feat: add gpt-5.3-chat-latest model support (#9746)
Add OpenAI's GPT-5.3 Chat model (128K context, 16K output) with pricing specs, and remove the "chat" keyword filter so chat variants are listed. 🐾 Generated with [Letta Code](https://letta.com) Co-authored-by: Letta Code <noreply@letta.com>
This commit is contained in:
@@ -17295,6 +17295,32 @@
|
|||||||
"supports_tool_choice": true,
|
"supports_tool_choice": true,
|
||||||
"supports_vision": true
|
"supports_vision": true
|
||||||
},
|
},
|
||||||
|
"gpt-5.3-chat-latest": {
|
||||||
|
"cache_read_input_token_cost": 1.75e-7,
|
||||||
|
"cache_read_input_token_cost_priority": 3.5e-7,
|
||||||
|
"input_cost_per_token": 1.75e-6,
|
||||||
|
"input_cost_per_token_priority": 3.5e-6,
|
||||||
|
"litellm_provider": "openai",
|
||||||
|
"max_input_tokens": 128000,
|
||||||
|
"max_output_tokens": 16384,
|
||||||
|
"max_tokens": 16384,
|
||||||
|
"mode": "chat",
|
||||||
|
"output_cost_per_token": 1.4e-5,
|
||||||
|
"output_cost_per_token_priority": 2.8e-5,
|
||||||
|
"supported_endpoints": ["/v1/chat/completions", "/v1/responses"],
|
||||||
|
"supported_modalities": ["text", "image"],
|
||||||
|
"supported_output_modalities": ["text"],
|
||||||
|
"supports_function_calling": true,
|
||||||
|
"supports_native_streaming": true,
|
||||||
|
"supports_parallel_function_calling": true,
|
||||||
|
"supports_pdf_input": true,
|
||||||
|
"supports_prompt_caching": true,
|
||||||
|
"supports_reasoning": true,
|
||||||
|
"supports_response_schema": true,
|
||||||
|
"supports_system_messages": true,
|
||||||
|
"supports_tool_choice": true,
|
||||||
|
"supports_vision": true
|
||||||
|
},
|
||||||
"gpt-5.3-codex": {
|
"gpt-5.3-codex": {
|
||||||
"cache_read_input_token_cost": 1.75e-7,
|
"cache_read_input_token_cost": 1.75e-7,
|
||||||
"cache_read_input_token_cost_priority": 3.5e-7,
|
"cache_read_input_token_cost_priority": 3.5e-7,
|
||||||
|
|||||||
@@ -14,7 +14,7 @@ from letta.schemas.providers.base import Provider
|
|||||||
logger = get_logger(__name__)
|
logger = get_logger(__name__)
|
||||||
|
|
||||||
ALLOWED_PREFIXES = {"gpt-4", "gpt-5", "o1", "o3", "o4"}
|
ALLOWED_PREFIXES = {"gpt-4", "gpt-5", "o1", "o3", "o4"}
|
||||||
DISALLOWED_KEYWORDS = {"transcribe", "search", "realtime", "tts", "audio", "computer", "o1-mini", "o1-preview", "o1-pro", "chat"}
|
DISALLOWED_KEYWORDS = {"transcribe", "search", "realtime", "tts", "audio", "computer", "o1-mini", "o1-preview", "o1-pro"}
|
||||||
DEFAULT_EMBEDDING_BATCH_SIZE = 1024
|
DEFAULT_EMBEDDING_BATCH_SIZE = 1024
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
11
tests/model_settings/openai-gpt-5.3-chat-latest.json
Normal file
11
tests/model_settings/openai-gpt-5.3-chat-latest.json
Normal file
@@ -0,0 +1,11 @@
|
|||||||
|
{
|
||||||
|
"handle": "openai/gpt-5.3-chat-latest",
|
||||||
|
"model_settings": {
|
||||||
|
"provider_type": "openai",
|
||||||
|
"max_output_tokens": 4096,
|
||||||
|
"parallel_tool_calls": false,
|
||||||
|
"reasoning": {
|
||||||
|
"reasoning_effort": "minimal"
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user