scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

Merge d4f2c64caf into 2d0c9eed4d

Browse source
This commit is contained in:
ExDevilLee 2026-08-27 12:00:03 -07:00 • committed by GitHub
commit bfff6dd1fc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 355 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

92
litellm/model_prices_and_context_window_backup.json
View file

@ -44353,6 +44353,36 @@
"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,
"output_cost_per_token": 4.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.2": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.1": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
@ -44368,6 +44398,37 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5-turbo": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5v-turbo": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5-code": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 3e-07,
@ -44413,6 +44474,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.7-flashx": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 1e-08,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 4e-07,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.6": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 1.1e-07,
@ -44428,6 +44504,22 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.6v": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 9e-07,
"litellm_provider": "zai",
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.5": {
"input_cost_per_token": 6e-07,
"output_cost_per_token": 2.2e-06,

28
litellm/proxy/public_endpoints/provider_create_fields.json
View file

@ -3296,6 +3296,34 @@
],
"default_model_placeholder": "gpt-3.5-turbo"
},
{
"provider": "ZAI",
"provider_display_name": "Z.AI",
"litellm_provider": "zai",
"credential_fields": [
{
"key": "api_key",
"label": "API Key",
"placeholder": "your-zai-api-key",
"tooltip": "Z.AI API Key from https://z.ai/manage-apikey/apikey-list",
"required": true,
"field_type": "password",
"options": null,
"default_value": null
},
{
"key": "api_base",
"label": "API Base",
"placeholder": "https://api.z.ai/api/paas/v4",
"tooltip": "General: https://api.z.ai/api/paas/v4. GLM Coding Plan: https://api.z.ai/api/coding/paas/v4. Override for self-hosted endpoints.",
"required": false,
"field_type": "text",
"options": null,
"default_value": "https://api.z.ai/api/paas/v4"
}
],
"default_model_placeholder": "zai/glm-4.6"
},
{
"provider": "CURSOR",
"provider_display_name": "Cursor",

92
model_prices_and_context_window.json
View file

@ -44353,6 +44353,36 @@
"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,
"output_cost_per_token": 4.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.2": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.1": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
@ -44368,6 +44398,37 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5-turbo": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5v-turbo": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5-code": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 3e-07,
@ -44413,6 +44474,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.7-flashx": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 1e-08,
"input_cost_per_token": 7e-08,
"output_cost_per_token": 4e-07,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 131072,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.6": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 1.1e-07,
@ -44428,6 +44504,22 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.6v": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 5e-08,
"input_cost_per_token": 3e-07,
"output_cost_per_token": 9e-07,
"litellm_provider": "zai",
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.5": {
"input_cost_per_token": 6e-07,
"output_cost_per_token": 2.2e-06,

22
tests/test_litellm/proxy/public_endpoints/test_public_endpoints.py
View file

@ -60,6 +60,28 @@ def test_get_provider_create_fields():
), "Expected at least one provider to have detailed credential fields"
def test_zai_provider_fields():
app_instance = FastAPI()
app_instance.include_router(router)
client = TestClient(app_instance)
response = client.get("/public/providers/fields")
assert response.status_code == 200
providers = response.json()
zai = next((provider for provider in providers if provider["provider"] == "ZAI"), None)
assert zai is not None
assert zai["provider_display_name"] == "Z.AI"
assert zai["litellm_provider"] == "zai"
assert zai["default_model_placeholder"] == "zai/glm-4.6"
credential_fields = {field["key"]: field for field in zai["credential_fields"]}
assert credential_fields["api_key"]["required"] is True
assert credential_fields["api_key"]["field_type"] == "password"
assert credential_fields["api_base"]["default_value"] == "https://api.z.ai/api/paas/v4"
def test_get_litellm_model_cost_map_returns_cost_map():
app = FastAPI()
app.include_router(router)

91
tests/test_litellm/test_zai_model_metadata.py Normal file
View file

@ -0,0 +1,91 @@
import json
from pathlib import Path
CURRENT_ZAI_MODELS = {
"zai/glm-5.3",
"zai/glm-5.2",
"zai/glm-5.1",
"zai/glm-5",
"zai/glm-5-turbo",
"zai/glm-5v-turbo",
"zai/glm-4.7",
"zai/glm-4.7-flash",
"zai/glm-4.7-flashx",
"zai/glm-4.6",
"zai/glm-4.6v",
"zai/glm-4.5",
"zai/glm-4.5v",
"zai/glm-4.5-air",
"zai/glm-4.5-flash",
}
ZAI_NEW_MODEL_METADATA = {
"zai/glm-5.3": {
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
},
"zai/glm-5.2": {
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
},
"zai/glm-5-turbo": {
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4e-06,
"max_input_tokens": 200000,
"max_output_tokens": 131072,
},
"zai/glm-5v-turbo": {
"input_cost_per_token": 1.2e-06,
"output_cost_per_token": 4e-06,
"max_input_tokens": 200000,
"max_output_tokens": 131072,
"supports_vision": True,
},
"zai/glm-4.7-flashx": {
"input_cost_per_token": 7e-08,
"output_cost_per_token": 4e-07,
"max_input_tokens": 200000,
"max_output_tokens": 131072,
},
"zai/glm-4.6v": {
"input_cost_per_token": 3e-07,
"output_cost_per_token": 9e-07,
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"supports_vision": True,
},
}
def test_zai_model_metadata():
json_path = Path(__file__).parents[2] / "model_prices_and_context_window.json"
model_cost = json.loads(json_path.read_text())
assert CURRENT_ZAI_MODELS.issubset(model_cost)
for model, expected_metadata in ZAI_NEW_MODEL_METADATA.items():
assert model in model_cost, f"{model} missing from model_prices_and_context_window.json"
metadata = model_cost[model]
assert metadata["litellm_provider"] == "zai"
assert metadata["mode"] == "chat"
assert metadata["supports_function_calling"] is True
assert metadata["supports_reasoning"] is True
assert metadata["supports_tool_choice"] is True
assert metadata["supports_prompt_caching"] is True
for key, value in expected_metadata.items():
assert metadata[key] == value
def test_zai_model_metadata_backup_matches_main():
repo_root = Path(__file__).parents[2]
model_cost = json.loads((repo_root / "model_prices_and_context_window.json").read_text())
backup_model_cost = json.loads((repo_root / "litellm" / "model_prices_and_context_window_backup.json").read_text())
for model in ZAI_NEW_MODEL_METADATA:
assert backup_model_cost[model] == model_cost[model]

29
ui/litellm-dashboard/src/components/add_model/AddModelForm.test.tsx
View file

@ -340,6 +340,35 @@ describe("AddModelForm", () => {
});
});
it("should allow searching providers by their LiteLLM provider slug", async () => {
const mockUseAuthorized = vi.mocked(await import("@/app/(dashboard)/hooks/useAuthorized"));
const mockUseProviderFields = vi.mocked(await import("@/app/(dashboard)/hooks/providers/useProviderFields"));
mockUseAuthorized.default.mockReturnValue(mockAuthorizedUser("proxy_admin", "user-1", true));
mockUseProviderFields.useProviderFields.mockReturnValue({
data: [
{
provider: "ZAI",
provider_display_name: "Z.AI",
litellm_provider: "zai",
default_model_placeholder: "zai/glm-4.6",
credential_fields: [],
},
],
isLoading: false,
error: null,
});
const props = createTestProps();
const user = userEvent.setup({ pointerEventsCheck: PointerEventsCheckLevel.Never });
renderWithProviders(<AddModelForm {...props} />);
const providerSelect = await screen.findByRole("combobox", { name: /provider/i });
await user.click(providerSelect);
await user.type(providerSelect, "zai");
expect(await screen.findByText("Z.AI")).toBeInTheDocument();
});
describe("cache control bindings reach the parent form store", () => {
const renderWithForm = async () => {
const mockUseAuthorized = vi.mocked(await import("@/app/(dashboard)/hooks/useAuthorized"));

1
ui/litellm-dashboard/src/components/add_model/AddModelForm.tsx
View file

@ -123,6 +123,7 @@ const AddModelForm: React.FC<AddModelFormProps> = ({
() =>
sortedProviderMetadata.map((providerInfo) => ({
label: providerInfo.provider_display_name,
sublabel: providerInfo.litellm_provider,
value: providerInfo.provider,
icon: <ProviderLogo provider={providerInfo.provider} className="w-5 h-5" />,
})),