Sebastian Krüger
d26310afb7
Added supports_prompt_caching: true to all Claude models: - claude-sonnet-4 - claude-sonnet-4.5 - claude-3-5-sonnet - claude-3-opus - claude-3-haiku This enables Anthropic's prompt caching feature across all models, significantly reducing latency and costs for repeated requests with the same system prompts. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
70 lines
2.0 KiB
YAML
70 lines
2.0 KiB
YAML
model_list:
|
|
- model_name: claude-sonnet-4
|
|
litellm_params:
|
|
model: anthropic/claude-sonnet-4-20250514
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
drop_params: true
|
|
supports_prompt_caching: true
|
|
|
|
- model_name: claude-sonnet-4.5
|
|
litellm_params:
|
|
model: anthropic/claude-sonnet-4-5-20250929
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
drop_params: true
|
|
supports_prompt_caching: true
|
|
|
|
- model_name: claude-3-5-sonnet
|
|
litellm_params:
|
|
model: anthropic/claude-3-5-sonnet-20241022
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
drop_params: true
|
|
supports_prompt_caching: true
|
|
|
|
- model_name: claude-3-opus
|
|
litellm_params:
|
|
model: anthropic/claude-3-opus-20240229
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
drop_params: true
|
|
supports_prompt_caching: true
|
|
|
|
- model_name: claude-3-haiku
|
|
litellm_params:
|
|
model: anthropic/claude-3-haiku-20240307
|
|
api_key: os.environ/ANTHROPIC_API_KEY
|
|
drop_params: true
|
|
supports_prompt_caching: true
|
|
|
|
litellm_settings:
|
|
drop_params: true
|
|
set_verbose: false # Disable verbose logging for better performance
|
|
# Enable caching with Redis for better performance
|
|
cache: true
|
|
cache_params:
|
|
type: redis
|
|
host: redis
|
|
port: 6379
|
|
ttl: 3600 # Cache for 1 hour
|
|
# Force strip specific parameters globally
|
|
allowed_fails: 0
|
|
# Modify params before sending to provider
|
|
modify_params: true
|
|
# Enable success and failure logging but minimize overhead
|
|
success_callback: [] # Disable all success callbacks to reduce DB writes
|
|
failure_callback: [] # Disable all failure callbacks
|
|
|
|
router_settings:
|
|
allowed_fails: 0
|
|
|
|
# Drop unsupported parameters
|
|
default_litellm_params:
|
|
drop_params: true
|
|
|
|
general_settings:
|
|
disable_responses_id_security: true
|
|
# Disable spend tracking to reduce database overhead
|
|
disable_spend_logs: true
|
|
# Disable tag tracking
|
|
disable_tag_tracking: true
|
|
# Disable daily spend updates
|
|
disable_daily_spend_logs: true
|