tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-18 08:25:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(openai): add gpt-5.4-pro to model map

Browse Source 
- Add gpt-5.4-pro and gpt-5.4-pro-2026-03-05 snapshot
- Input: $30/1M tokens, Output: $180/1M tokens
- 1.05M context window, 128K max output tokens
- Priority pricing for >272K input tokens (2x input, 1.5x output)
- Supports reasoning.effort: medium, high, xhigh
- Responses API, Chat Completions, Batch endpoints

Made-with: Cursor
This commit is contained in:
Sameer Kankute
2026-03-06 09:52:56 +05:30
parent 83e237bac2
commit 050503469a
2 changed files with 156 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+78
View File
@@ -21040,6 +21040,84 @@
"supports_vision": true,
"supports_web_search": true
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_priority": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_priority": 6e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_priority": 2.7e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/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": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_priority": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_priority": 6e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_priority": 2.7e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/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": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true
},
"gpt-5-pro": {
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,
model_prices_and_context_window.json
+78
View File
@@ -21040,6 +21040,84 @@
"supports_vision": true,
"supports_web_search": true
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_priority": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_priority": 6e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_priority": 2.7e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/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": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_priority": 6e-06,
"input_cost_per_token": 3e-05,
"input_cost_per_token_priority": 6e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_priority": 2.7e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/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": false,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_service_tier": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true
},
"gpt-5-pro": {
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,