lm-deluge 0.0.7__tar.gz → 0.0.8__tar.gz

lm_deluge-0.0.8/LICENSE

@@ -0,0 +1,7 @@
+Copyright 2025, Taylor AI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

{lm_deluge-0.0.7 → lm_deluge-0.0.8}/PKG-INFO

@@ -1,10 +1,11 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.7
+Version: 0.0.8
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Requires-Dist: python-dotenv
 Requires-Dist: json5
 Requires-Dist: PyYAML
@@ -22,10 +23,11 @@ Requires-Dist: pdf2image
 Requires-Dist: pillow
 Requires-Dist: fasttext-wheel
 Requires-Dist: fasttext-langdetect
+Dynamic: license-file
 
-# lm_deluge
+# lm-deluge
 
-`lm_deluge` is a lightweight helper library for maxing out your rate limits with LLM providers. It provides the following:
+`lm-deluge` is a lightweight helper library for maxing out your rate limits with LLM providers. It provides the following:
 
 - **Unified client** – Send prompts to all relevant models with a single client.
 - **Massive concurrency with throttling** – Set `max_tokens_per_minute` and `max_requests_per_minute` and let it fly. The client will process as many requests as possible while respecting rate limits and retrying failures.
@@ -77,11 +79,7 @@ print(resp[0].completion)
 
 API calls can be customized in a few ways.
 
-1. **Sampling Parameters.** This determines things like structured outputs, maximum completion tokens, nucleus sampling, etc. Provide a custom `SamplingParams` to the `LLMClient` to set temperature, top_p, json_mode, max_new_tokens, and/or reasoning_effort.
-
-You can pass 1 `SamplingParams` to use for all models, or a list of `SamplingParams` that's the same length as the list of models. You can also pass many of these arguments directly to `LLMClient.basic` so you don't have to construct an entire `SamplingParams` object.
-
-
+1. **Sampling Parameters.** This determines things like structured outputs, maximum completion tokens, nucleus sampling, etc. Provide a custom `SamplingParams` to the `LLMClient` to set temperature, top_p, json_mode, max_new_tokens, and/or reasoning_effort. You can pass 1 `SamplingParams` to use for all models, or a list of `SamplingParams` that's the same length as the list of models. You can also pass many of these arguments directly to `LLMClient.basic` so you don't have to construct an entire `SamplingParams` object.
 2. **Arguments to LLMClient.** This is where you set request timeout, rate limits, model name(s), model weight(s) for distributing requests across models, retries, and caching.
 3. **Arguments to process_prompts.** Per-call, you can set verbosity, whether to display progress, and whether to return just completions (rather than the full APIResponse object).
 

{lm_deluge-0.0.7 → lm_deluge-0.0.8}/README.md

@@ -1,6 +1,6 @@
-# lm_deluge
+# lm-deluge
 
-`lm_deluge` is a lightweight helper library for maxing out your rate limits with LLM providers. It provides the following:
+`lm-deluge` is a lightweight helper library for maxing out your rate limits with LLM providers. It provides the following:
 
 - **Unified client** – Send prompts to all relevant models with a single client.
 - **Massive concurrency with throttling** – Set `max_tokens_per_minute` and `max_requests_per_minute` and let it fly. The client will process as many requests as possible while respecting rate limits and retrying failures.
@@ -52,11 +52,7 @@ print(resp[0].completion)
 
 API calls can be customized in a few ways.
 
-1. **Sampling Parameters.** This determines things like structured outputs, maximum completion tokens, nucleus sampling, etc. Provide a custom `SamplingParams` to the `LLMClient` to set temperature, top_p, json_mode, max_new_tokens, and/or reasoning_effort.
-
-You can pass 1 `SamplingParams` to use for all models, or a list of `SamplingParams` that's the same length as the list of models. You can also pass many of these arguments directly to `LLMClient.basic` so you don't have to construct an entire `SamplingParams` object.
-
-
+1. **Sampling Parameters.** This determines things like structured outputs, maximum completion tokens, nucleus sampling, etc. Provide a custom `SamplingParams` to the `LLMClient` to set temperature, top_p, json_mode, max_new_tokens, and/or reasoning_effort. You can pass 1 `SamplingParams` to use for all models, or a list of `SamplingParams` that's the same length as the list of models. You can also pass many of these arguments directly to `LLMClient.basic` so you don't have to construct an entire `SamplingParams` object.
 2. **Arguments to LLMClient.** This is where you set request timeout, rate limits, model name(s), model weight(s) for distributing requests across models, retries, and caching.
 3. **Arguments to process_prompts.** Per-call, you can set verbosity, whether to display progress, and whether to return just completions (rather than the full APIResponse object).
 

{lm_deluge-0.0.7 → lm_deluge-0.0.8}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools", "wheel"]
 
 [project]
 name = "lm_deluge"
-version = "0.0.7"
+version = "0.0.8"
 authors = [{ name = "Benjamin Anderson", email = "ben@trytaylor.ai" }]
 description = "Python utility for using LLM API models."
 readme = "README.md"

{lm_deluge-0.0.7 → lm_deluge-0.0.8}/src/lm_deluge/models.py

@@ -420,6 +420,31 @@ registry = {
     #                                                                   ░███
     #                                                                   █████
     #                                                                  ░░░░░
+    "claude-4-opus": {
+        "id": "claude-4-opus",
+        "name": "claude-opus-4-20250514",
+        "api_base": "https://api.anthropic.com/v1",
+        "api_key_env_var": "ANTHROPIC_API_KEY",
+        "supports_json": False,
+        "api_spec": "anthropic",
+        "input_cost": 3.0,
+        "output_cost": 15.0,
+        "requests_per_minute": 4_000,
+        "tokens_per_minute": 400_000,
+        "reasoning_model": True,
+    },
+    "claude-4-sonnet": {
+        "id": "claude-4-sonnet",
+        "name": "claude-sonnet-4-20250514",
+        "api_base": "https://api.anthropic.com/v1",
+        "api_key_env_var": "ANTHROPIC_API_KEY",
+        "supports_json": False,
+        "api_spec": "anthropic",
+        "input_cost": 3.0,
+        "output_cost": 15.0,
+        "requests_per_minute": 4_000,
+        "tokens_per_minute": 400_000,
+    },
     "claude-3-haiku": {
         "id": "claude-3-haiku",
         "name": "claude-3-haiku-20240307",

{lm_deluge-0.0.7 → lm_deluge-0.0.8}/src/lm_deluge.egg-info/PKG-INFO

@@ -1,10 +1,11 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.7
+Version: 0.0.8
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Requires-Dist: python-dotenv
 Requires-Dist: json5
 Requires-Dist: PyYAML
@@ -22,10 +23,11 @@ Requires-Dist: pdf2image
 Requires-Dist: pillow
 Requires-Dist: fasttext-wheel
 Requires-Dist: fasttext-langdetect
+Dynamic: license-file
 
-# lm_deluge
+# lm-deluge
 
-`lm_deluge` is a lightweight helper library for maxing out your rate limits with LLM providers. It provides the following:
+`lm-deluge` is a lightweight helper library for maxing out your rate limits with LLM providers. It provides the following:
 
 - **Unified client** – Send prompts to all relevant models with a single client.
 - **Massive concurrency with throttling** – Set `max_tokens_per_minute` and `max_requests_per_minute` and let it fly. The client will process as many requests as possible while respecting rate limits and retrying failures.
@@ -77,11 +79,7 @@ print(resp[0].completion)
 
 API calls can be customized in a few ways.
 
-1. **Sampling Parameters.** This determines things like structured outputs, maximum completion tokens, nucleus sampling, etc. Provide a custom `SamplingParams` to the `LLMClient` to set temperature, top_p, json_mode, max_new_tokens, and/or reasoning_effort.
-
-You can pass 1 `SamplingParams` to use for all models, or a list of `SamplingParams` that's the same length as the list of models. You can also pass many of these arguments directly to `LLMClient.basic` so you don't have to construct an entire `SamplingParams` object.
-
-
+1. **Sampling Parameters.** This determines things like structured outputs, maximum completion tokens, nucleus sampling, etc. Provide a custom `SamplingParams` to the `LLMClient` to set temperature, top_p, json_mode, max_new_tokens, and/or reasoning_effort. You can pass 1 `SamplingParams` to use for all models, or a list of `SamplingParams` that's the same length as the list of models. You can also pass many of these arguments directly to `LLMClient.basic` so you don't have to construct an entire `SamplingParams` object.
 2. **Arguments to LLMClient.** This is where you set request timeout, rate limits, model name(s), model weight(s) for distributing requests across models, retries, and caching.
 3. **Arguments to process_prompts.** Per-call, you can set verbosity, whether to display progress, and whether to return just completions (rather than the full APIResponse object).
 

{lm_deluge-0.0.7 → lm_deluge-0.0.8}/src/lm_deluge.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+LICENSE
 README.md
 pyproject.toml
 src/lm_deluge/__init__.py