ctxlen 2026.10.11.dev1__tar.gz

ctxlen-2026.10.11.dev1/LICENSE

@@ -0,0 +1,76 @@
+MIT License
+
+Copyright (c) 2026 Michael Theologitis
+
+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.
+
+---
+
+src/ctxlen/_data.json holds data from litellm's model_prices_and_context_window.json,
+and src/ctxlen/_resolve.py ports litellm's lookup of a model id. Both are used under
+litellm's MIT license:
+
+MIT License
+
+Copyright (c) 2023 Berri 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.
+
+---
+
+src/ctxlen/_data.json also holds data from models.dev's api.json, used under
+models.dev's MIT license:
+
+MIT License
+
+Copyright (c) 2025 models.dev
+
+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.

ctxlen-2026.10.11.dev1/PKG-INFO

@@ -0,0 +1,113 @@
+Metadata-Version: 2.4
+Name: ctxlen
+Version: 2026.10.11.dev1
+Summary: max_input and max_output for any litellm model id, with no dependencies and no network
+Keywords: llm,litellm,context window,tokens,models.dev
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Programming Language :: Python :: 3
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Project-URL: Repository, https://github.com/michaeltheologitis/ctxlen
+Description-Content-Type: text/markdown
+
+# ctxlen
+
+How many tokens a model takes in, and how many it can write back, for any model id you would
+pass to `litellm.completion`. No dependencies, no network: the numbers ship inside the package.
+
+```shell
+uv add ctxlen
+```
+
+```pycon
+>>> import ctxlen
+>>> ctxlen.max_input("gpt-4o"), ctxlen.max_output("gpt-4o")
+(128000, 16384)
+>>> ctxlen.max_input("openai/gpt-4o")
+128000
+>>> ctxlen.max_input("GPT-4o")
+128000
+>>> ctxlen.max_input("text-embedding-3-small"), ctxlen.max_output("text-embedding-3-small")
+(8191, None)
+>>> print(ctxlen.max_input("not-a-model"))
+None
+
+```
+
+That is the whole API: `max_input(model)` and `max_output(model)`, each an `int` or `None`.
+
+## What the numbers mean
+
+The numbers are litellm's, from its `model_prices_and_context_window.json`. Where litellm's
+row has no number, ctxlen uses [models.dev](https://models.dev)'s for the same provider's model.
+litellm wins every conflict.
+
+The sources store what each provider publishes. For some models that is the input cap (gpt-5:
+272,000 tokens of a 400,000-token window); for others it is the whole window, the reply
+included (Claude). ctxlen passes the numbers through and does not reconcile them, so leave room
+for the reply.
+
+## The ids it takes
+
+Any id litellm takes, resolved the way litellm's `get_model_info` resolves it:
+
+- bare names, such as `gpt-4o` and `claude-sonnet-4-5`;
+- provider prefixes, such as `openai/gpt-4o`, `anthropic/claude-sonnet-4-5`,
+  `vertex_ai/gemini-2.5-pro`, `bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0` and
+  `azure/gpt-4.1`;
+- the forms litellm strips back to a known model: a date suffix such as `-2024-08-06`, a `-001`
+  version on Vertex and Gemini, a fine-tune such as `ft:gpt-4o-2024-08-06:acme::AbC123`,
+  Bedrock regions and routes, and any letter case.
+
+A test in CI runs the same ids through litellm itself and fails if any answer differs.
+
+ctxlen reads the id string only. litellm's `custom_llm_provider=`, `api_base=` and
+`register_model` have no counterpart.
+
+## When the answer is None
+
+`None` means no source has a number. ctxlen never guesses.
+
+- The id is unknown, or empty. Nothing is trimmed: `" gpt-4o"` is unknown.
+- The id names a deployment, such as `azure/my-prod-gpt4`. Ask by model: `azure/gpt-4.1`.
+- The id is an `openrouter/` id. OpenRouter's terms forbid scripted copying, so v1 leaves it out.
+- The model is too new for litellm, and models.dev has no entry for that provider either.
+  litellm's pattern rule would guess 200,000 tokens for an unknown Claude; ctxlen does not.
+- `max_output` of an embedding model, which writes no tokens.
+- models.dev's output limit equals the whole window, which is padding rather than a limit, so it
+  is dropped.
+
+A `model` that is not a `str` raises `TypeError`.
+
+## How fresh the data is
+
+A job rebuilds the data from litellm and models.dev every 6 hours, and publishes a release when
+the data has changed. The version is the date of that snapshot: `2026.10.11.3` is the third
+release built from data fetched on 2026-10-11 (UTC).
+
+Your lock file decides what you get: `uv lock --upgrade-package ctxlen`. If a release most days
+is too much for Dependabot, group the updates or check weekly:
+
+```yaml
+version: 2
+updates:
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: weekly
+    groups:
+      ctxlen:
+        patterns: [ctxlen]
+```
+
+## Credits
+
+- [litellm](https://github.com/BerriAI/litellm) (BerriAI, MIT): the model map, and the lookup
+  ctxlen ports from it.
+- [models.dev](https://github.com/anomalyco/models.dev) (MIT): the numbers where litellm has
+  none. Its entries for OpenRouter, Vercel and Venice are not used, because their terms forbid
+  copying, and neither are Hugging Face's, whose router serves one model on hosts with different
+  windows.
+
+Both MIT notices are in [LICENSE](LICENSE), after ctxlen's own.

ctxlen-2026.10.11.dev1/README.md

@@ -0,0 +1,100 @@
+# ctxlen
+
+How many tokens a model takes in, and how many it can write back, for any model id you would
+pass to `litellm.completion`. No dependencies, no network: the numbers ship inside the package.
+
+```shell
+uv add ctxlen
+```
+
+```pycon
+>>> import ctxlen
+>>> ctxlen.max_input("gpt-4o"), ctxlen.max_output("gpt-4o")
+(128000, 16384)
+>>> ctxlen.max_input("openai/gpt-4o")
+128000
+>>> ctxlen.max_input("GPT-4o")
+128000
+>>> ctxlen.max_input("text-embedding-3-small"), ctxlen.max_output("text-embedding-3-small")
+(8191, None)
+>>> print(ctxlen.max_input("not-a-model"))
+None
+
+```
+
+That is the whole API: `max_input(model)` and `max_output(model)`, each an `int` or `None`.
+
+## What the numbers mean
+
+The numbers are litellm's, from its `model_prices_and_context_window.json`. Where litellm's
+row has no number, ctxlen uses [models.dev](https://models.dev)'s for the same provider's model.
+litellm wins every conflict.
+
+The sources store what each provider publishes. For some models that is the input cap (gpt-5:
+272,000 tokens of a 400,000-token window); for others it is the whole window, the reply
+included (Claude). ctxlen passes the numbers through and does not reconcile them, so leave room
+for the reply.
+
+## The ids it takes
+
+Any id litellm takes, resolved the way litellm's `get_model_info` resolves it:
+
+- bare names, such as `gpt-4o` and `claude-sonnet-4-5`;
+- provider prefixes, such as `openai/gpt-4o`, `anthropic/claude-sonnet-4-5`,
+  `vertex_ai/gemini-2.5-pro`, `bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0` and
+  `azure/gpt-4.1`;
+- the forms litellm strips back to a known model: a date suffix such as `-2024-08-06`, a `-001`
+  version on Vertex and Gemini, a fine-tune such as `ft:gpt-4o-2024-08-06:acme::AbC123`,
+  Bedrock regions and routes, and any letter case.
+
+A test in CI runs the same ids through litellm itself and fails if any answer differs.
+
+ctxlen reads the id string only. litellm's `custom_llm_provider=`, `api_base=` and
+`register_model` have no counterpart.
+
+## When the answer is None
+
+`None` means no source has a number. ctxlen never guesses.
+
+- The id is unknown, or empty. Nothing is trimmed: `" gpt-4o"` is unknown.
+- The id names a deployment, such as `azure/my-prod-gpt4`. Ask by model: `azure/gpt-4.1`.
+- The id is an `openrouter/` id. OpenRouter's terms forbid scripted copying, so v1 leaves it out.
+- The model is too new for litellm, and models.dev has no entry for that provider either.
+  litellm's pattern rule would guess 200,000 tokens for an unknown Claude; ctxlen does not.
+- `max_output` of an embedding model, which writes no tokens.
+- models.dev's output limit equals the whole window, which is padding rather than a limit, so it
+  is dropped.
+
+A `model` that is not a `str` raises `TypeError`.
+
+## How fresh the data is
+
+A job rebuilds the data from litellm and models.dev every 6 hours, and publishes a release when
+the data has changed. The version is the date of that snapshot: `2026.10.11.3` is the third
+release built from data fetched on 2026-10-11 (UTC).
+
+Your lock file decides what you get: `uv lock --upgrade-package ctxlen`. If a release most days
+is too much for Dependabot, group the updates or check weekly:
+
+```yaml
+version: 2
+updates:
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: weekly
+    groups:
+      ctxlen:
+        patterns: [ctxlen]
+```
+
+## Credits
+
+- [litellm](https://github.com/BerriAI/litellm) (BerriAI, MIT): the model map, and the lookup
+  ctxlen ports from it.
+- [models.dev](https://github.com/anomalyco/models.dev) (MIT): the numbers where litellm has
+  none. Its entries for OpenRouter, Vercel and Venice are not used, because their terms forbid
+  copying, and neither are Hugging Face's, whose router serves one model on hosts with different
+  windows.
+
+Both MIT notices are in [LICENSE](LICENSE), after ctxlen's own.

ctxlen-2026.10.11.dev1/pyproject.toml

@@ -0,0 +1,36 @@
+[project]
+name = "ctxlen"
+version = "2026.10.11.dev1"
+description = "max_input and max_output for any litellm model id, with no dependencies and no network"
+requires-python = ">=3.9"
+dependencies = []
+license = "MIT"
+license-files = ["LICENSE"]
+readme = "README.md"
+keywords = [
+    "llm",
+    "litellm",
+    "context window",
+    "tokens",
+    "models.dev",
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Typing :: Typed",
+]
+
+[project.urls]
+Repository = "https://github.com/michaeltheologitis/ctxlen"
+
+[build-system]
+requires = ["uv_build>=0.11.32,<0.12"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = ["pytest>=8"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["."]
+markers = ["live: real PyPI and GitHub; run with -m live"]
+addopts = "-m 'not live'"

ctxlen-2026.10.11.dev1/pyproject.toml.orig

@@ -0,0 +1,30 @@
+[project]
+name = "ctxlen"
+version = "2026.10.11.dev1"
+description = "max_input and max_output for any litellm model id, with no dependencies and no network"
+requires-python = ">=3.9"
+dependencies = []
+license = "MIT"
+license-files = ["LICENSE"]
+readme = "README.md"
+keywords = ["llm", "litellm", "context window", "tokens", "models.dev"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Typing :: Typed",
+]
+
+[project.urls]
+Repository = "https://github.com/michaeltheologitis/ctxlen"
+
+[build-system]
+requires = ["uv_build>=0.11.32,<0.12"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = ["pytest>=8"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["."]
+markers = ["live: real PyPI and GitHub; run with -m live"]
+addopts = "-m 'not live'"

ctxlen-2026.10.11.dev1/src/ctxlen/__init__.py

@@ -0,0 +1,35 @@
+"""max_input and max_output for any litellm model id, from bundled data, with no network."""
+
+import typing as _typing
+
+from ctxlen import _resolve
+
+__all__ = ["max_input", "max_output"]
+
+
+def max_input(model: str) -> _typing.Optional[int]:  # noqa: FA100 (help() shows Optional[int] on 3.9)
+    """The most input tokens `model` accepts, or None if no source knows it.
+
+    `model` is any id you would pass to litellm.completion ("gpt-4o",
+    "anthropic/claude-sonnet-4-5", "bedrock/us.anthropic..."), resolved as
+    litellm resolves it. The number is litellm's; where litellm has none,
+    models.dev's for the same provider's model.
+
+    The sources store what each provider publishes: for some models the input
+    cap (gpt-5: 272,000 of a 400,000 window), for others the whole window,
+    the reply included (Claude). ctxlen does not reconcile them: leave room
+    for the reply.
+    """
+    return _resolve.limits(model, "max_input")[0]
+
+
+def max_output(model: str) -> _typing.Optional[int]:  # noqa: FA100
+    """The most tokens `model` can generate in one reply, or None if no source knows it.
+
+    `model` is any id you would pass to litellm.completion ("gpt-4o",
+    "anthropic/claude-sonnet-4-5", "bedrock/us.anthropic..."), resolved as
+    litellm resolves it. The number is litellm's max_output_tokens for that
+    model; where litellm has none, models.dev's for the same provider's model.
+    An embedding model has no output limit, so it gives None.
+    """
+    return _resolve.limits(model, "max_output")[1]