Skip to main content

llm-1minai

PyPI License Tests Code Quality

Plugin for LLM adding support for 1min.ai AI models.

Access 30 AI models through a single API: GPT-6 Astra / Sol / Luna, GPT-5.3 Codex, Claude Opus / Sonnet / Haiku 5.5, Gemini 4 Argon, Qwen3.8, DeepSeek V4.1 Flash, Grok 4.7, Mistral, Muse, Kimi, GLM, Sonar, and more.

Requires Python >=3.10 (tested 3.10-3.14) and llm>=0.36. Current version: 0.5.0.

Built on the unified /api/chat-with-ai endpoint with SSE streaming, image and file attachments, AI memory across conversations, brand voice, and structured prompt settings.

Looking for a standalone CLI? omi is a single-binary Go port of this plugin. No Python required, sub-20ms startup, same API-KEY and same routing (UNIFY_CHAT_WITH_AI for chat / vision / docs, CODE_GENERATOR + SPEECH_TO_TEXT on /api/features). Run go install github.com/gl0bal01/omi/cmd/omi@latest.

Installation

Install this plugin in the same environment as LLM:

llm install llm-1minai

Using pipx

If you installed LLM with pipx, inject the plugin into the LLM environment:

pipx inject llm llm-1minai

Or install both LLM and the plugin with pipx:

pipx install llm
pipx inject llm llm-1minai

From Source (Development)

Install from source for development:

git clone https://github.com/gl0bal01/llm-1minai
cd llm-1minai
llm install -e .

Or with pipx:

git clone https://github.com/gl0bal01/llm-1minai
cd llm-1minai
pipx inject llm -e .

Upgrade or Uninstall

Upgrade an existing install

# Plugin-manager install
llm install -U llm-1minai

# pipx-injected install
pipx runpip llm install -U llm-1minai

# Editable / source install
cd llm-1minai && git pull && llm install -e .

Uninstall

# Plugin-manager install
llm uninstall llm-1minai

# pipx-injected install
pipx uninject llm llm-1minai

# Editable / source install
pip uninstall llm-1minai

Verify removal

llm models list | grep 1min   # should print nothing
llm plugins | grep 1min       # should print nothing

Wipe local data (optional)

The plugin keeps user settings and the conversation-UUID map at ~/.config/llm-1min/. Remove them after uninstall if you want a clean slate:

rm -rf ~/.config/llm-1min/

The 1min.ai API key is stored separately by LLM, not under that directory:

llm keys remove 1min
unset ONEMIN_API_KEY  # if you exported it

Migrating to the standalone Go CLI

If you're switching to omi, it uses a different config dir (~/.config/omi/) and won't conflict with leftover Python-plugin state. After uninstalling above:

go install github.com/gl0bal01/omi/cmd/omi@latest
omi config set api_key sk-...

Configuration

You need a 1min.ai API key to use this plugin. Get one from 1min.ai.

Set your API key using:

llm keys set 1min
# Paste your API key when prompted

Or set it as an environment variable:

export ONEMIN_API_KEY="your-api-key-here"

Available Models

Quick View

See all 1min.ai models in your terminal:

# Show all LLM models (look for "1min.ai:" prefix)
llm models list | grep "1min.ai"

# Or use our dedicated command with descriptions
llm 1min models

Model Categories

30 models across 12 providers (v0.5.0):

  • OpenAI (5 models): GPT-6 Astra / 6.1 Sol / 6 Luna, GPT-5.5 Pro, GPT-5.3 Codex
  • Anthropic (4 models): Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Claude Haiku 5.5
  • Google (3 models): Gemini 4 Argon, Gemini 3.8 Flash, Gemini 3.1 Flash Lite (Preview)
  • Alibaba (Qwen) (2 models): Qwen3.8 Max, Qwen3.8 Flash
  • DeepSeek (1 model): DeepSeek V4.1 Flash
  • xAI (2 models): Grok 4.7, Grok 4.3
  • Mistral (3 models): Mistral Large 3, Mistral Medium 3.5, Mistral Small 4
  • Cohere (1 model): Command A+
  • Meta (2 models): Muse Wonder, Muse Spark 1.3
  • Moonshot (2 models): Kimi K3, Kimi K2.7 Code
  • Z.AI (1 model): GLM-5.3
  • Perplexity (4 models): Sonar, Sonar Pro, Sonar Reasoning Pro, Sonar Deep Research

Important: Use llm 1min models to see all available models with descriptions.

For a complete model reference with IDs and usage examples, see MODEL_SELECTION.md.

Usage

List Available Models

First, see what models are available:

# See model IDs and friendly names
llm 1min models

# Or see just the model IDs
llm models list | grep "1min.ai"
# Output example:
# 1min.ai: 1min/gpt-6-luna          ← Use this ID with -m flag
# 1min.ai: 1min/claude-sonnet-5-5

Basic Usage

Use the model ID (shown after "1min.ai:") with the -m flag:

# Fast and cheap - GPT-6 Luna
llm -m 1min/gpt-6-luna "Explain quantum computing in simple terms"

# Most powerful - GPT-6 Astra or Claude Fable 5.1
llm -m 1min/gpt-6-astra "Design a complex system architecture"
llm -m 1min/claude-fable-5-1 "Advanced reasoning task"

# Best for coding - Claude Sonnet 5.5 or Kimi K2.7 Code
llm -m 1min/claude-sonnet-5-5 "Write a REST API with FastAPI"
llm -m 1min/kimi-k2.7-code "Refactor this function"

# Best for reasoning - GPT-5.5 Pro or Gemini 4 Argon
llm -m 1min/gpt-5.5-pro "Solve this logic puzzle"
llm -m 1min/gemini-4-argon "Complex math problem"

# Web-aware - Sonar or Sonar Reasoning Pro
llm -m 1min/sonar "What are the latest AI developments?"
llm -m 1min/sonar-reasoning-pro "Research topic with citations"

# Fast responses - Claude Haiku 5.5 or Gemini Flash
llm -m 1min/claude-haiku-5-5 "Quick question"
llm -m 1min/gemini-3.8-flash "Fast response needed"

Debug Mode (Troubleshooting)

See exactly what's being sent to the API:

# Enable debug to see all options and API payload
llm -m 1min/gpt-6-luna -o debug true "test prompt"

# Or use environment variable
LLM_1MIN_DEBUG=1 llm -m 1min/gpt-6-luna "test prompt"

# See all available options for any model
llm models --options | grep -A 8 "1min/gpt-6-luna"

Note: The -d flag is already used by LLM for database operations, so debug uses -o debug true. Debug output redacts prompt text, attachment keys/IDs, and brand voice IDs by default. For more details, see DEBUG_USAGE.md

Conversation Mode (Chat)

Continue a conversation with context using the -c flag:

# Start a conversation
llm -m 1min/gpt-6-luna "Hello, I need help with Python"

# Continue the conversation (uses -c flag)
llm -m 1min/gpt-6-luna -c "What are list comprehensions?"

# Keep going - model is remembered automatically
llm -c "Show me an example"

# Resume a specific conversation by ID
llm -c --cid <conversation-id> "Continue this topic"

# View conversation history
llm logs -n 5

Important: The -c flag is handled by the LLM framework, not this plugin. Each continuation re-sends prior messages to maintain context.

See the LLM chat documentation for more details.

Code Generation

The code-only models use CODE_GENERATOR mode by default. Every other model (including Claude) uses regular chat, so streaming, attachments, memory and brand voice work; CODE_GENERATOR supports none of those (the plugin warns if you pass them).

# These models auto-use CODE_GENERATOR (no -o needed)
llm -m 1min/gpt-5.3-codex "Create a simple REST API with Go"
llm -m 1min/kimi-k2.7-code "Optimize this algorithm"

# Explicitly set for other models
llm -m 1min/claude-sonnet-5-5 \
  -o conversation_type CODE_GENERATOR \
  "Write a binary search function"

# Any -o value wins over defaults, even the default value itself
llm -m 1min/gpt-5.3-codex -o conversation_type UNIFY_CHAT_WITH_AI "Explain this diff"
llm -m 1min/sonar -o web_search false "Answer from training data only"

Built-in defaults (see llm 1min options defaults):

  • Code models: gpt-5.3-codex, moonshotai/kimi-k2.7-code → CODE_GENERATOR
  • Web-aware models: sonar, sonar-pro, sonar-reasoning-pro, sonar-deep-research → web_search=true

Advanced Options

Available Options

  • conversation_type: UNIFY_CHAT_WITH_AI (default) or CODE_GENERATOR
  • web_search: Enable real-time web search (true/false, default: false)
  • num_of_site: Number of sites to search when web_search is enabled (1-10, default: 3)
  • max_word: Maximum words from web search results (100-10000, default: 1000)
  • history_mixed: Mix context between different models (true/false, default: false) (renamed from is_mixed in v0.4.0; run llm 1min options migrate to update saved configs)
  • history_limit: Max history messages included as context (1-50, default: 10)
  • with_memories: Enable AI memory across conversations (true/false, default: false)
  • brand_voice_id: Brand voice ID for response style (string, default: none)
  • images: Comma-separated image asset keys from Asset API (string, default: none)
  • files: Comma-separated file IDs from Asset API (string, default: none)
  • debug: Show detailed API request information (true/false, default: false)
    • Use: -o debug true (Note: -d is taken by LLM's database option)
    • See: DEBUG_USAGE.md for details

One-Time Usage (CLI Flags)

# Enable web search for any model
llm -m 1min/gpt-6-luna \
  -o web_search true \
  -o num_of_site 5 \
  "What's the latest in AI?"

# Use code generator mode
llm -m 1min/gpt-6-luna \
  -o conversation_type CODE_GENERATOR \
  "Write a binary search algorithm"

# Mix context between models
# Start a conversation first (no -c needed for the first turn)
llm -m 1min/gpt-6-luna "My name is Fabien"

# Continue with a different model: -c reuses the LLM conversation,
# history_mixed=true shares the 1min.ai conversation UUID across models.
llm -m 1min/claude-opus-5-5 -c -o history_mixed true "What is my name?"

# Stream responses (SSE) - streaming is the default for `llm prompt`
llm -m 1min/gpt-6-luna "Explain transformers in 200 words"

# Disable streaming with --no-stream
llm -m 1min/gpt-6-luna --no-stream "Explain transformers in 200 words"

# Image attachments — upload first to get an asset key
KEY=$(llm 1min upload -q photo.png)
llm -m 1min/gpt-6-luna -o images "$KEY" "What do you see in this image?"

# Or upload interactively (prints key + usage hint)
llm 1min upload photo.png

# Cross-conversation memory
llm -m 1min/gpt-6-luna -o with_memories true "Remember I prefer Python over JS"

# Debug mode - see what's being sent to the API
llm -m 1min/gpt-6-luna -o debug true "test prompt"

# Alternative: environment variable
LLM_1MIN_DEBUG=1 llm -m 1min/gpt-6-luna "test prompt"

# Or set as default (useful for troubleshooting)
llm 1min options set debug true

Persistent Configuration

Set default options that apply automatically:

# Set global defaults
llm 1min options set web_search true
llm 1min options set num_of_site 5

# Now web search is enabled by default
llm -m 1min/gpt-6-luna "Latest AI news"  # Uses web_search=true automatically

# Set per-model options
llm 1min options set --model gpt-6-luna web_search true
llm 1min options set --model sonar num_of_site 10

# View all options
llm 1min options list

# View specific option
llm 1min options get web_search

# Remove an option
llm 1min options unset web_search

# Reset everything
llm 1min options reset

Priority hierarchy (highest to lowest):

  1. CLI flags (-o web_search true)
  2. Per-model config (--model gpt-6-luna)
  3. Global defaults
  4. Code defaults

List 1min.ai Models

# Show 1min.ai models with descriptions
llm 1min models

# Or see all models (including non-1min.ai)
llm models list | grep "1min.ai"

View Logs

# View last response
llm logs -n 1

# View last 5 responses
llm logs -n 5

Options Management

Manage persistent options that apply automatically to your models:

# Set global defaults
llm 1min options set web_search true
llm 1min options set num_of_site 5
llm 1min options set max_word 1000

# Set per-model options
llm 1min options set --model gpt-6-luna web_search true
llm 1min options set --model sonar num_of_site 10

# List all options
llm 1min options list

# List options for specific model
llm 1min options list --model gpt-6-luna

# Get specific option value
llm 1min options get web_search
llm 1min options get --model gpt-6-luna web_search

# Remove options
llm 1min options unset web_search
llm 1min options unset --model gpt-6-luna num_of_site

# Export/import configuration
llm 1min options export --output my-config.json
llm 1min options import my-config.json

# Reset all options
llm 1min options reset

Example config file (~/.config/llm-1min/config.json):

{
  "defaults": {
    "web_search": true,
    "num_of_site": 3
  },
  "models": {
    "gpt-6-luna": {
      "web_search": true,
      "num_of_site": 5
    },
    "sonar": {
      "num_of_site": 10
    }
  }
}

Conversation Management

The plugin provides commands to manage your 1min.ai conversations:

# List all active conversations
llm 1min conversations

# Clear conversation for a specific model
llm 1min clear --model 1min/gpt-6-luna

# Clear all conversations
llm 1min clear --all

Advanced Conversation Management:

Use the included utility script for more options:

# List all conversations on 1min.ai server
python manage_conversations.py list

# Get details of a specific conversation
python manage_conversations.py get <conversation-uuid>

# Delete a specific conversation
python manage_conversations.py delete <conversation-uuid>

# Clear all conversations from server
python manage_conversations.py clear --all

# Export conversations to JSON
python manage_conversations.py export --output my-conversations.json

Features

  • ✅ 30 AI models from 12 providers through a single API
  • ✅ Latest models: GPT-6 Astra / Sol / Luna, GPT-5.3 Codex, Claude Fable 5.1 / Opus 5.5 / Sonnet 5.5 / Haiku 5.5, Gemini 4 Argon, Qwen3.8, DeepSeek V4.1 Flash, Grok 4.7, Muse Spark / Wonder, Kimi K3, GLM-5.3, Sonar
  • ✅ Unified chat endpoint (/api/chat-with-ai) with structured settings
  • ✅ SSE streaming: stream content chunks live via llm chat --stream
  • ✅ Attachments: pass image keys / file IDs via images and files options
  • ✅ AI memory: cross-conversation memory via with_memories
  • ✅ Brand voice: per-call brand_voice_id
  • ✅ Web search: real-time grounding on any model
  • ✅ Mixed history: share conversation history across models (history_mixed)
  • ✅ Persistent options: global and per-model defaults; options migrate for upgrades
  • ✅ Test suite: 182 tests, 70% coverage
  • ✅ CI/CD: GitHub Actions for automated testing on Python 3.10-3.14
  • ✅ Conversation history tracking and management
  • ✅ Specialized code generation mode
  • ✅ Automatic conversation management
  • ✅ List, export, and clear conversations
  • ✅ Secure API key management
  • ✅ Proper error handling with helpful messages
  • ✅ Comprehensive model documentation

How It Works

This plugin uses the 1min.ai API v2 (/api/chat-with-ai) for chat models and the legacy /api/features endpoint for code generation:

  1. Conversation Creation: When you start a chat, the plugin creates a conversation of type UNIFY_CHAT_WITH_AI on 1min.ai.
  2. Chat Messages: Chat prompts POST to /api/chat-with-ai with structured promptObject.settings (web search, history, memory) and optional attachments (images, files).
  3. Code Generation: When conversation_type=CODE_GENERATOR, prompts go to the legacy /api/features endpoint with the flat promptObject shape.
  4. Streaming: Pass --stream (llm chat --stream ...) to receive server-sent events (content chunks streamed live; done terminates).
  5. Context Management: Conversations are tracked per model in ~/.config/llm-1min/conversations.json.

API Endpoints Used

  • POST https://api.1min.ai/api/chat-with-ai — chat (UNIFY_CHAT_WITH_AI), add ?isStreaming=true for SSE streaming
  • POST https://api.1min.ai/api/features — CODE_GENERATOR only
  • POST https://api.1min.ai/api/conversations — create conversation context
  • GET https://api.1min.ai/api/conversations — list all conversations
  • GET https://api.1min.ai/api/conversations/{uuid} — get specific conversation
  • DELETE https://api.1min.ai/api/conversations/{uuid} — delete/clear a conversation
  • POST https://api.1min.ai/api/assets — upload images/files (use the asset key returned in responses with the images / files options)

Authentication

The plugin uses the API-KEY header format (not OAuth/Bearer tokens).

Security Best Practices

API Key Management

  • ✅ Never hardcode API keys in scripts or code
  • ✅ Use environment variables: export ONEMIN_API_KEY="your-key"
  • ✅ Or use LLM's secure key storage: llm keys set 1min
  • ✅ Add .env files to .gitignore if used
  • ✅ Rotate keys periodically

Script Security

All scripts in this repository follow security best practices:

  • API keys are read from environment variables only
  • No credentials are logged or printed
  • Proper timeout values on all HTTP requests
  • Error handling prevents information leakage
  • Input validation where applicable

Development

Project Structure

llm-1min/
├── llm_1min.py              # Main plugin implementation
├── manage_conversations.py  # Conversation management utility
├── test_api.py              # Live smoke test for all models
├── tests/                   # Test suite (182 tests)
│   ├── test_options_config.py    # Options + legacy-key rejection (28 tests)
│   ├── test_model_execution.py   # Model execution + payload shape (18 tests)
│   ├── test_cli_commands.py      # CLI command tests (33 tests)
│   ├── test_streaming.py         # SSE parser + decoding edge cases (14 tests)
│   ├── test_attachments.py       # Attachments, options, errors, conversation keys (29 tests)
│   ├── test_web_search_config.py # Nested settings.webSearchSettings (4 tests)
│   ├── test_web_search_debug.py  # Debug payload inspection (3 tests)
│   ├── test_debug_option.py      # Debug option behavior (5 tests)
│   ├── test_integration.py       # Integration + edge cases (45 tests)
│   ├── test_register_models.py   # Curated roster + defaults (3 tests)
│   ├── conftest.py               # Shared fixtures
│   └── fixtures/                 # Mock API responses
├── .github/workflows/       # CI/CD pipelines (182 tests passing)
│   ├── test.yml            # Automated testing (Python 3.10-3.14)
│   └── lint.yml            # Code quality checks
├── pyproject.toml          # Package configuration
├── README.md               # Main documentation
├── MODEL_SELECTION.md      # Comprehensive model guide
├── TESTING.md              # Testing documentation
├── CHANGELOG.md            # Version history
├── LICENSE                 # Apache 2.0 license
└── .gitignore             # Git ignore rules

Running Tests

This project includes a comprehensive test suite with 182 unit tests covering all major functionality:

# Install test dependencies
pip install -e .[test]

# Run all tests
pytest tests/ -v

# Run with coverage report
pytest tests/ -v --cov=llm_1min --cov-report=term-missing

# Run specific test file
pytest tests/test_options_config.py -v

# Run specific test
pytest tests/test_options_config.py::TestOptionsConfigSetters::test_set_option_global -v

Test Coverage:

  • ✅ 182/182 tests passing (100%)
  • ✅ 70% code coverage
  • ✅ Options configuration + legacy-key rejection (28 tests)
  • ✅ Model execution + payload shape (18 tests)
  • ✅ CLI commands (33 tests)
  • ✅ SSE streaming parser + decoding edge cases (14 tests)
  • ✅ Attachments, options, errors, conversation keys (29 tests)
  • ✅ Web search config + debug (7 tests)
  • ✅ Debug option behavior (5 tests)
  • ✅ Integration and edge cases (45 tests)
  • ✅ Model roster + defaults (3 tests)

See TESTING.md for complete testing documentation.

Testing the Plugin

  1. Install in development mode:

    cd llm-1min
    llm install -e .
    
  2. Verify installation:

    llm models list | grep 1min
    
  3. Test with a simple prompt:

    llm -m 1min/gpt-6-luna "Hello, world!"
    
  4. Check logs for debugging:

    llm logs -n 1
    

Testing the API Directly

Use the included live smoke test to verify every registered model (chat, streaming, and CODE_GENERATOR for code-default models). It prints PASS/FAIL per model and exits non-zero on any failure:

export ONEMIN_API_KEY="your-api-key"
python test_api.py                              # all models
python test_api.py 1min/gpt-6-luna 1min/sonar   # subset

Comparison with Other Providers

Why Use 1min.ai?

Advantages:

  • 🎯 Multi-model access: One API key for 30 models across 12 providers
  • 💰 Cost-effective: Often offers lifetime subscription deals
  • 🔄 Model flexibility: Switch between OpenAI, Anthropic, Google, xAI, Mistral, Meta, etc.
  • 🚀 Latest models: Quick access to GPT-6.1 Sol, Claude Opus 5.5, Gemini 4 Argon, Qwen3.8, DeepSeek V4.1 Flash, Grok 4.7, Kimi K3
  • 🌐 Diverse capabilities: From fast responses to complex reasoning to web-aware answers

Use Cases:

  • Comparing responses from different models and providers
  • Cost optimization by choosing the right model per task
  • Avoiding vendor lock-in with multi-provider access
  • Testing different reasoning approaches (O4, DeepSeek R1, Grok 4)
  • Accessing models not available through direct APIs (Grok, Sonar)

Troubleshooting

"Authentication failed" Error

  • Verify your API key is correct: llm keys set 1min
  • Check that your 1min.ai account is active

"Rate limit exceeded" Error

  • Wait a few moments before retrying
  • Check your 1min.ai usage limits

No Response or Timeout

  • Some models (like O3, O1) may take longer for complex reasoning
  • Try increasing timeout or using a faster model

Model Not Found

  • Ensure you're using the exact model ID from the Available Models list
  • Check 1min.ai documentation for model availability

Debugging API Requests

To see exactly what's being sent to the API:

# Use debug option
llm -m 1min/gpt-6-luna -o debug true "your prompt"

# Or use environment variable
LLM_1MIN_DEBUG=1 llm -m 1min/gpt-6-luna "your prompt"

This will show:

  • Options loaded from config files
  • Options passed via CLI
  • Final merged options
  • Complete API payload being sent

Useful for troubleshooting:

  • Why web_search isn't working as expected
  • Which options are being applied
  • Configuration conflicts between global and per-model settings

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

Apache 2.0

  • omi — Standalone Go CLI sharing the same routing and API key. Single static binary, no Python runtime, sub-20ms cold start. Drop-in replacement when you don't need the LLM ecosystem.

Resources

Credits

Based on the LLM plugin architecture by Simon Willison.

Powered by 1min.ai - Multi-model AI API platform.

Metadata

Release files for llm-1minai 0.5.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llm-1minai 0.5.0
File Size Uploaded Provenance Actions
llm_1minai-0.5.0.tar.gz 52.2 kB With provenance Details for llm_1minai-0.5.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llm-1minai 0.5.0
File Interpreter ABI Platform Actions
llm_1minai-0.5.0-py3-none-any.whl Python 3 none any Details for llm_1minai-0.5.0-py3-none-any.whl

Total release size: 77.5 kB

Release files / llm_1minai-0.5.0.tar.gz

Download URL llm_1minai-0.5.0.tar.gz
Size 52.2 kB
Tags Source
SHA-256 checksum
How to use checksums
04e10983bab5ef60e0e1331c09e66f9eb96f64e507c03e666d8a1b00696e007c
BLAKE2b-256 checksum
How to use checksums
0200fad4c28fff0aa9ad59c18ee566c59807fc512612a632f55d332776643b57
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 2, 2026.

Transparency log

Release files / llm_1minai-0.5.0-py3-none-any.whl

Download URL llm_1minai-0.5.0-py3-none-any.whl
Size 25.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d0d61ba0ded803d8d771b2e53ff3c61f6e2cdf2971df5792b96f7fb2f9de9d17
BLAKE2b-256 checksum
How to use checksums
e2b1fb7a6caf5990b83dd77b7ba683ee61e6411f7e37be250485db91645ee515
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 2, 2026.

Transparency log

Security for llm-1minai 0.5.0

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

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for llm_1minai-0.5.0.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 Nov 2, 2026.

Transparency log

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page