scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Merge pull request #18579 from BerriAI/litellm_remove_prompt_chaching_header

Browse source 
Remove prompt caching headers as the support has been removed
This commit is contained in:
Sameer Kankute 2026-01-02 21:01:50 +05:30 • committed by GitHub
commit c8bb92afdc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 23 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/my-website/docs/providers/anthropic.md
View file

@ -444,7 +444,7 @@ Here's what a sample Raw Request from LiteLLM for Anthropic Context Caching look
POST Request Sent from LiteLLM:
curl -X POST \
https://api.anthropic.com/v1/messages \
-H 'accept: application/json' -H 'anthropic-version: 2023-06-01' -H 'content-type: application/json' -H 'x-api-key: sk-...' -H 'anthropic-beta: prompt-caching-2024-07-31' \
-H 'accept: application/json' -H 'anthropic-version: 2023-06-01' -H 'content-type: application/json' -H 'x-api-key: sk-...' \
-d '{'model': 'claude-3-5-sonnet-20240620', [
{
"role": "user",
@ -472,6 +472,8 @@ https://api.anthropic.com/v1/messages \
"max_tokens": 10
}'
```
**Note:** Anthropic no longer requires the `anthropic-beta: prompt-caching-2024-07-31` header. Prompt caching now works automatically when you use `cache_control` in your messages.
:::
### Caching - Large Context Caching

9
litellm/llms/anthropic/chat/transformation.py
View file

@ -54,7 +54,10 @@ from litellm.types.utils import (
CompletionTokensDetailsWrapper,
)
from litellm.types.utils import Message as LitellmMessage
from litellm.types.utils import PromptTokensDetailsWrapper, ServerToolUse
from litellm.types.utils import (
PromptTokensDetailsWrapper,
ServerToolUse,
)
from litellm.utils import (
ModelResponse,
Usage,
@ -204,9 +207,11 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
) # Relevant issue: https://github.com/BerriAI/litellm/issues/7755
def get_cache_control_headers(self) -> dict:
# Anthropic no longer requires the prompt-caching beta header
# Prompt caching now works automatically when cache_control is used in messages
# Reference: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
return {
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
}
def _map_tool_choice(

16
litellm/llms/anthropic/common_utils.py
View file

@ -12,7 +12,11 @@ from litellm.litellm_core_utils.prompt_templates.common_utils import (
)
from litellm.llms.base_llm.base_utils import BaseLLMModelInfo, BaseTokenCounter
from litellm.llms.base_llm.chat.transformation import BaseLLMException
from litellm.types.llms.anthropic import AllAnthropicToolsValues, AnthropicMcpServerTool, ANTHROPIC_HOSTED_TOOLS
from litellm.types.llms.anthropic import (
ANTHROPIC_HOSTED_TOOLS,
AllAnthropicToolsValues,
AnthropicMcpServerTool,
)
from litellm.types.llms.openai import AllMessageValues
from litellm.types.utils import TokenCountResponse
@ -273,8 +277,9 @@ class AnthropicModelInfo(BaseLLMModelInfo):
beta_header = self.get_computer_tool_beta_header(computer_tool_used)
betas.append(beta_header)
if prompt_caching_set:
betas.append("prompt-caching-2024-07-31")
# Anthropic no longer requires the prompt-caching beta header
# Prompt caching now works automatically when cache_control is used in messages
# Reference: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
if file_id_used:
betas.append("files-api-2025-04-14")
@ -305,8 +310,9 @@ class AnthropicModelInfo(BaseLLMModelInfo):
container_with_skills_used: bool = False,
) -> dict:
betas = set()
if prompt_caching_set:
betas.add("prompt-caching-2024-07-31")
# Anthropic no longer requires the prompt-caching beta header
# Prompt caching now works automatically when cache_control is used in messages
# Reference: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
if computer_tool_used:
beta_header = self.get_computer_tool_beta_header(computer_tool_used)
betas.add(beta_header)

8
tests/local_testing/test_anthropic_prompt_caching.py
View file

@ -104,7 +104,6 @@ async def test_litellm_anthropic_prompt_caching_tools():
],
extra_headers={
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
},
)
@ -112,11 +111,12 @@ async def test_litellm_anthropic_prompt_caching_tools():
print("call args=", mock_post.call_args)
expected_url = "https://api.anthropic.com/v1/messages"
# Note: anthropic-beta header for prompt-caching is no longer required
# Anthropic now supports prompt caching automatically when cache_control is used
expected_headers = {
"accept": "application/json",
"content-type": "application/json",
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
"x-api-key": "mock_api_key",
}
@ -285,7 +285,6 @@ async def test_anthropic_api_prompt_caching_basic():
max_tokens=10,
extra_headers={
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
},
)
@ -356,7 +355,6 @@ async def test_anthropic_api_prompt_caching_basic_with_cache_creation():
max_tokens=10,
extra_headers={
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
},
)
@ -645,7 +643,6 @@ async def test_litellm_anthropic_prompt_caching_system():
],
extra_headers={
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
},
)
@ -657,7 +654,6 @@ async def test_litellm_anthropic_prompt_caching_system():
"accept": "application/json",
"content-type": "application/json",
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
"x-api-key": "mock_api_key",
}

1
tests/old_proxy_tests/tests/test_anthropic_context_caching.py
View file

@ -30,7 +30,6 @@ response = client.chat.completions.create(
],
extra_headers={
"anthropic-version": "2023-06-01",
"anthropic-beta": "prompt-caching-2024-07-31",
},
)