mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-17 09:34:48 +00:00
docs(proxy): name pattern and access group keys in model_max_budget docstrings
This commit is contained in:
parent
a39d95c64e
commit
21b0cf1fcb
5 changed files with 21 additions and 19 deletions
|
|
@ -499,7 +499,7 @@ async def new_user(
|
|||
- permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
|
||||
- metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
- max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
|
||||
- model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
- model_max_budget: Optional[dict] - Model-specific max budget for user, keyed by model name, `*` pattern, or model access group. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
- budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
- model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
- mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}. Enforced for keys and teams only; values set on a user are stored but not enforced per user.
|
||||
|
|
@ -1702,7 +1702,7 @@ async def user_update(
|
|||
- permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
|
||||
- metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
- max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
|
||||
- model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
- model_max_budget: Optional[dict] - Model-specific max budget for user, keyed by model name, `*` pattern, or model access group. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
- budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
- model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
- mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}. Enforced for keys and teams only; values set on a user are stored but not enforced per user.
|
||||
|
|
|
|||
|
|
@ -2328,7 +2328,7 @@ async def generate_key_fn(
|
|||
- throttle_on_budget_exceeded: Optional[bool] - When the key exceeds its max_budget, throttle its tpm/rpm to the global budget_exceeded_throttle_percentage instead of blocking the key entirely.
|
||||
- enable_prompt_caching: Optional[bool] - Auto-inject prompt caching breakpoints (Anthropic cache_control markers) on requests made with this key. Supported Claude models on Anthropic, Bedrock, Vertex AI, and Azure AI only.
|
||||
- permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false}
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
- budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
- model_rpm_limit: Optional[dict] - key-specific model rpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific rpm limit.
|
||||
- model_tpm_limit: Optional[dict] - key-specific model tpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific tpm limit.
|
||||
|
|
@ -2538,7 +2538,7 @@ async def generate_service_account_key_fn(
|
|||
- metadata: Optional[dict] - Metadata for key, store information for key. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
- guardrails: Optional[List[str]] - List of active guardrails for the key
|
||||
- permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false}
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
- budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
- model_rpm_limit: Optional[dict] - key-specific model rpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific rpm limit.
|
||||
- model_tpm_limit: Optional[dict] - key-specific model tpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific tpm limit.
|
||||
|
|
@ -3855,7 +3855,7 @@ async def update_key_fn(
|
|||
- enforced_params: Optional[List[str]] - List of enforced params for the key (Enterprise only). [Docs](https://docs.litellm.ai/docs/proxy/enterprise#enforce-required-params-for-llm-requests)
|
||||
- spend: Optional[float] - Amount spent by key
|
||||
- max_budget: Optional[float] - Max budget for key
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
- budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
- budget_duration: Optional[str] - Budget reset period ("30d", "1h", etc.)
|
||||
- soft_budget: Optional[float] - Soft budget limit (warning vs. hard stop). Will trigger a slack alert when this soft budget is reached. Set to null to remove the soft budget.
|
||||
|
|
@ -6303,7 +6303,7 @@ async def regenerate_key_fn(
|
|||
- tags: Optional[List[str]] - Tags for organizing keys (Enterprise only)
|
||||
- spend: Optional[float] - Amount spent by key
|
||||
- max_budget: Optional[float] - Max budget for key
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
- model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
- budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
- budget_duration: Optional[str] - Budget reset period ("30d", "1h", etc.)
|
||||
- soft_budget: Optional[float] - Soft budget limit (warning vs. hard stop). Will trigger a slack alert when this soft budget is reached.
|
||||
|
|
|
|||
|
|
@ -1642,7 +1642,7 @@ async def new_team(
|
|||
- prompts: Optional[List[str]] - List of prompts that the team is allowed to use.
|
||||
- organization_id: Optional[str] - The organization id of the team. Default is None. Create via `/organization/new`.
|
||||
- model_aliases: Optional[dict] - Model aliases for the team. [Docs](https://docs.litellm.ai/docs/proxy/team_based_routing#create-team-with-model-alias)
|
||||
- model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
- model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model, keyed by model name, `*` pattern, or model access group. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
- guardrails: Optional[List[str]] - Guardrails for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails)
|
||||
- policies: Optional[List[str]] - Policies for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails/guardrail_policies)
|
||||
- disable_global_guardrails: Optional[bool] - Whether to disable global guardrails for the team. Proxy admin only.
|
||||
|
|
@ -2420,7 +2420,7 @@ async def update_team(
|
|||
- tags: Optional[List[str]] - Tags for [tracking spend](https://litellm.vercel.app/docs/proxy/enterprise#tracking-spend-for-custom-tags) and/or doing [tag-based routing](https://litellm.vercel.app/docs/proxy/tag_routing).
|
||||
- organization_id: Optional[str] - The organization id of the team. Default is None. Create via `/organization/new`.
|
||||
- model_aliases: Optional[dict] - Model aliases for the team. [Docs](https://docs.litellm.ai/docs/proxy/team_based_routing#create-team-with-model-alias)
|
||||
- model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
- model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model, keyed by model name, `*` pattern, or model access group. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
- guardrails: Optional[List[str]] - Guardrails for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails)
|
||||
- policies: Optional[List[str]] - Policies for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails/guardrail_policies)
|
||||
- disable_global_guardrails: Optional[bool] - Whether to disable global guardrails for the team. Proxy admin only.
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
import litellm.proxy
|
||||
import litellm.proxy.proxy_server
|
||||
|
||||
from typing import Dict, Final, List, Optional
|
||||
from typing import Dict, Final, List, Mapping, Optional
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
|
@ -1367,7 +1367,9 @@ async def test_check_user_model_budget(user_id, user_model_max_budget, expected_
|
|||
calls = []
|
||||
|
||||
class _Limiter:
|
||||
async def is_user_within_model_budget(self, user_id, user_model_max_budget, model, team_id=None):
|
||||
async def is_user_within_model_budget(
|
||||
self, user_id: str, user_model_max_budget: Mapping[str, object], model: str, team_id: str | None = None
|
||||
) -> bool:
|
||||
calls.append((user_id, user_model_max_budget, model))
|
||||
return True
|
||||
|
||||
|
|
|
|||
18
ui/litellm-dashboard/src/lib/http/schema.d.ts
generated
vendored
18
ui/litellm-dashboard/src/lib/http/schema.d.ts
generated
vendored
|
|
@ -8475,7 +8475,7 @@ export interface paths {
|
|||
* - throttle_on_budget_exceeded: Optional[bool] - When the key exceeds its max_budget, throttle its tpm/rpm to the global budget_exceeded_throttle_percentage instead of blocking the key entirely.
|
||||
* - enable_prompt_caching: Optional[bool] - Auto-inject prompt caching breakpoints (Anthropic cache_control markers) on requests made with this key. Supported Claude models on Anthropic, Bedrock, Vertex AI, and Azure AI only.
|
||||
* - permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false}
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
* - model_rpm_limit: Optional[dict] - key-specific model rpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific rpm limit.
|
||||
* - model_tpm_limit: Optional[dict] - key-specific model tpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific tpm limit.
|
||||
|
|
@ -8721,7 +8721,7 @@ export interface paths {
|
|||
* - tags: Optional[List[str]] - Tags for organizing keys (Enterprise only)
|
||||
* - spend: Optional[float] - Amount spent by key
|
||||
* - max_budget: Optional[float] - Max budget for key
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
* - budget_duration: Optional[str] - Budget reset period ("30d", "1h", etc.)
|
||||
* - soft_budget: Optional[float] - Soft budget limit (warning vs. hard stop). Will trigger a slack alert when this soft budget is reached.
|
||||
|
|
@ -8798,7 +8798,7 @@ export interface paths {
|
|||
* - metadata: Optional[dict] - Metadata for key, store information for key. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
* - guardrails: Optional[List[str]] - List of active guardrails for the key
|
||||
* - permissions: Optional[dict] - key-specific permissions. Currently just used for turning off pii masking (if connected). Example - {"pii": false}
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}}. IF null or {} then no model specific budget.
|
||||
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
* - model_rpm_limit: Optional[dict] - key-specific model rpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific rpm limit.
|
||||
* - model_tpm_limit: Optional[dict] - key-specific model tpm limit. Example - {"text-davinci-002": 1000, "gpt-3.5-turbo": 1000}. IF null or {} then no model specific tpm limit.
|
||||
|
|
@ -8931,7 +8931,7 @@ export interface paths {
|
|||
* - enforced_params: Optional[List[str]] - List of enforced params for the key (Enterprise only). [Docs](https://docs.litellm.ai/docs/proxy/enterprise#enforce-required-params-for-llm-requests)
|
||||
* - spend: Optional[float] - Amount spent by key
|
||||
* - max_budget: Optional[float] - Max budget for key
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
* - budget_duration: Optional[str] - Budget reset period ("30d", "1h", etc.)
|
||||
* - soft_budget: Optional[float] - Soft budget limit (warning vs. hard stop). Will trigger a slack alert when this soft budget is reached. Set to null to remove the soft budget.
|
||||
|
|
@ -9020,7 +9020,7 @@ export interface paths {
|
|||
* - tags: Optional[List[str]] - Tags for organizing keys (Enterprise only)
|
||||
* - spend: Optional[float] - Amount spent by key
|
||||
* - max_budget: Optional[float] - Max budget for key
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
* - model_max_budget: Optional[Dict[str, BudgetConfig]] - Model-specific budgets keyed by model name, `*` pattern like "claude-opus*", or model access group, e.g. {"gpt-4": {"budget_limit": 0.0005, "time_period": "30d"}}
|
||||
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
* - budget_duration: Optional[str] - Budget reset period ("30d", "1h", etc.)
|
||||
* - soft_budget: Optional[float] - Soft budget limit (warning vs. hard stop). Will trigger a slack alert when this soft budget is reached.
|
||||
|
|
@ -17098,7 +17098,7 @@ export interface paths {
|
|||
* - prompts: Optional[List[str]] - List of prompts that the team is allowed to use.
|
||||
* - organization_id: Optional[str] - The organization id of the team. Default is None. Create via `/organization/new`.
|
||||
* - model_aliases: Optional[dict] - Model aliases for the team. [Docs](https://docs.litellm.ai/docs/proxy/team_based_routing#create-team-with-model-alias)
|
||||
* - model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
* - model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model, keyed by model name, `*` pattern, or model access group. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
* - guardrails: Optional[List[str]] - Guardrails for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails)
|
||||
* - policies: Optional[List[str]] - Policies for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails/guardrail_policies)
|
||||
* - disable_global_guardrails: Optional[bool] - Whether to disable global guardrails for the team. Proxy admin only.
|
||||
|
|
@ -17328,7 +17328,7 @@ export interface paths {
|
|||
* - tags: Optional[List[str]] - Tags for [tracking spend](https://litellm.vercel.app/docs/proxy/enterprise#tracking-spend-for-custom-tags) and/or doing [tag-based routing](https://litellm.vercel.app/docs/proxy/tag_routing).
|
||||
* - organization_id: Optional[str] - The organization id of the team. Default is None. Create via `/organization/new`.
|
||||
* - model_aliases: Optional[dict] - Model aliases for the team. [Docs](https://docs.litellm.ai/docs/proxy/team_based_routing#create-team-with-model-alias)
|
||||
* - model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
* - model_max_budget: Optional[dict] - Per-model max budget every key on the team inherits unless the key sets its own for that model, keyed by model name, `*` pattern, or model access group. Example: {"gpt-4o": {"max_budget": 10, "budget_duration": "1d"}}
|
||||
* - guardrails: Optional[List[str]] - Guardrails for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails)
|
||||
* - policies: Optional[List[str]] - Policies for the team. [Docs](https://docs.litellm.ai/docs/proxy/guardrails/guardrail_policies)
|
||||
* - disable_global_guardrails: Optional[bool] - Whether to disable global guardrails for the team. Proxy admin only.
|
||||
|
|
@ -18778,7 +18778,7 @@ export interface paths {
|
|||
* - permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
|
||||
* - metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
* - max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
|
||||
* - model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
* - model_max_budget: Optional[dict] - Model-specific max budget for user, keyed by model name, `*` pattern, or model access group. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
* - model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
* - mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}. Enforced for keys and teams only; values set on a user are stored but not enforced per user.
|
||||
|
|
@ -18917,7 +18917,7 @@ export interface paths {
|
|||
* - permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
|
||||
* - metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
* - max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
|
||||
* - model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
* - model_max_budget: Optional[dict] - Model-specific max budget for user, keyed by model name, `*` pattern, or model access group. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
* - budget_fallbacks: Optional[Dict[str, List[str]]] - Per-model fallback chain tried in order when that model's own `model_max_budget` is exceeded, e.g. {"gpt-4o": ["gpt-4o-mini"]}.
|
||||
* - model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
* - mcp_rpm_limit: Optional[dict] - Per-MCP-server rpm limit, keyed by MCP server name {"github": 100, "slack": 200}. Enforced for keys and teams only; values set on a user are stored but not enforced per user.
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue