scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-13 08:52:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 174

feat(together_ai): add zai-org/GLM-5.3-Flash to the model registry

Browse source 
Adds pricing (0.15/0.50 per 1M tokens, 0.03 cached read), the 1M context window, and capability flags (tools, parallel tools, tool choice, response schema, reasoning, vision) for Together AI's zai-org/GLM-5.3-Flash, mirrored into the backup cost map, with exact-value regression tests.
This commit is contained in:
mateo-berri 2026-08-27 01:12:12 -07:00
parent cd63c7e5a7
commit b4c6e01fcc
3 changed files with 50 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
litellm/model_prices_and_context_window_backup.json
View file

@ -38770,6 +38770,23 @@
"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_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",

17
model_prices_and_context_window.json
View file

@ -38770,6 +38770,23 @@
"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_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",

16
tests/test_litellm/test_together_ai_model_metadata.py
View file

@ -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",
"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813",
"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731",
@ -110,6 +111,21 @@ 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_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"