scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-26 01:12:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 99

fix(oci/catalog): real prices for Llama 4, drop zero-cost OCI OpenAI entries

Browse source 
Zero-cost catalog entries (input_cost_per_token=0, output_cost_per_token=0)
make proxy spend tracking silently report $0 for these paid OCI models, so
any caller can drive them without decrementing a budget.

For Llama 4 Maverick and Scout, OCI charges the same character-based rate
as Llama 3.3 70B ($0.0018 per 10,000 characters), so use the same per-token
price as the existing oci/meta.llama-3.3-70b-instruct entry (7.2e-07 in/out).

For oci/openai.gpt-5, gpt-5-mini, gpt-5-nano, gpt-oss-120b, and gpt-oss-20b,
no public per-token pricing is available; drop the entries so operators must
register them with explicit custom pricing. The existing GPT-5 reasoning test
fixture already injects synthetic entries when the catalog omits them, so the
chat transformation's supports_reasoning lookup keeps working in tests.
This commit is contained in:
mateo-berri 2026-05-21 06:09:39 +00:00 • committed by Claude
parent e3ee32e1d9
commit 09c0537000
No known key found for this signature in database
2 changed files with 6 additions and 116 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
litellm/model_prices_and_context_window_backup.json
View file

@ -26336,48 +26336,6 @@
"supports_response_schema": true,
"supports_vision": true
},
"oci/openai.gpt-5": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/openai.gpt-5-mini": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/openai.gpt-5-nano": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/cohere.embed-english-v3.0": {
"input_cost_per_token": 1e-07,
"litellm_provider": "oci",

80
model_prices_and_context_window.json
View file

@ -26067,28 +26067,28 @@
"supports_native_streaming": true
},
"oci/meta.llama-4-maverick-17b-128e-instruct-fp8": {
"input_cost_per_token": 0.0,
"input_cost_per_token": 7.2e-07,
"litellm_provider": "oci",
"max_input_tokens": 1048576,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"output_cost_per_token": 7.2e-07,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true,
"supports_vision": true
},
"oci/meta.llama-4-scout-17b-16e-instruct": {
"input_cost_per_token": 0.0,
"input_cost_per_token": 7.2e-07,
"litellm_provider": "oci",
"max_input_tokens": 10485760,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"output_cost_per_token": 7.2e-07,
"source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
@ -26239,74 +26239,6 @@
"supports_vision": true,
"supports_native_streaming": true
},
"oci/openai.gpt-5": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/openai.gpt-5-mini": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/openai.gpt-5-nano": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/openai.gpt-oss-120b": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/openai.gpt-oss-20b": {
"input_cost_per_token": 0.0,
"litellm_provider": "oci",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 0.0,
"source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/",
"supports_function_calling": true,
"supports_response_schema": false,
"supports_native_streaming": true
},
"oci/cohere.command-a-vision": {
"input_cost_per_token": 1.56e-06,
"litellm_provider": "oci",