scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

feat: Add GPT-5 model family with official OpenAI specifications (#13… (#13386)

Browse source 
* feat: Add GPT-5 model family with official OpenAI specifications (#13378)

* Add GPT-5 model family support

Added four new GPT-5 models:
- gpt-5: Flagship model for logic and multi-step tasks
- gpt-5-mini: Cost-sensitive version for budget use cases
- gpt-5-nano: Speed-optimized version for low latency
- gpt-5-chat: Enterprise-focused version for advanced conversations

* Update GPT-5 models with official OpenAI specifications

- Add gpt-5-chat-latest with 400k context, 128k output tokens
- Add gpt-5-2025-08-07 with enhanced reasoning capabilities
- Add gpt-5-mini-2025-08-07 with cost-optimized pricing
- Add gpt-5-nano-2025-08-07 with ultra-fast performance
- Update existing gpt-5, gpt-5-mini, gpt-5-nano to match dated versions
- All models now support reasoning tokens and 400k context window
- Pricing updated per official OpenAI documentation

* fix conflicts

---------

Co-authored-by: Cole McIntosh <82463175+colesmcintosh@users.noreply.github.com>
This commit is contained in:
Ishaan Jaff 2025-08-07 11:58:37 -07:00 • committed by GitHub
parent 729e1f530a
commit 087a1a622c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 514 additions and 108 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

311
litellm/model_prices_and_context_window_backup.json
View file

@ -296,60 +296,6 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"watsonx/ibm/granite-3-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -666,6 +612,263 @@
"search_context_size_high": 0.03
}
},
"gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-chat": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2e-05,
"input_cost_per_token_batches": 2.5e-06,
"output_cost_per_token_batches": 1e-05,
"cache_read_input_token_cost": 1.25e-06,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
},
"gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"codex-mini-latest": {
"max_tokens": 100000,
"max_input_tokens": 200000,

311
model_prices_and_context_window.json
View file

@ -296,60 +296,6 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"watsonx/ibm/granite-3-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -666,6 +612,263 @@
"search_context_size_high": 0.03
}
},
"gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-chat": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2e-05,
"input_cost_per_token_batches": 2.5e-06,
"output_cost_per_token_batches": 1e-05,
"cache_read_input_token_cost": 1.25e-06,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
},
"gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
"cache_read_input_token_cost": 1.25e-07,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
"cache_read_input_token_cost": 2.5e-08,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
"cache_read_input_token_cost": 5e-09,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_pdf_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true,
"supports_reasoning": true
},
"codex-mini-latest": {
"max_tokens": 100000,
"max_input_tokens": 200000,