SimLLMs
One client shape for every major LLM provider — impossible requests are refused locally, before you pay for them.
simllms unifies DeepSeek, Moonshot (Kimi), Qwen/DashScope, Zhipu (GLM),
Xiaomi MiMo, OpenRouter, and any OpenAI-compatible gateway behind one
client: one chat, one generate_image, one streaming shape, and a
per-model statement of what that model can actually do. The capability
Gate refuses impossible requests before any network call and tells you
what is missing — and which models on the same provider can do it.
- 中文文档 / Chinese: README.md。
- Full docs: docs/getting-started.md (also on GitHub Pages once published).
let client = Client::new(Provider::DeepSeek, "deepseek-v4-pro", api_key);
let reply = client.chat(vec![Message::text("你好")]).await?;
from simllms import Client
client = Client("deepseek", "deepseek-v4-pro", api_key)
reply = client.chat(["你好"])
Runnable examples
Every example talks to a local mock service when no credentials are present, and to the real provider when the matching API key is set.
| Topic | Rust (crates/simllms/examples/) |
Python (crates/simllms-python/examples/) |
|---|---|---|
| Chat | deepseek_chat.rs |
chat.py |
| Streaming | chat_stream.rs |
chat_stream.py |
| Structured output | structured_output.rs |
structured_output.py |
| Image generation | generate_image.rs |
generate_image.py |
| Custom gateway | custom_gateway.rs |
— |
Rust: cargo run --example deepseek_chat (same pattern for the rest).
Python: from crates/simllms-python/, run uv run examples/chat.py
(same pattern for the rest).
The examples cover DeepSeek, Moonshot, OpenRouter, and Zhipu; each
provider's API key is read from its environment variable
(DEEPSEEK_API_KEY etc.), falling back to the local mock when unset.
Install
# Rust
cargo add simllms
# Python
pip install simllms # or: uv add simllms
This release does not bind every client entry point on the Python side; the list is in the "Rust-only for now" section of docs/getting-started.md, and Python coverage lands in a later minor release.
Docs: docs/getting-started.md ·
topic guides live under docs/ (chat / streaming / structured-output /
image-generation / capabilities / custom-gateway).
License
MIT OR Apache-2.0. The model capability snapshot comes from models.dev (MIT), see THIRD-PARTY-NOTICES.md.
1 maintainer
Metadata
1 maintainer
Release files for simllms 0.1.0
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 |
|---|---|---|---|---|
| simllms-0.1.0.tar.gz | 107.6 kB | With provenance | Details for simllms-0.1.0.tar.gz |
Built distributions (wheels)
| File | Actions Reset | |||
|---|---|---|---|---|
| simllms-0.1.0-cp310-abi3-win_amd64.whl | CPython 3.10 | abi3 | Windows x86-64 | Details for simllms-0.1.0-cp310-abi3-win_amd64.whl |
| simllms-0.1.0-cp310-abi3-manylinux_2_28_x86_64.whl | CPython 3.10 | abi3 | Linux glibc 2.28+ x86-64 | Details for simllms-0.1.0-cp310-abi3-manylinux_2_28_x86_64.whl |
| simllms-0.1.0-cp310-abi3-manylinux_2_28_aarch64.whl | CPython 3.10 | abi3 | Linux glibc 2.28+ ARM64 | Details for simllms-0.1.0-cp310-abi3-manylinux_2_28_aarch64.whl |
| simllms-0.1.0-cp310-abi3-macosx_11_0_arm64.whl | CPython 3.10 | abi3 | macOS 11.0+ ARM64 | Details for simllms-0.1.0-cp310-abi3-macosx_11_0_arm64.whl |
| simllms-0.1.0-cp310-abi3-macosx_10_12_x86_64.whl | CPython 3.10 | abi3 | macOS 10.12+ x86-64 | Details for simllms-0.1.0-cp310-abi3-macosx_10_12_x86_64.whl |
Total release size: 15.2 MB
Release files / simllms-0.1.0.tar.gz
| Download URL | simllms-0.1.0.tar.gz |
|---|---|
| Size | 107.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a86aa42d10f69e9d5254ebd591a6e17dce1a4c1e6ee37e0356945b2b4501c53f
|
|
BLAKE2b-256 checksum How to use checksums |
dcebdc12dae8b302064507b8e89fdc21cf2ad0b9556c60db8793e6efb309f866
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / simllms-0.1.0-cp310-abi3-win_amd64.whl
| Download URL | simllms-0.1.0-cp310-abi3-win_amd64.whl |
|---|---|
| Size | 2.6 MB |
| Tags | CPython 3.10 Windows x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
ab2884cf98a3e75b909346bb02bf01cfdd1d4b4bb47193b529e7a9bf95c9c4ab
|
|
BLAKE2b-256 checksum How to use checksums |
8639c1b73d34905ba969de07e38cac5140af74d5adc643c6f03f6333ae9060cf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / simllms-0.1.0-cp310-abi3-manylinux_2_28_x86_64.whl
| Download URL | simllms-0.1.0-cp310-abi3-manylinux_2_28_x86_64.whl |
|---|---|
| Size | 3.3 MB |
| Tags | CPython 3.10 Linux glibc 2.28+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
d5e9e3db80391b5697d9c6708ab9530b0994339fd59b7642c2bce5fb064d3a0a
|
|
BLAKE2b-256 checksum How to use checksums |
5e6b76912caf4d5d33e9dea3130b8e76b6803394bca5e903a13c369afee70c0f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / simllms-0.1.0-cp310-abi3-manylinux_2_28_aarch64.whl
| Download URL | simllms-0.1.0-cp310-abi3-manylinux_2_28_aarch64.whl |
|---|---|
| Size | 3.2 MB |
| Tags | CPython 3.10 Linux glibc 2.28+ ARM64 abi3 |
|
SHA-256 checksum How to use checksums |
57d7c9c0e32347e8a6696e1fecfdc1a1c2db3f2a6fbce084a22f8c23e4c4b770
|
|
BLAKE2b-256 checksum How to use checksums |
6b138c852b3751df820f38ac39c25538d3c29038665b8ac2cf9b108508847bea
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / simllms-0.1.0-cp310-abi3-macosx_11_0_arm64.whl
| Download URL | simllms-0.1.0-cp310-abi3-macosx_11_0_arm64.whl |
|---|---|
| Size | 2.9 MB |
| Tags | CPython 3.10 abi3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
e221bb9640b9d4eab4c0bdb906cda3d03b827d62a9e99e46ed3913406ba85d5d
|
|
BLAKE2b-256 checksum How to use checksums |
6b5afba18247c8b75512c6a02805268ce8bf64ad3d8c7f305bb6cbfdb1e9b74c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logRelease files / simllms-0.1.0-cp310-abi3-macosx_10_12_x86_64.whl
| Download URL | simllms-0.1.0-cp310-abi3-macosx_10_12_x86_64.whl |
|---|---|
| Size | 3.1 MB |
| Tags | CPython 3.10 abi3 macOS 10.12+ x86-64 |
|
SHA-256 checksum How to use checksums |
118dd753fc4ad77eaa6f94bc156601ab4620a27a95098b0452fbe59b0de64b88
|
|
BLAKE2b-256 checksum How to use checksums |
add2d613254573ff562aec3d151fa5ad6537e23dc0bce237b56ce52a3faba6cd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logSecurity for simllms 0.1.0
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.
Full provenance
All 6 files in this release have been uploaded with provenance metadata.
Attestation for simllms-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.
Transparency logA 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.
