ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

remove prompt caching headers as the support has been removed

Browse Source
This commit is contained in:
Sameer Kankute 2026-01-02 11:08:35 +05:30
parent 7ba14a30ed
commit ca94990307
6 changed files with 81 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)

58
litellm/model_prices_and_context_window_backup.json
View File

@ -249,6 +249,30 @@
"/v1/images/generations"
]
},
"aiml/google/imagen-4.0-ultra-generate-001": {
"litellm_provider": "aiml",
"metadata": {
"notes": "Imagen 4.0 Ultra Generate API - Photorealistic image generation with precise text rendering"
},
"mode": "image_generation",
"output_cost_per_image": 0.063,
"source": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate",
"supported_endpoints": [
"/v1/images/generations"
]
},
"aiml/google/nano-banana-pro": {
"litellm_provider": "aiml",
"metadata": {
"notes": "Gemini 3 Pro Image (Nano Banana Pro) - Advanced text-to-image generation with reasoning and 4K resolution support"
},
"mode": "image_generation",
"output_cost_per_image": 0.1575,
"source": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview",
"supported_endpoints": [
"/v1/images/generations"
]
},
"amazon.nova-canvas-v1:0": {
"litellm_provider": "bedrock",
"max_input_tokens": 2600,
@ -3508,6 +3532,40 @@
"supports_service_tier": true,
"supports_vision": true
},
"azure/gpt-5.2-chat": {
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_priority": 3.5e-07,
"input_cost_per_token": 1.75e-06,
"input_cost_per_token_priority": 3.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 1.4e-05,
"output_cost_per_token_priority": 2.8e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/gpt-5.2-chat-2025-12-11": {
"cache_read_input_token_cost": 1.75e-07,
"cache_read_input_token_cost_priority": 3.5e-07,

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",
},
)