scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-10 03:28:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 85

feat(model_prices): add zai glm 5.3

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-08-26 22:27:21 +00:00
parent e4cdeeac58
commit eef22e57a4
3 changed files with 60 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
litellm/model_prices_and_context_window_backup.json
View file

@ -44332,6 +44332,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.3": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://docs.z.ai/guides/overview/pricing",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"zai/glm-5.1": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,

15
model_prices_and_context_window.json
View file

@ -44332,6 +44332,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.3": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://docs.z.ai/guides/overview/pricing",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"zai/glm-5.1": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,

30
tests/test_litellm/llms/zai/test_zai_provider.py
View file

@ -128,6 +128,36 @@ def test_glm47_cost_calculation(local_model_cost_map):
assert math.isclose(completion_cost, 2.2, rel_tol=1e-6)
def test_glm53_context_and_capabilities(local_model_cost_map):
"""GLM-5.3 ships a 1M context with 128K max output, text in, reasoning always on"""
info = litellm.model_cost["zai/glm-5.3"]
assert info["max_input_tokens"] == 1000000
assert info["max_output_tokens"] == 128000
assert info["supports_reasoning"] is True
assert info["supports_prompt_caching"] is True
assert info.get("supports_vision") is not True
def test_glm53_cost_calculation(local_model_cost_map):
"""GLM-5.3 bills $1.4/M input, $4.4/M output, $0.26/M on a cache hit"""
prompt_cost, completion_cost = cost_per_token(
model="zai/glm-5.3",
prompt_tokens=1000000,
completion_tokens=1000000,
)
assert math.isclose(prompt_cost, 1.4, rel_tol=1e-6)
assert math.isclose(completion_cost, 4.4, rel_tol=1e-6)
assert math.isclose(
litellm.model_cost["zai/glm-5.3"]["cache_read_input_token_cost"] * 1000000,
0.26,
rel_tol=1e-6,
)
@pytest.mark.asyncio
async def test_zai_completion_call(respx_mock, zai_response, monkeypatch):
"""Test completion call with zai provider using mocked response"""