Add new Claude models (Sonnet-4 and Opus-4) (#73)

Co-authored-by: Jonas Mueller <[email protected]>

Author: elisno

CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.1.8] - 2025-06-11
+
+### Added
+
+- Add new Claude models: `claude-opus-4-0`, `claude-sonnet-4-0`
+
 ## [1.1.7] - 2025-06-05
 
 - Updated `chat.py` to handle the Responses API `instructions` parameter
@@ -174,7 +180,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Release of the Cleanlab TLM Python client.
 
-[Unreleased]: https://github.com/cleanlab/cleanlab-tlm/compare/v1.1.7...HEAD
+[Unreleased]: https://github.com/cleanlab/cleanlab-tlm/compare/v1.1.8...HEAD
+[1.1.8]: https://github.com/cleanlab/cleanlab-tlm/compare/v1.1.7...v1.1.8
 [1.1.7]: https://github.com/cleanlab/cleanlab-tlm/compare/v1.1.6...v1.1.7
 [1.1.6]: https://github.com/cleanlab/cleanlab-tlm/compare/v1.1.5...v1.1.6
 [1.1.5]: https://github.com/cleanlab/cleanlab-tlm/compare/v1.1.4...v1.1.5

src/cleanlab_tlm/__about__.py

@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: MIT
-__version__ = "1.1.7"
+__version__ = "1.1.8"

src/cleanlab_tlm/internal/constants.py

@@ -28,6 +28,8 @@
     "claude-3.5-sonnet",
     "claude-3.5-sonnet-v2",
     "claude-3.7-sonnet",
+    "claude-opus-4-0",
+    "claude-sonnet-4-0",
     "nova-micro",
     "nova-lite",
     "nova-pro",

src/cleanlab_tlm/tlm.py

@@ -598,12 +598,12 @@ class TLMOptions(TypedDict):
 
     Args:
         model ({"gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano", "o4-mini", "o3", "gpt-4.5-preview", "gpt-4o-mini", "gpt-4o", "o3-mini", \
-         "o1", "o1-mini", "gpt-4", "gpt-3.5-turbo-16k", "claude-3.7-sonnet", "claude-3.5-sonnet-v2", "claude-3.5-sonnet", \
-         "claude-3.5-haiku", "claude-3-haiku", "nova-micro", "nova-lite", "nova-pro"}, default = "gpt-4.1-mini"): \
+         "o1", "o1-mini", "gpt-4", "gpt-3.5-turbo-16k", "claude-opus-4-0", "claude-sonnet-4-0", "claude-3.7-sonnet",  \
+         "claude-3.5-sonnet-v2", "claude-3.5-sonnet", "claude-3.5-haiku", "claude-3-haiku", "nova-micro", "nova-lite", "nova-pro"}, default = "gpt-4.1-mini"): \
         Underlying base LLM to use (better models yield better results, faster models yield faster results).
         - Models still in beta: "o3", "o1", "o4-mini", "o3-mini", "o1-mini", "gpt-4.5-preview", \
-            "claude-3.7-sonnet", "claude-3.5-haiku".
-        - Recommended models for accuracy: "gpt-4.1", "o4-mini", "o3", "claude-3.7-sonnet", "claude-3.5-sonnet-v2".
+            "claude-opus-4-0", "claude-sonnet-4-0", "claude-3.7-sonnet", "claude-3.5-haiku".
+        - Recommended models for accuracy: "gpt-4.1", "o4-mini", "o3", "claude-opus-4-0", "claude-sonnet-4-0".
         - Recommended models for low latency/costs: "gpt-4.1-nano", "nova-micro".
 
         max_tokens (int, default = 512): the maximum number of tokens that can be generated in the TLM response (and in internal trustworthiness scoring).

tests/constants.py

@@ -27,6 +27,8 @@
     "claude-3.5-sonnet",
     "claude-3.5-sonnet-v2",
     "claude-3.7-sonnet",
+    "claude-opus-4-0",
+    "claude-sonnet-4-0",
     "o1-preview",
     "o1",
     "o1-mini",
@@ -47,6 +49,8 @@
     "claude-3.5-sonnet",
     "claude-3.5-sonnet-v2",
     "claude-3.7-sonnet",
+    "claude-opus-4-0",
+    "claude-sonnet-4-0",
     "o1-preview",
     "o1",
     "o1-mini",