From 1c289e5ecd1a022e71fface263992708d1b536e8 Mon Sep 17 00:00:00 2001
From: "devin-ai-integration[bot]"
 <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Wed, 23 Sep 2026 11:31:27 -0700
Subject: [PATCH] fix(prices): add baseten/zai-org/GLM-5.3-Fast pricing
 (#42764)

* fix(prices): add baseten/zai-org/GLM-5.3-Fast pricing with cost tracking e2e

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(e2e): assert message instead of comment on breakdown row

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(baseten): drop the live e2e cost tracking test

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: kerry <kerry@berri.ai>
---
 ...odel_prices_and_context_window_backup.json | 24 +++++++++++++++++++
 model_prices_and_context_window.json          | 24 +++++++++++++++++++
 tests/test_litellm/test_cost_calculator.py    | 18 ++++++++++++++
 3 files changed, 66 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index da8013ae709..4a058eafd1f 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -64063,6 +64063,30 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "baseten/zai-org/GLM-5.3-Fast": {
+        "cache_read_input_token_cost": 2.1e-07,
+        "input_cost_per_token": 2.1e-06,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-06,
+        "source": "https://www.baseten.co/library/glm-53-fast/",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "openrouter/minimax/minimax-m3": {
         "input_cost_per_token": 3e-07,
         "output_cost_per_token": 1.2e-06,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index da8013ae709..4a058eafd1f 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -64063,6 +64063,30 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "baseten/zai-org/GLM-5.3-Fast": {
+        "cache_read_input_token_cost": 2.1e-07,
+        "input_cost_per_token": 2.1e-06,
+        "litellm_provider": "baseten",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-06,
+        "source": "https://www.baseten.co/library/glm-53-fast/",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "openrouter/minimax/minimax-m3": {
         "input_cost_per_token": 3e-07,
         "output_cost_per_token": 1.2e-06,
diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py
index 10a904d6141..f7d6cfaf079 100644
--- a/tests/test_litellm/test_cost_calculator.py
+++ b/tests/test_litellm/test_cost_calculator.py
@@ -4635,6 +4635,24 @@ def test_gemini_live_native_audio_limits_and_capabilities_match_vendor_model_car
     assert info["supports_pdf_input"] is False
 
 
+def test_baseten_glm_5_3_fast_is_priced_from_registry(_local_model_cost_map: None) -> None:
+    model: Final = "baseten/zai-org/GLM-5.3-Fast"
+    prompt_tokens: Final = 1000
+    completion_tokens: Final = 500
+
+    prompt_usd, completion_usd = litellm.cost_per_token(
+        model=model,
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+    )
+
+    entry: Final = litellm.model_cost[model]
+    assert prompt_usd == pytest.approx(prompt_tokens * entry["input_cost_per_token"])
+    assert completion_usd == pytest.approx(completion_tokens * entry["output_cost_per_token"])
+    assert prompt_usd > 0
+    assert completion_usd > 0
+
+
 def test_completion_cost_charges_explicit_per_token_rates_over_registered_ones(
     monkeypatch: pytest.MonkeyPatch,
 ) -> None: