mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
Merge pull request #38486 from BerriAI/litellm_together_glm53_flash
feat(together_ai): add zai-org/GLM-5.3-Flash to the model registry
This commit is contained in:
commit
a6816f0e96
5 changed files with 99 additions and 0 deletions
|
|
@ -39069,6 +39069,24 @@
|
|||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"together_ai/zai-org/GLM-5.3-Flash": {
|
||||
"cache_read_input_token_cost": 3e-08,
|
||||
"input_cost_per_token": 1.5e-07,
|
||||
"litellm_provider": "together_ai",
|
||||
"max_input_tokens": 1048575,
|
||||
"max_output_tokens": 1048575,
|
||||
"max_tokens": 1048575,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 5e-07,
|
||||
"source": "https://docs.together.ai/docs/serverless-models",
|
||||
"supports_function_calling": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true
|
||||
},
|
||||
"tts-1": {
|
||||
"input_cost_per_character": 1.5e-05,
|
||||
"litellm_provider": "openai",
|
||||
|
|
|
|||
|
|
@ -15038,6 +15038,17 @@
|
|||
}
|
||||
],
|
||||
"title": "Upstream Resource"
|
||||
},
|
||||
"upstream_token_header": {
|
||||
"anyOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "null"
|
||||
}
|
||||
],
|
||||
"title": "Upstream Token Header"
|
||||
}
|
||||
},
|
||||
"title": "MCPCredentials",
|
||||
|
|
@ -17518,6 +17529,17 @@
|
|||
}
|
||||
],
|
||||
"title": "Upstream Resource"
|
||||
},
|
||||
"upstream_token_header": {
|
||||
"anyOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "null"
|
||||
}
|
||||
],
|
||||
"title": "Upstream Token Header"
|
||||
}
|
||||
},
|
||||
"title": "MCPCredentials",
|
||||
|
|
@ -20352,6 +20374,17 @@
|
|||
}
|
||||
],
|
||||
"title": "Upstream Resource"
|
||||
},
|
||||
"upstream_token_header": {
|
||||
"anyOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "null"
|
||||
}
|
||||
],
|
||||
"title": "Upstream Token Header"
|
||||
}
|
||||
},
|
||||
"title": "MCPCredentials",
|
||||
|
|
@ -23699,6 +23732,17 @@
|
|||
}
|
||||
],
|
||||
"title": "Upstream Resource"
|
||||
},
|
||||
"upstream_token_header": {
|
||||
"anyOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "null"
|
||||
}
|
||||
],
|
||||
"title": "Upstream Token Header"
|
||||
}
|
||||
},
|
||||
"title": "MCPCredentials",
|
||||
|
|
|
|||
|
|
@ -39069,6 +39069,24 @@
|
|||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"together_ai/zai-org/GLM-5.3-Flash": {
|
||||
"cache_read_input_token_cost": 3e-08,
|
||||
"input_cost_per_token": 1.5e-07,
|
||||
"litellm_provider": "together_ai",
|
||||
"max_input_tokens": 1048575,
|
||||
"max_output_tokens": 1048575,
|
||||
"max_tokens": 1048575,
|
||||
"mode": "chat",
|
||||
"output_cost_per_token": 5e-07,
|
||||
"source": "https://docs.together.ai/docs/serverless-models",
|
||||
"supports_function_calling": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
"supports_prompt_caching": true,
|
||||
"supports_reasoning": true,
|
||||
"supports_response_schema": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": true
|
||||
},
|
||||
"tts-1": {
|
||||
"input_cost_per_character": 1.5e-05,
|
||||
"litellm_provider": "openai",
|
||||
|
|
|
|||
|
|
@ -15,6 +15,7 @@ COST_MAP_ADAPTER: Final = TypeAdapter(CostMap)
|
|||
SERVERLESS_CHAT_MODELS: Final = (
|
||||
"together_ai/moonshotai/Kimi-K3",
|
||||
"together_ai/zai-org/GLM-5.2",
|
||||
"together_ai/zai-org/GLM-5.3-Flash",
|
||||
"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813",
|
||||
"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731",
|
||||
"together_ai/MiniMaxAI/MiniMax-M3",
|
||||
|
|
@ -110,6 +111,22 @@ def test_together_glm_52_pricing(cost_map: CostMap):
|
|||
assert info["supports_reasoning"] is True
|
||||
|
||||
|
||||
def test_together_glm_53_flash_pricing_and_capabilities(cost_map: CostMap):
|
||||
info = cost_map["together_ai/zai-org/GLM-5.3-Flash"]
|
||||
assert info["input_cost_per_token"] == 1.5e-07
|
||||
assert info["output_cost_per_token"] == 5e-07
|
||||
assert info["cache_read_input_token_cost"] == 3e-08
|
||||
assert info["max_input_tokens"] == 1048575
|
||||
assert info["max_output_tokens"] == 1048575
|
||||
assert info["supports_function_calling"] is True
|
||||
assert info["supports_parallel_function_calling"] is True
|
||||
assert info["supports_prompt_caching"] is True
|
||||
assert info["supports_tool_choice"] is True
|
||||
assert info["supports_response_schema"] is True
|
||||
assert info["supports_vision"] is True
|
||||
assert info["supports_reasoning"] is True
|
||||
|
||||
|
||||
def test_together_multilingual_e5_embedding_entry(cost_map: CostMap):
|
||||
info = cost_map["together_ai/intfloat/multilingual-e5-large-instruct"]
|
||||
assert info["mode"] == "embedding"
|
||||
|
|
|
|||
2
ui/litellm-dashboard/src/lib/http/schema.d.ts
generated
vendored
2
ui/litellm-dashboard/src/lib/http/schema.d.ts
generated
vendored
|
|
@ -30221,6 +30221,8 @@ export interface components {
|
|||
token_exchange_profile?: string | null;
|
||||
/** Upstream Resource */
|
||||
upstream_resource?: string | null;
|
||||
/** Upstream Token Header */
|
||||
upstream_token_header?: string | null;
|
||||
};
|
||||
/**
|
||||
* MCPEnvVar
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue