2f35
|
|
BLAKE2b-256 checksum How to use checksums |
386901c3a09c5554f2847fb0d22ef2c384a75922485acfd34badb48b0a51daeb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.9.13 {"installer":{"name":"uv","version":"0.9.13"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for langchain-telnyx 1.0.0
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.