Skip to content

Add new metrics for litellm #24955

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
steveny91 wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Add new metrics for litellm #24955

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c66bf02
add new metrics for litellm
steveny91 Aug 22, 2026
55bdd12
changelog
steveny91 Aug 22, 2026
738d5f3
add undocumented metrics
steveny91 Aug 22, 2026
51ada47
descriptions
steveny91 Aug 24, 2026
5d851e5
address feedback
steveny91 Aug 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions litellm/changelog.d/24955.added
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Add new metrics introduced up to LiteLLM version 1.95.0.
196 changes: 118 additions & 78 deletions litellm/datadog_checks/litellm/metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,85 +3,125 @@
# Licensed under a 3-clause BSD style license (see LICENSE)

METRICS = {
'litellm_api_key_budget_remaining_hours_metric': "api.key.budget.remaining_hours.metric",
'litellm_api_key_max_budget_metric': "api.key.max_budget.metric",
'litellm_auth_failed_requests': "auth.failed_requests",
'litellm_auth_latency': "auth.latency",
'litellm_auth_total_requests': "auth.total_requests",
'litellm_batch_write_to_db_failed_requests': "batch_write_to_db.failed_requests",
'litellm_batch_write_to_db_latency': "batch_write_to_db.latency",
'litellm_batch_write_to_db_total_requests': "batch_write_to_db.total_requests",
'litellm_deployment_cooled_down': "deployment.cooled_down",
'litellm_deployment_failed_fallbacks': "deployment.failed_fallbacks",
'litellm_deployment_failure_by_tag_responses': "deployment.failure_by_tag_responses",
'litellm_deployment_failure_responses': "deployment.failure_responses",
'litellm_deployment_latency_per_output_token': "deployment.latency_per_output_token",
'litellm_deployment_state': "deployment.state",
'litellm_deployment_success_responses': "deployment.success_responses",
'litellm_deployment_successful_fallbacks': "deployment.successful_fallbacks",
'litellm_deployment_total_requests': "deployment.total_requests",
'litellm_in_memory_daily_spend_update_queue_size': "in_memory.daily_spend_update_queue.size",
'litellm_in_memory_spend_update_queue_size': "in_memory.spend_update_queue.size",
'litellm_input_tokens': "input.tokens",
'litellm_input_tokens_metric': "input_tokens.metric",
'litellm_llm_api_latency_metric': "llm.api.latency.metric",
'litellm_llm_api_time_to_first_token_metric': "llm.api.time_to_first_token.metric",
'litellm_not_a_premium_user_metric': "not_a_premium_user.metric",
'litellm_output_tokens': "output.tokens",
'litellm_output_tokens_metric': "output_tokens.metric",
'litellm_overhead_latency_metric': "overhead_latency.metric",
'litellm_pod_lock_manager_size': "pod_lock_manager.size",
'litellm_postgres_failed_requests': "postgres.failed_requests",
'litellm_postgres_latency': "postgres.latency",
'litellm_postgres_total_requests': "postgres.total_requests",
'litellm_provider_remaining_budget_metric': "provider.remaining_budget.metric",
'litellm_proxy_failed_requests_metric': "proxy.failed_requests.metric",
'litellm_proxy_pre_call_failed_requests': "proxy.pre_call.failed_requests",
'litellm_proxy_pre_call_latency': "proxy.pre_call.latency",
'litellm_proxy_pre_call_total_requests': "proxy.pre_call.total_requests",
'litellm_proxy_total_requests_metric': "proxy.total_requests.metric",
'litellm_redis_daily_spend_update_queue_size': "redis.daily_spend_update_queue.size",
'litellm_redis_daily_tag_spend_update_queue_failed_requests': (
"redis.daily_tag_spend_update_queue.failed_requests"
),
'litellm_redis_daily_tag_spend_update_queue_latency': "redis.daily_tag_spend_update_queue.latency",
'litellm_redis_daily_tag_spend_update_queue_total_requests': "redis.daily_tag_spend_update_queue.total_requests",
'litellm_active_users': 'active_users',
'litellm_api_key_budget_remaining_hours_metric': 'api.key.budget.remaining_hours.metric',
'litellm_api_key_max_budget_metric': 'api.key.max_budget.metric',
'litellm_auth_failed_requests': 'auth.failed_requests',
'litellm_auth_latency': 'auth.latency',
'litellm_auth_total_requests': 'auth.total_requests',
'litellm_batch_write_to_db_failed_requests': 'batch_write_to_db.failed_requests',
'litellm_batch_write_to_db_latency': 'batch_write_to_db.latency',
'litellm_batch_write_to_db_total_requests': 'batch_write_to_db.total_requests',
'litellm_cache_hits_metric': 'cache.hits.metric',
'litellm_cache_misses_metric': 'cache.misses.metric',
'litellm_cached_tokens_metric': 'cached_tokens.metric',
'litellm_callback_logging_failures_metric': 'callback.logging_failures.metric',
'litellm_check_batch_cost_errors': 'check_batch_cost.errors',
'litellm_check_batch_cost_jobs_polled': 'check_batch_cost.jobs_polled',
'litellm_check_batch_cost_jobs_processed': 'check_batch_cost.jobs_processed',
'litellm_check_batch_cost_last_run_timestamp': 'check_batch_cost.last_run_timestamp',
'litellm_deployment_cooled_down': 'deployment.cooled_down',
'litellm_deployment_failed_fallbacks': 'deployment.failed_fallbacks',
'litellm_deployment_failure_by_tag_responses': 'deployment.failure_by_tag_responses',
'litellm_deployment_failure_responses': 'deployment.failure_responses',
'litellm_deployment_latency_per_output_token': 'deployment.latency_per_output_token',
'litellm_deployment_rpm_limit': 'deployment.rpm_limit',
'litellm_deployment_state': 'deployment.state',
'litellm_deployment_success_responses': 'deployment.success_responses',
'litellm_deployment_successful_fallbacks': 'deployment.successful_fallbacks',
'litellm_deployment_total_requests': 'deployment.total_requests',
'litellm_deployment_tpm_limit': 'deployment.tpm_limit',
'litellm_guardrail_errors': 'guardrail.errors',
'litellm_guardrail_latency_seconds': 'guardrail.latency_seconds',
'litellm_guardrail_requests': 'guardrail.requests',
'litellm_images_generated_metric': 'images_generated.metric',
'litellm_in_flight_requests': 'in_flight_requests',
'litellm_in_memory_daily_spend_update_queue_size': 'in_memory.daily_spend_update_queue.size',
'litellm_in_memory_spend_update_queue_size': 'in_memory.spend_update_queue.size',
'litellm_input_audio_tokens_metric': 'input_audio_tokens.metric',
'litellm_input_cache_creation_tokens_metric': 'input_cache_creation_tokens.metric',
'litellm_input_cached_tokens_metric': 'input_cached_tokens.metric',
Comment thread
steveny91 marked this conversation as resolved.
'litellm_input_tokens': 'input.tokens',
'litellm_input_tokens_metric': 'input_tokens.metric',
'litellm_llm_api_latency_metric': 'llm.api.latency.metric',
'litellm_llm_api_time_to_first_token_metric': 'llm.api.time_to_first_token.metric',
'litellm_managed_batch_created': 'managed.batch_created',
'litellm_managed_batch_duration_seconds': 'managed.batch_duration_seconds',
'litellm_managed_file_created': 'managed.file_created',
'litellm_managed_file_deleted': 'managed.file_deleted',
'litellm_managed_file_size_bytes': 'managed.file_size_bytes',
'litellm_mcp_tool_call_spend_metric': 'mcp.tool_call_spend.metric',
'litellm_mcp_tool_calls': 'mcp.tool_calls',
'litellm_not_a_premium_user_metric': 'not_a_premium_user.metric',
'litellm_org_budget_remaining_hours_metric': 'org.budget.remaining_hours.metric',
'litellm_org_max_budget_metric': 'org.max_budget.metric',
'litellm_output_audio_tokens_metric': 'output_audio_tokens.metric',
'litellm_output_reasoning_tokens_metric': 'output_reasoning_tokens.metric',
'litellm_output_tokens': 'output.tokens',
'litellm_output_tokens_metric': 'output_tokens.metric',
'litellm_overhead_latency_metric': 'overhead_latency.metric',
'litellm_overhead_with_guardrails_latency_metric': 'overhead_with_guardrails_latency.metric',
'litellm_pod_lock_manager_size': 'pod_lock_manager.size',
'litellm_postgres_failed_requests': 'postgres.failed_requests',
'litellm_postgres_latency': 'postgres.latency',
'litellm_postgres_total_requests': 'postgres.total_requests',
'litellm_provider_cache_creation_input_tokens_metric': 'provider_cache.creation_input_tokens.metric',
'litellm_provider_cache_read_input_tokens_metric': 'provider_cache.read_input_tokens.metric',
'litellm_provider_remaining_budget_metric': 'provider.remaining_budget.metric',
'litellm_proxy_failed_requests_metric': 'proxy.failed_requests.metric',
'litellm_proxy_pre_call_failed_requests': 'proxy.pre_call.failed_requests',
'litellm_proxy_pre_call_latency': 'proxy.pre_call.latency',
'litellm_proxy_pre_call_total_requests': 'proxy.pre_call.total_requests',
'litellm_proxy_total_requests_metric': 'proxy.total_requests.metric',
'litellm_redis_daily_agent_spend_update_queue_size': 'redis.daily_agent_spend_update_queue.size',
'litellm_redis_daily_end_user_spend_update_queue_size': 'redis.daily_end_user_spend_update_queue.size',
'litellm_redis_daily_spend_update_queue_size': 'redis.daily_spend_update_queue.size',
'litellm_redis_daily_tag_spend_update_queue_failed_requests': 'redis.daily_tag_spend_update_queue.failed_requests',
'litellm_redis_daily_tag_spend_update_queue_latency': 'redis.daily_tag_spend_update_queue.latency',
'litellm_redis_daily_tag_spend_update_queue_total_requests': 'redis.daily_tag_spend_update_queue.total_requests',
'litellm_redis_daily_team_spend_update_queue_failed_requests': (
"redis.daily_team_spend_update_queue.failed_requests"
),
'litellm_redis_daily_team_spend_update_queue_latency': "redis.daily_team_spend_update_queue.latency",
'litellm_redis_daily_team_spend_update_queue_total_requests': (
"redis.daily_team_spend_update_queue.total_requests"
'redis.daily_team_spend_update_queue.failed_requests'
),
'litellm_redis_failed_requests': "redis.failed_requests",
'litellm_redis_latency': "redis.latency",
'litellm_redis_spend_update_queue_size': "redis.spend_update_queue.size",
'litellm_redis_total_requests': "redis.total_requests",
'litellm_remaining_api_key_budget_metric': "remaining.api_key.budget.metric",
'litellm_remaining_api_key_requests_for_model': "remaining.api_key.requests_for_model",
'litellm_remaining_api_key_tokens_for_model': "remaining.api_key.tokens_for_model",
'litellm_remaining_requests': "remaining.requests",
'litellm_remaining_requests_metric': "remaining_requests.metric",
'litellm_remaining_team_budget_metric': "remaining.team_budget.metric",
'litellm_remaining_tokens': "remaining_tokens",
'litellm_remaining_tokens_metric': "remaining_tokens.metric",
'litellm_request_total_latency_metric': "request.total_latency.metric",
'litellm_reset_budget_job_failed_requests': "reset_budget_job.failed_requests",
'litellm_reset_budget_job_latency': "reset_budget_job.latency",
'litellm_reset_budget_job_total_requests': "reset_budget_job.total_requests",
'litellm_router_failed_requests': "router.failed_requests",
'litellm_router_latency': "router.latency",
'litellm_router_total_requests': "router.total_requests",
'litellm_self_failed_requests': "self.failed_requests",
'litellm_self_latency': "self.latency",
'litellm_self_total_requests': "self.total_requests",
'litellm_spend_metric': "spend.metric",
'litellm_team_budget_remaining_hours_metric': "team.budget.remaining_hours.metric",
'litellm_team_max_budget_metric': "team.max_budget.metric",
'litellm_total_tokens': "total.tokens",
'litellm_total_tokens_metric': "total.tokens",
'process_start_time_seconds': {"name": "process.uptime.seconds", "type": "time_elapsed"},
'litellm_redis_daily_team_spend_update_queue_latency': 'redis.daily_team_spend_update_queue.latency',
'litellm_redis_daily_team_spend_update_queue_total_requests': 'redis.daily_team_spend_update_queue.total_requests',
'litellm_redis_failed_requests': 'redis.failed_requests',
'litellm_redis_latency': 'redis.latency',
'litellm_redis_spend_update_queue_size': 'redis.spend_update_queue.size',
'litellm_redis_total_requests': 'redis.total_requests',
'litellm_remaining_api_key_budget_metric': 'remaining.api_key.budget.metric',
'litellm_remaining_api_key_requests_for_model': 'remaining.api_key.requests_for_model',
'litellm_remaining_api_key_tokens_for_model': 'remaining.api_key.tokens_for_model',
'litellm_remaining_org_budget_metric': 'remaining.org_budget.metric',
'litellm_remaining_requests': 'remaining.requests',
'litellm_remaining_requests_metric': 'remaining_requests.metric',
'litellm_remaining_team_budget_metric': 'remaining.team_budget.metric',
'litellm_remaining_tokens': 'remaining_tokens',
'litellm_remaining_tokens_metric': 'remaining_tokens.metric',
'litellm_remaining_user_budget_metric': 'remaining.user_budget.metric',
'litellm_request_queue_time_seconds': 'request.queue_time_seconds',
'litellm_request_total_latency_metric': 'request.total_latency.metric',
'litellm_reset_budget_job_failed_requests': 'reset_budget_job.failed_requests',
'litellm_reset_budget_job_latency': 'reset_budget_job.latency',
'litellm_reset_budget_job_total_requests': 'reset_budget_job.total_requests',
'litellm_router_failed_requests': 'router.failed_requests',
'litellm_router_latency': 'router.latency',
'litellm_router_total_requests': 'router.total_requests',
'litellm_self_failed_requests': 'self.failed_requests',
'litellm_self_latency': 'self.latency',
'litellm_self_total_requests': 'self.total_requests',
'litellm_spend_metric': 'spend.metric',
'litellm_team_budget_remaining_hours_metric': 'team.budget.remaining_hours.metric',
'litellm_team_max_budget_metric': 'team.max_budget.metric',
'litellm_team_members_metric': 'team.members.metric',
'litellm_teams_count': 'teams_count',
'litellm_total_tokens': 'total.tokens',
'litellm_total_tokens_metric': 'total.tokens',
'litellm_total_users': 'total_users',
'litellm_user_budget_remaining_hours_metric': 'user.budget.remaining_hours.metric',
'litellm_user_max_budget_metric': 'user.max_budget.metric',
'litellm_video_duration_seconds_metric': 'video_duration_seconds.metric',
'process_start_time_seconds': {'name': 'process.uptime.seconds', 'type': 'time_elapsed'},
# Deprecated
'litellm_llm_api_failed_requests_metric': "llm.api.failed_requests.metric",
'litellm_requests_metric': "requests.metric",
'litellm_llm_api_failed_requests_metric': 'llm.api.failed_requests.metric',
'litellm_requests_metric': 'requests.metric',
}
Loading
Loading