From e3119cef38622dffb5d99135217f2bf302983d60 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Mon, 5 Aug 2024 09:27:22 -0700 Subject: [PATCH] add sample spec to model cost map --- .../model_prices_and_context_window_backup.json | 14 +++++++++++++- model_prices_and_context_window.json | 14 +++++++++++++- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c6e99f80546..0ef9f33ea2c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1,4 +1,16 @@ { + "sample_spec": { + "max_tokens": "set to max_output_tokens if provider specifies it. IF not set to max_tokens provider specifies", + "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", + "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", + "input_cost_per_token": 0.0000, + "output_cost_per_token": 0.000, + "litellm_provider": "one of https://docs.litellm.ai/docs/providers", + "mode": "one of chat, embedding, completion, image_generation, audio_transcription", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true + }, "gpt-4": { "max_tokens": 4096, "max_input_tokens": 8192, @@ -24,7 +36,7 @@ "gpt-4o-mini": { "max_tokens": 4096, "max_input_tokens": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "input_cost_per_token": 0.00000015, "output_cost_per_token": 0.00000060, "litellm_provider": "openai", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index c6e99f80546..0ef9f33ea2c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1,4 +1,16 @@ { + "sample_spec": { + "max_tokens": "set to max_output_tokens if provider specifies it. IF not set to max_tokens provider specifies", + "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", + "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", + "input_cost_per_token": 0.0000, + "output_cost_per_token": 0.000, + "litellm_provider": "one of https://docs.litellm.ai/docs/providers", + "mode": "one of chat, embedding, completion, image_generation, audio_transcription", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true + }, "gpt-4": { "max_tokens": 4096, "max_input_tokens": 8192, @@ -24,7 +36,7 @@ "gpt-4o-mini": { "max_tokens": 4096, "max_input_tokens": 128000, - "max_output_tokens": 4096, + "max_output_tokens": 16384, "input_cost_per_token": 0.00000015, "output_cost_per_token": 0.00000060, "litellm_provider": "openai",