tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-14 00:23:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Correct GPT-5 token limits and price (#13423)

Browse Source
This commit is contained in:
Emerson Gomes
2025-08-08 08:55:33 -07:00
committed by GitHub
parent aefa71a300
commit aea5af2165
1 changed files with 31 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model_prices_and_context_window.json
+31 -32
View File
@@ -614,7 +614,7 @@
},
"gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
@@ -646,7 +646,7 @@
},
"gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
@@ -678,7 +678,7 @@
},
"gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
@@ -709,14 +709,12 @@
"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,
"max_tokens": 128000,
"max_input_tokens": 272000,
"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": [
@@ -739,11 +737,12 @@
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
"supports_native_streaming": true,
"supports_reasoning": true
},
"gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
@@ -775,7 +774,7 @@
},
"gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 2720000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
@@ -807,7 +806,7 @@
},
"gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
@@ -839,7 +838,7 @@
},
"gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
@@ -2266,7 +2265,7 @@
},
"azure/gpt-5": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
@@ -2298,7 +2297,7 @@
},
"azure/gpt-5-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,
@@ -2330,7 +2329,7 @@
},
"azure/gpt-5-mini": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
@@ -2362,7 +2361,7 @@
},
"azure/gpt-5-mini-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.5e-07,
"output_cost_per_token": 2e-06,
@@ -2394,7 +2393,7 @@
},
"azure/gpt-5-nano-2025-08-07": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
@@ -2426,7 +2425,7 @@
},
"azure/gpt-5-nano": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 4e-07,
@@ -2457,14 +2456,12 @@
"supports_reasoning": true
},
"azure/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,
"max_tokens": 128000,
"max_input_tokens": 128000,
"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": "azure",
"mode": "chat",
"supported_endpoints": [
@@ -2487,11 +2484,13 @@
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_native_streaming": true
"supports_native_streaming": true,
"supports_reasoning": true,
"source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/"
},
"azure/gpt-5-chat-latest": {
"max_tokens": 128000,
"max_input_tokens": 400000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 1.25e-06,
"output_cost_per_token": 1e-05,