Update Key Fn

Update an existing API key's parameters.

The body is a merge patch: a field left out keeps its stored value, and on the key's own columns an explicit null clears it. The metadata-backed fields below are the exception, merging into the stored metadata instead: passing one as null leaves it unchanged, while metadata itself replaces the stored metadata wholesale.

Parameters:

• key: Optional[str] - The key to update. Either key or key_alias must be provided.
• key_alias: Optional[str] - User-friendly key alias. If key is omitted, also identifies the key to update (must match exactly one key, same as /key/delete's key_aliases)
• user_id: Optional[str] - User ID associated with key
• team_id: Optional[str] - Team ID associated with key
• agent_id: Optional[str] - The agent id associated with the key.
• project_id: Optional[str] - Omit to retain the project, or send null to detach. A different project ID is rejected.
• organization_id: Optional[str] - The organization id of the key.
• budget_id: Optional[str] - The budget id associated with the key. Created by calling /budget/new.
• end_user_budget_id: Optional[str] - Proxy admin only. Budget id applied to end users first seen through this key that carry no budget of their own. Omit to keep the current value, pass an empty string to clear it.
• models: Optional[list] - Model_name's a user is allowed to call
• tags: Optional[List[str]] - Tags for organizing keys (Enterprise only)
• prompts: Optional[List[str]] - List of prompts that the key is allowed to use.
• enforced_params: Optional[List[str]] - List of enforced params for the key (Enterprise only). Docs
• 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"}}
• 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.
• max_parallel_requests: Optional[int] - Rate limit for parallel requests
• metadata: Optional[dict] - Metadata for key. Example {"team": "core-infra", "app": "app2"}
• tpm_limit: Optional[int] - Tokens per minute limit
• rpm_limit: Optional[int] - Requests per minute limit
• tpd_limit: Optional[int] - Tokens per day limit, charged by batch submissions instead of tpm_limit/rpm_limit
• model_rpm_limit: Optional[dict] - Model-specific RPM limits {"gpt-4": 100, "claude-v1": 200}
• mcp_rpm_limit: Optional[dict] - Per-MCP-server RPM limits, keyed by MCP server name {"github": 100, "slack": 200}
• tag_rpm_limit: Optional[dict] - Per-request-tag RPM limits, keyed by request tag {"cell-1": 1000, "cell-2": 500}. Each tag gets an independent counter; absent tags fall back to the key-level rpm limit.
• model_tpm_limit: Optional[dict] - Model-specific TPM limits {"gpt-4": 100000, "claude-v1": 200000}
• default_estimated_output_tokens: Optional[int] - Proxy admin only. Expected output tokens reserved for TPM limiting when a request omits max_tokens. Positive integer.
• default_estimated_output_tokens_per_model: Optional[dict] - Proxy admin only. Per-model override of the above {"gpt-4": 4096, "gpt-3.5-turbo": 1024}
• tpm_limit_type: Optional[str] - TPM rate limit type - "best_effort_throughput", "guaranteed_throughput", or "dynamic"
• rpm_limit_type: Optional[str] - RPM rate limit type - "best_effort_throughput", "guaranteed_throughput", or "dynamic"
• allowed_cache_controls: Optional[list] - List of allowed cache control values
• duration: Optional[str] - Key validity duration ("30d", "1h", etc.), null to never expire, or "-1" to never expire (deprecated, use null)
• permissions: Optional[dict] - Key-specific permissions
• send_invite_email: Optional[bool] - Send invite email to user_id
• guardrails: Optional[List[str]] - List of active guardrails for the key
• policies: Optional[List[str]] - List of policy names to apply to the key. Policies define guardrails, conditions, and inheritance rules.
• disable_global_guardrails: Optional[bool] - Whether to disable global guardrails for the key. Proxy admin only.
• 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.
• prompts: Optional[List[str]] - List of prompts that the key is allowed to use.
• blocked: Optional[bool] - Whether the key is blocked
• aliases: Optional[dict] - Model aliases for the key - Docs
• config: Optional[dict] - [DEPRECATED PARAM] Key-specific config.
• temp_budget_increase: Optional[float] - Temporary budget increase for the key (Enterprise only).
• temp_budget_expiry: Optional[str] - Expiry time for the temporary budget increase (Enterprise only).
• allowed_routes: Optional[list] - List of allowed routes for the key. Store the actual route or store a wildcard pattern for a set of routes. Example - ["/chat/completions", "/embeddings", "/keys/*"]
• allowed_passthrough_routes: Optional[list] - List of allowed pass through routes for the key. Store the actual route or store a wildcard pattern for a set of routes. Example - ["/my-custom-endpoint"]. Use this instead of allowed_routes, if you just want to specify which pass through routes the key can access, without specifying the routes. If allowed_routes is specified, allowed_passthrough_routes is ignored.
• prompts: Optional[List[str]] - List of allowed prompts for the key. If specified, the key will only be able to use these specific prompts.
• object_permission: Optional[LiteLLM_ObjectPermissionBase] - key-specific object permission. Example - {"vector_stores": ["vector_store_1", "vector_store_2"], "agents": ["agent_1", "agent_2"], "agent_access_groups": ["dev_group"]}. IF null or {} then no object permission.
• auto_rotate: Optional[bool] - Whether this key should be automatically rotated
• rotation_interval: Optional[str] - How often to rotate this key (e.g., '30d', '90d'). Required if auto_rotate=True
• allowed_vector_store_indexes: Optional[List[dict]] - List of allowed vector store indexes for the key. Example - [{"index_name": "my-index", "index_permissions": ["write", "read"]}]. If specified, the key will only be able to use these specific vector store indexes. Create index, using /v1/indexes endpoint.
• router_settings: Optional[UpdateRouterConfig] - key-specific router settings. Example - {"model_group_retry_policy": {"gpt-4": {"RateLimitErrorRetries": 5}}}. IF null or {} then no router settings.
• access_group_ids: Optional[List[str]] - List of access group IDs to associate with the key. Access groups define which models a key can access. Example - ["access_group_1", "access_group_2"].
• budget_limits: Optional[list] - List of concurrent budget windows for the key. Each window specifies a budget_limit, time_period, and optional budget_duration. Example - [{"budget_limit": 10.0, "time_period": "1d"}, {"budget_limit": 50.0, "time_period": "7d"}].

Example:

curl --location 'http://0.0.0.0:4000/key/update'     --header "Authorization: Bearer $LITELLM_MASTER_KEY"     --header 'Content-Type: application/json'     --data '{
    "key": "sk-your-key",
    "key_alias": "my-key",
    "user_id": "user-1234",
    "team_id": "team-1234",
    "max_budget": 100,
    "metadata": {"any_key": "any-val"},
}'