llms-py 2.0.33__tar.gz → 2.0.35__tar.gz

llms_py-2.0.35/PKG-INFO

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: llms-py
+Version: 2.0.35
+Summary: A lightweight CLI tool and OpenAI-compatible server for querying multiple Large Language Model (LLM) providers
+Home-page: https://github.com/ServiceStack/llms
+Author: ServiceStack
+Author-email: ServiceStack <team@servicestack.net>
+Maintainer-email: ServiceStack <team@servicestack.net>
+License-Expression: BSD-3-Clause
+Project-URL: Homepage, https://github.com/ServiceStack/llms
+Project-URL: Documentation, https://github.com/ServiceStack/llms#readme
+Project-URL: Repository, https://github.com/ServiceStack/llms
+Project-URL: Bug Reports, https://github.com/ServiceStack/llms/issues
+Keywords: llm,ai,openai,anthropic,google,gemini,groq,mistral,ollama,cli,server,chat,completion
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: System Administrators
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Internet :: WWW/HTTP :: HTTP Servers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: System :: Systems Administration
+Classifier: Topic :: Utilities
+Classifier: Environment :: Console
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: aiohttp
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+# llms.py
+
+Lightweight CLI, API and ChatGPT-like alternative to Open WebUI for accessing multiple LLMs, entirely offline, with all data kept private in browser storage.
+
+[llmspy.org](https://llmspy.org)
+
+[![](https://github.com/ServiceStack/llmspy.org/blob/main/public/img/llmspy-home.webp?raw=true)](https://llmspy.org)
+
+GitHub: [llmspy.org](https://github.com/ServiceStack/llmspy.org)

llms_py-2.0.35/README.md

@@ -0,0 +1,9 @@
+# llms.py
+
+Lightweight CLI, API and ChatGPT-like alternative to Open WebUI for accessing multiple LLMs, entirely offline, with all data kept private in browser storage.
+
+[llmspy.org](https://llmspy.org)
+
+[![](https://github.com/ServiceStack/llmspy.org/blob/main/public/img/llmspy-home.webp?raw=true)](https://llmspy.org)
+
+GitHub: [llmspy.org](https://github.com/ServiceStack/llmspy.org)

llms_py-2.0.35/llms/__init__.py

@@ -0,0 +1,4 @@
+# Import the main module content
+from .main import main as main
+
+__all__ = ["main"]

{llms_py-2.0.33 → llms_py-2.0.35}/llms/llms.json

@@ -219,32 +219,39 @@
       "base_url": "https://openrouter.ai/api",
       "api_key": "$OPENROUTER_API_KEY",
       "models": {
-        "qwen2.5vl": "qwen/qwen2.5-vl-32b-instruct:free",
-        "llama4:109b": "meta-llama/llama-4-scout:free",
-        "llama4:400b": "meta-llama/llama-4-maverick:free",
+        "kat-coder-pro": "kwaipilot/kat-coder-pro:free",
+        "nemotron-nano-vl:12b": "nvidia/nemotron-nano-12b-v2-vl:free",
+        "tongyi-deepresearch:30b": "alibaba/tongyi-deepresearch-30b-a3b:free",
+        "longcat-flash-chat": "meituan/longcat-flash-chat:free",
+        "nemotron-nano:9b": "nvidia/nemotron-nano-9b-v2:free",
         "deepseek-v3.1:671b": "deepseek/deepseek-chat-v3.1:free",
-        "deepseek-r1:671b": "deepseek/deepseek-r1-0528:free",
-        "gemini-2.0-flash": "google/gemini-2.0-flash-exp:free",
-        "gemma3n:e2b": "google/gemma-3n-e2b-it:free",
+        "gpt-oss:20b": "openai/gpt-oss-20b:free",
         "glm-4.5-air": "z-ai/glm-4.5-air:free",
+        "qwen3-coder": "qwen/qwen3-coder:free",
+        "kimi-k2": "moonshotai/kimi-k2:free",
+        "venice-mistral:24b":"cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
+        "gemma3n:2b":"google/gemma-3n-e2b-it:free",
+        "deepseek-r1t2-chimera": "tngtech/deepseek-r1t2-chimera:free",
+        "mistral-small3.2:24b": "mistralai/mistral-small-3.2-24b-instruct:free",
+        "deepseek-r1:671b": "deepseek/deepseek-r1-0528:free",
+        "gemma3n:4b":"google/gemma-3n-e4b-it:free",
+        "qwen3:30b": "qwen/qwen3-30b-a3b:free",
+        "qwen3:14b": "qwen/qwen3-14b:free",
+        "qwen3:235b": "qwen/qwen3-235b-a22b:free",
         "mai-ds-r1": "microsoft/mai-ds-r1:free",
+        "qwen-2.5:72b": "qwen/qwen-2.5-72b-instruct:free",
+        "qwen2.5vl": "qwen/qwen2.5-vl-32b-instruct:free",
+        "qwen2.5vl:32b": "qwen/qwen2.5-vl-32b-instruct:free",
+        "gemma3:4b":"google/gemma-3-4b-it:free",
+        "gemma3:12b":"google/gemma-3-12b-it:free",
+        "gemma3:27b": "google/gemma-3-27b-it:free",
+        "deepseek-r1": "deepseek/deepseek-r1-0528:free",
+        "gemini-2.0-flash": "google/gemini-2.0-flash-exp:free",
         "llama3.3:70b": "meta-llama/llama-3.3-70b-instruct:free",
-        "nemotron-nano:9b": "nvidia/nemotron-nano-9b-v2:free",
-        "nemotron-nano-vl:12b": "nvidia/nemotron-nano-12b-v2-vl:free",
-        "deepseek-r1-distill-llama:70b": "deepseek/deepseek-r1-distill-llama-70b:free",
-        "gpt-oss:20b": "openai/gpt-oss-20b:free",
-        "mistral-small3.2:24b": "mistralai/mistral-small-3.2-24b-instruct:free",
+        "llama3.2:3b":"meta-llama/llama-3.2-3b-instruct:free",
         "mistral-nemo:12b": "mistralai/mistral-nemo:free",
-        "venice-uncensored:24b": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
-        "llama3.3:8b": "meta-llama/llama-3.3-8b-instruct:free",
-        "gemma3:27b": "google/gemma-3-27b-it:free",
-        "qwen3-coder": "qwen/qwen3-coder:free",
-        "qwen3:235b": "qwen/qwen3-235b-a22b:free",
-        "qwen3:30b": "qwen/qwen3-30b-a3b:free",
         "qwen3:4b": "qwen/qwen3-4b:free",
-        "qwen2.5vl:32b": "qwen/qwen2.5-vl-32b-instruct:free",
-        "qwen-2.5:72b": "qwen/qwen-2.5-72b-instruct:free",
-        "minimax-m2": "minimax/minimax-m2:free"
+        "mistral:7b":"mistralai/mistral-7b-instruct:free"
       },
       "default_pricing": {
         "input": "0",
@@ -398,6 +405,10 @@
       "base_url": "https://api.openai.com",
       "api_key": "$OPENAI_API_KEY",
       "models": {
+        "gpt-5.1": "gpt-5.1",
+        "gpt-5.1-chat-latest": "gpt-5.1-chat-latest",
+        "gpt-5.1-codex": "gpt-5.1-codex",
+        "gpt-5.1-codex-mini": "gpt-5.1-codex-mini",
         "gpt-5-nano": "gpt-5-nano",
         "gpt-5-mini": "gpt-5-mini",
         "gpt-5": "gpt-5",
@@ -417,6 +428,22 @@
         "gpt-3.5-turbo": "gpt-3.5-turbo"
       },
       "pricing": {
+        "gpt-5.1": {
+          "input": "0.00000125",
+          "output": "0.00001"
+        },
+        "gpt-5.1-chat-latest": {
+          "input": "0.00000125",
+          "output": "0.00001"
+        },
+        "gpt-5.1-codex": {
+          "input": "0.00000125",
+          "output": "0.00001"
+        },
+        "gpt-5.1-codex-mini": {
+          "input": "0.00000025",
+          "output": "0.000002"
+        },
         "gpt-5-nano": {
           "input": "0.00000005",
           "output": "0.0000004"
@@ -859,6 +886,10 @@
         "gemma3:4b": "google/gemma-3-4b-it",
         "gemma3:12b": "google/gemma-3-12b-it",
         "gemma3:27b": "google/gemma-3-27b-it",
+        "gpt-5.1": "openai/gpt-5.1",
+        "gpt-5.1-chat": "openai/gpt-5.1-chat",
+        "gpt-5.1-codex": "openai/gpt-5.1-codex",
+        "gpt-5.1-codex-mini": "openai/gpt-5.1-codex-mini",
         "gpt-5": "openai/gpt-5",
         "gpt-5-chat": "openai/gpt-5-chat",
         "gpt-5-mini": "openai/gpt-5-mini",
@@ -882,6 +913,8 @@
         "glm-4.5-air": "z-ai/glm-4.5-air",
         "minimax-m2": "minimax/minimax-m2",
         "kimi-k2": "moonshotai/kimi-k2",
+        "kimi-k2-thinking": "moonshotai/kimi-k2-thinking",
+        "kimi-linear:48b": "moonshotai/kimi-linear-48b-a3b-instruct",
         "deepseek-v3.1:671b": "deepseek/deepseek-chat",
         "deepseek-v3.2-exp": "deepseek/deepseek-v3.2-exp",
         "deepseek-chat-v3.1:671b": "deepseek/deepseek-chat-v3.1",
@@ -904,8 +937,8 @@
       },
       "pricing": {
         "meta-llama/llama-3.1-405b-instruct": {
-          "input": "0.0000008",
-          "output": "0.0000008"
+          "input": "0.0000035",
+          "output": "0.0000035"
         },
         "meta-llama/llama-3.3-70b-instruct": {
           "input": "0.00000013",
@@ -983,6 +1016,22 @@
           "input": "0.00000009",
           "output": "0.00000016"
         },
+        "openai/gpt-5.1": {
+          "input": "0.00000125",
+          "output": "0.00001"
+        },
+        "openai/gpt-5.1-chat": {
+          "input": "0.00000125",
+          "output": "0.00001"
+        },
+        "openai/gpt-5.1-codex": {
+          "input": "0.00000125",
+          "output": "0.00001"
+        },
+        "openai/gpt-5.1-codex-mini": {
+          "input": "0.00000025",
+          "output": "0.000002"
+        },
         "openai/gpt-5": {
           "input": "0.00000125",
           "output": "0.00001"
@@ -1061,23 +1110,31 @@
         },
         "z-ai/glm-4.5": {
           "input": "0.00000035",
-          "output": "0.00000155"
+          "output": "0.0000015"
         },
         "z-ai/glm-4.5-air": {
           "input": "0.00000013",
           "output": "0.00000085"
         },
         "minimax/minimax-m2": {
-          "input": "0.00000015",
-          "output": "0.00000045"
+          "input": "0.000000255",
+          "output": "0.00000102"
         },
         "moonshotai/kimi-k2": {
-          "input": "0.00000014",
-          "output": "0.00000249"
+          "input": "0.0000005",
+          "output": "0.0000024"
+        },
+        "moonshotai/kimi-k2-thinking": {
+          "input": "0.00000055",
+          "output": "0.00000225"
+        },
+        "moonshotai/kimi-linear-48b-a3b-instruct": {
+          "input": "0.0000003",
+          "output": "0.0000006"
         },
         "deepseek/deepseek-chat": {
           "input": "0.0000003",
-          "output": "0.00000085"
+          "output": "0.0000012"
         },
         "deepseek/deepseek-v3.2-exp": {
           "input": "0.00000027",