scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-30 06:43:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 249

Merge b250ff66eb into bc18e10f6b

Browse source
This commit is contained in:
kailian zhou 2026-10-23 17:15:37 +00:00 • committed by GitHub
commit a9859ee1d3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 1049 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
litellm/__init__.py
View file

@ -680,6 +680,7 @@ moonshot_models: Set = set()
publicai_models: Set = set()
darkbloom_models: Set = set()
openinfer_models: Final[Set[str]] = set()
streamlake_models: Final[Set[str]] = set()
v0_models: Set = set()
morph_models: Set = set()
lambda_ai_models: Set = set()
@ -966,6 +967,8 @@ def _populate_provider_model_sets(model_cost_map: Mapping[str, Mapping[str, obje
darkbloom_models.add(key)
elif value.get("litellm_provider") == "openinfer":
openinfer_models.add(key)
elif value.get("litellm_provider") == "streamlake":
streamlake_models.add(key)
elif value.get("litellm_provider") == "v0":
v0_models.add(key)
elif value.get("litellm_provider") == "morph":
@ -1135,6 +1138,7 @@ model_list = list(
| publicai_models
| darkbloom_models
| openinfer_models
| streamlake_models
| v0_models
| morph_models
| lambda_ai_models
@ -1252,6 +1256,7 @@ def _build_models_by_provider() -> dict:
"publicai": publicai_models,
"darkbloom": darkbloom_models,
"openinfer": openinfer_models,
"streamlake": streamlake_models,
"v0": v0_models,
"morph": morph_models,
"lambda_ai": lambda_ai_models,

2
litellm/constants.py
View file

@ -1060,6 +1060,7 @@ openai_compatible_endpoints: Final[list[str]] = [
"https://api.reka.ai/v1",
"https://gigachat.devices.sberbank.ru/api/v1",
"https://api.openinfer.ai/v1",
"https://vanchin.streamlake.ai/api/gateway/v1/endpoints",
]
@ -1138,6 +1139,7 @@ openai_compatible_providers: Final[list[str]] = [
"prism",
"sail",
"reka",
"streamlake",
]
OPENAI_AUDIO_TRANSCRIPTION_PROVIDERS: Final = frozenset({"openai"} | frozenset(openai_compatible_providers))

13
litellm/llms/openai_like/providers.json
View file

@ -249,5 +249,18 @@
"/v1/responses",
"/v1/messages"
]
},
"streamlake": {
"base_url": "https://vanchin.streamlake.ai/api/gateway/v1/endpoints",
"api_key_env": "STREAMLAKE_API_KEY",
"api_base_env": "STREAMLAKE_API_BASE",
"param_mappings": {
"max_completion_tokens": "max_tokens"
},
"provider_info": {
"supports_function_calling": true,
"supports_reasoning": true
},
"supported_endpoints": ["/v1/chat/completions"]
}
}

291
litellm/model_prices_and_context_window_backup.json
View file

@ -62175,6 +62175,297 @@
"supports_tool_choice": true,
"supports_vision": true
},
"streamlake/deepseek-v4-flash-0731": {
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 4.4e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/DeepSeek-V4-Pro-0813": {
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/DeepSeek-V3": {
"cache_read_input_token_cost": 1.14e-07,
"input_cost_per_token": 2.86e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 56000,
"max_output_tokens": 8000,
"max_tokens": 8000,
"mode": "chat",
"output_cost_per_token": 1.143e-06,
"supports_function_calling": true,
"supports_reasoning": false,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/GLM-5.3": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_assistant_prefill": true,
"supports_prompt_caching": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/GLM-5.3-Flash": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_assistant_prefill": true,
"supports_prompt_caching": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/Kimi-K2-Instruct-0905": {
"cache_read_input_token_cost": 1.43e-07,
"input_cost_per_token": 5.71e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 224000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.286e-06,
"supports_function_calling": true,
"supports_reasoning": false,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-r1": {
"cache_read_input_token_cost": 2.29e-07,
"input_cost_per_token": 5.71e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 112000,
"max_output_tokens": 16000,
"max_tokens": 16000,
"mode": "chat",
"output_cost_per_token": 2.286e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v3.1": {
"cache_read_input_token_cost": 2.29e-07,
"input_cost_per_token": 5.71e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 96000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 1.714e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4-flash": {
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.4e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4-pro": {
"cache_read_input_token_cost": 1.45e-07,
"input_cost_per_token": 1.74e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.48e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4.1-flash-1017": {
"cache_read_input_token_cost": 6e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4.1-flash-260910": {
"cache_read_input_token_cost": 6e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/glm-5": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 1e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/glm-5.1": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/glm-5.2": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/kimi-k2.6": {
"cache_read_input_token_cost": 1.6e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"supports_function_calling": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 256000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/minimax-m2.5": {
"cache_creation_input_token_cost": 3.75e-07,
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 3e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.5-397b-a17b": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 252000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.6-27b": {
"input_cost_per_token": 6e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 254000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"supports_function_calling": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.6-35b-a3b": {
"input_cost_per_token": 3.75e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 254000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 2.25e-06,
"supports_function_calling": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.8-2.4t-a95b": {
"input_cost_per_token": 2e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 991000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"deepseek-v4-flash": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 6e-09,

17
litellm/provider_endpoints_support_backup.json
View file

@ -2748,6 +2748,23 @@
"rerank": false,
"a2a": false
}
},
"streamlake": {
"display_name": "StreamLake (`streamlake`)",
"url": "https://docs.litellm.ai/docs/providers/openai_compatible",
"endpoints": {
"chat_completions": true,
"messages": false,
"responses": false,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
}
},
"endpoints": {

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

@ -3417,6 +3417,34 @@
],
"default_model_placeholder": "inferenceapis/deepseek-ai/DeepSeek-V4-Flash"
},
{
"provider": "StreamLake",
"provider_display_name": "StreamLake",
"litellm_provider": "streamlake",
"credential_fields": [
{
"key": "api_base",
"label": "API Base",
"placeholder": "https://vanchin.streamlake.ai/api/gateway/v1/endpoints",
"tooltip": null,
"required": false,
"field_type": "text",
"options": null,
"default_value": null
},
{
"key": "api_key",
"label": "API Key",
"placeholder": null,
"tooltip": null,
"required": true,
"field_type": "password",
"options": null,
"default_value": null
}
],
"default_model_placeholder": "streamlake/GLM-5.3-Flash"
},
{
"provider": "Snowflake",
"provider_display_name": "Snowflake",

1
litellm/types/utils.py
View file

@ -4553,6 +4553,7 @@ class LlmProviders(str, Enum):
META = "meta"
SAIL = "sail"
REKA = "reka"
STREAMLAKE = "streamlake"
LITELLM_AGENT = "litellm_agent"
CURSOR = "cursor"
BEDROCK_MANTLE = "bedrock_mantle"

291
model_prices_and_context_window.json
View file

@ -62175,6 +62175,297 @@
"supports_tool_choice": true,
"supports_vision": true
},
"streamlake/deepseek-v4-flash-0731": {
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 4.4e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.32e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/DeepSeek-V4-Pro-0813": {
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/DeepSeek-V3": {
"cache_read_input_token_cost": 1.14e-07,
"input_cost_per_token": 2.86e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 56000,
"max_output_tokens": 8000,
"max_tokens": 8000,
"mode": "chat",
"output_cost_per_token": 1.143e-06,
"supports_function_calling": true,
"supports_reasoning": false,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/GLM-5.3": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_assistant_prefill": true,
"supports_prompt_caching": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/GLM-5.3-Flash": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_assistant_prefill": true,
"supports_prompt_caching": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/Kimi-K2-Instruct-0905": {
"cache_read_input_token_cost": 1.43e-07,
"input_cost_per_token": 5.71e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 224000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 2.286e-06,
"supports_function_calling": true,
"supports_reasoning": false,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-r1": {
"cache_read_input_token_cost": 2.29e-07,
"input_cost_per_token": 5.71e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 112000,
"max_output_tokens": 16000,
"max_tokens": 16000,
"mode": "chat",
"output_cost_per_token": 2.286e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v3.1": {
"cache_read_input_token_cost": 2.29e-07,
"input_cost_per_token": 5.71e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 96000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 1.714e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4-flash": {
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.4e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4-pro": {
"cache_read_input_token_cost": 1.45e-07,
"input_cost_per_token": 1.74e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 3.48e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4.1-flash-1017": {
"cache_read_input_token_cost": 6e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/deepseek-v4.1-flash-260910": {
"cache_read_input_token_cost": 6e-09,
"input_cost_per_token": 3e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 384000,
"max_tokens": 384000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/glm-5": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 1e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/glm-5.1": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/glm-5.2": {
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 1048576,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/kimi-k2.6": {
"cache_read_input_token_cost": 1.6e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"supports_function_calling": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
"input_cost_per_token": 9.5e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 256000,
"max_output_tokens": 32000,
"max_tokens": 32000,
"mode": "chat",
"output_cost_per_token": 4e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/minimax-m2.5": {
"cache_creation_input_token_cost": 3.75e-07,
"cache_read_input_token_cost": 3e-08,
"input_cost_per_token": 3e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.5-397b-a17b": {
"cache_read_input_token_cost": 1.2e-07,
"input_cost_per_token": 6e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 252000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.6-27b": {
"input_cost_per_token": 6e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 254000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 3.6e-06,
"supports_function_calling": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.6-35b-a3b": {
"input_cost_per_token": 3.75e-07,
"litellm_provider": "streamlake",
"max_input_tokens": 254000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 2.25e-06,
"supports_function_calling": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"streamlake/qwen3.8-2.4t-a95b": {
"input_cost_per_token": 2e-06,
"litellm_provider": "streamlake",
"max_input_tokens": 991000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://www.streamlake.ai/document/DOC/mgrnm4xm362hvp5wyce"
},
"deepseek-v4-flash": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 6e-09,

17
provider_endpoints_support.json
View file

@ -2547,6 +2547,23 @@
"text_completion": true
}
},
"streamlake": {
"display_name": "StreamLake (`streamlake`)",
"url": "https://docs.litellm.ai/docs/providers/openai_compatible",
"endpoints": {
"chat_completions": true,
"messages": true,
"responses": true,
"embeddings": false,
"image_generations": false,
"audio_transcriptions": false,
"audio_speech": false,
"moderations": false,
"batches": false,
"rerank": false,
"a2a": false
}
},
"tencent": {
"display_name": "Tencent TokenHub (`tencent`)",
"url": "https://docs.litellm.ai/docs/providers/tencent",

315
tests/unit/llms/openai_like/test_streamlake_provider.py Normal file
View file

@ -0,0 +1,315 @@
import json
from pathlib import Path
from typing import Final
import httpx
import pytest
import respx
import litellm
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
from litellm.llms.openai_like.dynamic_config import create_config_class
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
from litellm.types.utils import ModelResponse, Usage
STREAMLAKE_BASE_URL = "https://vanchin.streamlake.ai/api/gateway/v1/endpoints"
STREAMLAKE_CHAT_URL = f"{STREAMLAKE_BASE_URL}/chat/completions"
REPO_ROOT: Final = Path(__file__).parents[4]
class TestStreamlakeProviderConfig:
def test_streamlake_provider_resolution(self):
model, provider, api_key, api_base = get_llm_provider(
model="streamlake/ep-test-endpoint",
custom_llm_provider=None,
api_base=None,
api_key="sk-test",
)
assert model == "ep-test-endpoint"
assert provider == "streamlake"
assert api_base == STREAMLAKE_BASE_URL
assert api_key == "sk-test"
def test_streamlake_api_base_override(self):
model, provider, api_key, api_base = get_llm_provider(
model="streamlake/ep-test-endpoint",
custom_llm_provider=None,
api_base="https://custom.streamlake.example/v1",
api_key="sk-test",
)
assert model == "ep-test-endpoint"
assert provider == "streamlake"
assert api_base == "https://custom.streamlake.example/v1"
assert api_key == "sk-test"
def test_streamlake_url_autodetection(self):
model, provider, api_key, api_base = get_llm_provider(
model="some-public-model",
custom_llm_provider=None,
api_base=STREAMLAKE_BASE_URL,
api_key=None,
)
assert provider == "streamlake"
assert api_base == STREAMLAKE_BASE_URL
def test_streamlake_api_key_resolved_from_env(self, monkeypatch):
monkeypatch.setenv("STREAMLAKE_API_KEY", "sk-env-key")
_, provider, api_key, _ = get_llm_provider(
model="streamlake/ep-test-endpoint",
custom_llm_provider=None,
api_base=None,
api_key=None,
)
assert provider == "streamlake"
assert api_key == "sk-env-key"
def test_streamlake_validate_environment_sets_bearer(self):
from litellm.llms.openai_like.dynamic_config import create_config_class
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
provider = JSONProviderRegistry.get("streamlake")
assert provider is not None
config = create_config_class(provider)()
headers = config.validate_environment(
headers={},
model="ep-test-endpoint",
messages=[{"role": "user", "content": "hi"}],
optional_params={},
litellm_params={},
api_key="sk-resolved-key",
api_base=None,
)
assert headers["Authorization"] == "Bearer sk-resolved-key"
def test_streamlake_complete_url_appends_chat_completions(self):
from litellm.llms.openai_like.dynamic_config import create_config_class
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
provider = JSONProviderRegistry.get("streamlake")
assert provider is not None
config = create_config_class(provider)()
url = config.get_complete_url(
api_base=None,
api_key="sk-test",
model="ep-test-endpoint",
optional_params={},
litellm_params={},
)
assert url == STREAMLAKE_CHAT_URL
def test_streamlake_max_completion_tokens_mapped_to_max_tokens(self):
from litellm.llms.openai_like.dynamic_config import create_config_class
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
provider = JSONProviderRegistry.get("streamlake")
assert provider is not None
config = create_config_class(provider)()
optional_params = config.map_openai_params(
non_default_params={"max_completion_tokens": 1024},
optional_params={},
model="ep-test-endpoint",
drop_params=False,
)
assert optional_params == {"max_tokens": 1024}
assert "max_completion_tokens" not in optional_params
def test_streamlake_chat_params_pass_through(self):
from litellm.llms.openai_like.dynamic_config import create_config_class
from litellm.llms.openai_like.json_loader import JSONProviderRegistry
provider = JSONProviderRegistry.get("streamlake")
assert provider is not None
config = create_config_class(provider)()
optional_params = config.map_openai_params(
non_default_params={"temperature": 0.2, "top_p": 0.9, "stream": True},
optional_params={},
model="ep-test-endpoint",
drop_params=False,
)
assert optional_params == {"temperature": 0.2, "top_p": 0.9, "stream": True}
@pytest.mark.asyncio
@pytest.mark.parametrize(
"is_async, api_base",
(
(False, None),
(False, "https://custom.streamlake.example/v1"),
(False, "https://custom.streamlake.example/v1/"),
(True, None),
(True, "https://custom.streamlake.example/v1"),
(True, "https://custom.streamlake.example/v1/"),
),
ids=(
"sync-default",
"sync-override",
"sync-override-trailing-slash",
"async-default",
"async-override",
"async-override-trailing-slash",
),
)
async def test_streamlake_completion_uses_openai_compatible_http(
is_async: bool, api_base: str | None, monkeypatch: pytest.MonkeyPatch
) -> None:
response_body: Final[dict[str, object]] = {
"id": "chatcmpl-streamlake-test",
"object": "chat.completion",
"created": 1710000000,
"model": "ep-test-endpoint",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "StreamLake response"},
"finish_reason": "stop",
}
],
"usage": {"prompt_tokens": 3, "completion_tokens": 2, "total_tokens": 5},
}
expected_url: Final[str] = f"{(api_base or STREAMLAKE_BASE_URL).rstrip('/')}/chat/completions"
expected_request_body: Final[dict[str, object]] = {
"messages": [{"role": "user", "content": "hello"}],
"model": "ep-test-endpoint",
"max_tokens": 512,
}
def handler(request: httpx.Request) -> httpx.Response:
assert request.method == "POST"
assert str(request.url) == expected_url
assert request.headers["authorization"] == "Bearer sk-streamlake-test"
assert request.headers["content-type"] == "application/json"
assert json.loads(request.content) == expected_request_body
return httpx.Response(200, json=response_body, request=request)
monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
litellm.in_memory_llm_clients_cache.flush_cache()
with respx.mock(assert_all_called=True) as respx_mock:
route: Final = respx_mock.post(expected_url).mock(side_effect=handler)
if is_async:
response: Final = await litellm.acompletion(
model="streamlake/ep-test-endpoint",
messages=[{"role": "user", "content": "hello"}],
api_key="sk-streamlake-test",
api_base=api_base,
max_completion_tokens=512,
)
else:
response: Final = litellm.completion(
model="streamlake/ep-test-endpoint",
messages=[{"role": "user", "content": "hello"}],
api_key="sk-streamlake-test",
api_base=api_base,
max_completion_tokens=512,
)
assert route.call_count == 1
assert len(response.choices) == 1
assert response.choices[0].message.role == "assistant"
assert response.choices[0].message.content == "StreamLake response"
assert response.usage is not None
assert response.usage.prompt_tokens == 3
assert response.usage.completion_tokens == 2
assert response.usage.total_tokens == 5
@pytest.mark.usefixtures("local_model_cost_map")
def test_endpoint_id_call_forwards_tools_and_reasoning_effort_to_streamlake(monkeypatch: pytest.MonkeyPatch) -> None:
tools: Final = [
{
"type": "function",
"function": {
"name": "get_weather",
"parameters": {"type": "object", "properties": {"city": {"type": "string"}}},
},
}
]
response_body: Final[dict[str, object]] = {
"id": "chatcmpl-streamlake-tools",
"object": "chat.completion",
"created": 1710000000,
"model": "glm-5.3",
"choices": [{"index": 0, "message": {"role": "assistant", "content": "ok"}, "finish_reason": "stop"}],
"usage": {"prompt_tokens": 3, "completion_tokens": 1, "total_tokens": 4},
}
monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
litellm.in_memory_llm_clients_cache.flush_cache()
with respx.mock(assert_all_called=True) as respx_mock:
route: Final = respx_mock.post(STREAMLAKE_CHAT_URL).mock(
return_value=httpx.Response(200, json=response_body)
)
litellm.completion(
model="streamlake/ep-test-endpoint",
messages=[{"role": "user", "content": "weather in Paris?"}],
api_key="sk-streamlake-test",
tools=tools,
tool_choice="auto",
reasoning_effort="low",
)
sent: Final = json.loads(route.calls.last.request.content)
assert sent["tools"] == tools
assert sent["tool_choice"] == "auto"
assert sent["reasoning_effort"] == "low"
def _streamlake_keys(cost_map: dict[str, object]) -> tuple[str, ...]:
return tuple(key for key in cost_map if key.startswith("streamlake/"))
def test_root_and_backup_cost_maps_carry_the_same_streamlake_rows() -> None:
root: Final = json.loads((REPO_ROOT / "model_prices_and_context_window.json").read_text())
backup: Final = json.loads((REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json").read_text())
assert _streamlake_keys(root)
assert {key: root[key] for key in _streamlake_keys(root)} == {key: backup[key] for key in _streamlake_keys(backup)}
@pytest.mark.usefixtures("local_model_cost_map")
def test_endpoint_id_call_is_priced_from_the_lowercase_model_streamlake_returns() -> None:
keys: Final = _streamlake_keys(litellm.model_cost)
assert keys
for key in keys:
info = litellm.get_model_info(model=key)
response = ModelResponse(
model=key.split("/", 1)[1].lower(),
usage=Usage(prompt_tokens=1000, completion_tokens=500, total_tokens=1500),
)
cost = litellm.completion_cost(
completion_response=response,
model="streamlake/ep-test-endpoint",
custom_llm_provider="streamlake",
)
expected = 1000 * info["input_cost_per_token"] + 500 * info["output_cost_per_token"]
assert cost == pytest.approx(expected), key
@pytest.mark.usefixtures("local_model_cost_map")
def test_named_model_params_follow_the_row_and_fall_back_to_the_provider_default() -> None:
provider: Final = JSONProviderRegistry.get("streamlake")
assert provider is not None
config: Final = create_config_class(provider)()
keys: Final = _streamlake_keys(litellm.model_cost)
assert keys
for key in keys:
row = litellm.model_cost[key]
supported = config.get_supported_openai_params(model=key.split("/", 1)[1].lower())
assert ("tools" in supported) is (row.get("supports_function_calling") is not False), key
assert ("reasoning_effort" in supported) is (row.get("supports_reasoning") is not False), key
@pytest.mark.usefixtures("local_model_cost_map")
def test_streamlake_wildcard_expands_to_every_streamlake_row() -> None:
from litellm.proxy.auth.model_checks import get_known_models_from_wildcard
expanded: Final = get_known_models_from_wildcard("streamlake/*")
assert set(expanded) == set(_streamlake_keys(litellm.model_cost))

23
tests/unit/proxy/public_endpoints/test_public_endpoints.py
View file

@ -1121,6 +1121,29 @@ def test_get_supported_endpoints_chat_completions_present(reset_endpoints_cache)
assert len(chat["providers"]) > 0
def test_get_supported_endpoints_streamlake_only_advertises_chat_completions(
reset_endpoints_cache: None,
) -> None:
app: Final[FastAPI] = FastAPI()
app.include_router(router)
client: Final[TestClient] = TestClient(app)
with client:
response: Final = client.get("/public/endpoints")
assert response.status_code == 200, response.text
endpoints: Final = response.json()["endpoints"]
streamlake_endpoints: Final = {
endpoint["key"]
for endpoint in endpoints
if any(provider["slug"] == "streamlake" for provider in endpoint["providers"])
}
assert streamlake_endpoints == {"chat_completions"}
chat_completions: Final = next(endpoint for endpoint in endpoints if endpoint["key"] == "chat_completions")
assert chat_completions["endpoint"] == "/chat/completions"
assert "streamlake" in {provider["slug"] for provider in chat_completions["providers"]}
def test_get_supported_endpoints_display_names_have_no_slug_suffix(
reset_endpoints_cache,
):

29
ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/panels/AddModelPanel.integration.test.tsx
View file

@ -80,6 +80,13 @@ vi.mock("@/app/(dashboard)/hooks/providers/useProviderFields", () => ({
default_model_placeholder: "jev-latest",
credential_fields: [{ key: "api_key", label: "API Key", field_type: "password", required: false }],
},
{
provider: "StreamLake",
provider_display_name: "StreamLake",
litellm_provider: "streamlake",
default_model_placeholder: "streamlake/<model-or-endpoint>",
credential_fields: [{ key: "api_key", label: "API Key", field_type: "password", required: false }],
},
],
isLoading: false,
error: null,
@ -278,6 +285,28 @@ describe("AddModelPanel submit payload contract", () => {
});
});
it("creates a StreamLake model from a public model selection and API key", async () => {
mockUseModelCostMap.mockReturnValue({ data: { "streamlake/GLM-5.3": { litellm_provider: "streamlake" } } });
const { user, submit } = await setup();
await user.click(screen.getByRole("combobox", { name: /provider/i }));
await user.click(await screen.findByText("StreamLake"));
await user.click(screen.getByRole("combobox", { name: "Select models" }));
await user.click(await screen.findByText("streamlake/GLM-5.3"));
await user.type(screen.getByLabelText("API Key"), "sk-streamlake-test");
await submit();
expect(lastCreatedModel()).toStrictEqual({
model_name: "streamlake/GLM-5.3",
litellm_params: {
model: "streamlake/GLM-5.3",
custom_llm_provider: "streamlake",
api_key: "sk-streamlake-test",
},
model_info: { ...baseModelInfo },
});
});
it("registers four more keys as undefined once Advanced Settings opens", async () => {
const { openAdvanced, fillRequired, submit } = await setup();
await fillRequired();

14
ui/litellm-dashboard/src/components/provider_info_helpers.test.tsx
View file

@ -222,6 +222,7 @@ describe("provider_info_helpers", () => {
Providers.PG_VECTOR,
Providers.PREDIBASE,
Providers.Sail,
Providers.StreamLake,
Providers.WANDB,
Providers.ZAI,
];
@ -457,6 +458,19 @@ describe("provider_info_helpers", () => {
expect(result).toEqual(["gpt-3.5-turbo", "gpt-4"]);
});
it("should return StreamLake models and exclude models from other providers", () => {
const modelMap = {
"streamlake/GLM-5.3": { litellm_provider: "streamlake" },
"streamlake/DeepSeek-V3": { litellm_provider: "streamlake" },
"gpt-4o": { litellm_provider: "openai" },
};
const result = getProviderModels(Providers.StreamLake, modelMap);
expect(provider_map.StreamLake).toBe("streamlake");
expect(result).toEqual(["streamlake/GLM-5.3", "streamlake/DeepSeek-V3"]);
expect(result).not.toContain("gpt-4o");
});
it("should return models whose litellm_provider is a prefix-anchored variant of the provider", () => {
const modelMap = {
"anthropic-text-model": { litellm_provider: "anthropic_text" },

3
ui/litellm-dashboard/src/components/provider_info_helpers.tsx
View file

@ -175,6 +175,7 @@ export enum Providers {
Snowflake = "Snowflake",
Soniox = "Soniox",
StrandsDecider = "Strands Decider",
StreamLake = "StreamLake",
TEXT_COMPLETION_CODESTRAL = "Text-Completion-Codestral",
Tencent = "Tencent",
TogetherAI = "TogetherAI",
@ -302,6 +303,7 @@ export const provider_map: Record<string, string> = {
Snowflake: "snowflake",
Soniox: "soniox",
StrandsDecider: "strands_decider",
StreamLake: "streamlake",
TEXT_COMPLETION_CODESTRAL: "text-completion-codestral",
Tencent: "tencent",
TogetherAI: "together_ai",
@ -488,6 +490,7 @@ const providerPlaceholderMap: Partial<Record<Providers, string>> = {
[Providers.Tencent]: "tencent/deepseek-v4-pro",
[Providers.TypeSafe]: "typesafe/jev-latest",
[Providers.Nace]: "nace/drex-latest",
[Providers.StreamLake]: "streamlake/<model-or-endpoint>",
[Providers.Vertex_AI]: "gemini-pro",
[Providers.VolcEngine]: "volcengine/<any-model-on-volcengine>",
[Providers.Voyage]: "voyage/",