Skip to main content
Glama

get_token_analytics

Read-onlyIdempotent

Retrieve time-series token analytics with summary and per-bucket counts of total, prompt, and completion tokens for consumption trend analysis.

Instructions

Get token-usage time-series data with summary.total_tokens, summary.prompt_tokens, summary.completion_tokens, and per-bucket total/prompt/completion counts. Use this for consumption trends; use get_cost_analytics when you need spend instead of token volume. Enterprise-gated. Returns 403 on non-Enterprise Portkey plans.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
time_of_generation_minYesStart time for the analytics period (ISO8601 format, e.g., '2024-01-01T00:00:00Z')
time_of_generation_maxYesEnd time for the analytics period (ISO8601 format, e.g., '2024-02-01T00:00:00Z')
total_units_minNoMinimum number of total tokens to filter by
total_units_maxNoMaximum number of total tokens to filter by
cost_minNoMinimum cost in cents to filter by
cost_maxNoMaximum cost in cents to filter by
prompt_token_minNoMinimum number of prompt tokens
prompt_token_maxNoMaximum number of prompt tokens
completion_token_minNoMinimum number of completion tokens
completion_token_maxNoMaximum number of completion tokens
status_codeNoLegacy Portkey query param for HTTP status codes. Comma-separated string; prefer status_codes for structured inputs.
weighted_feedback_minNoMinimum weighted feedback score (-10 to 10)
weighted_feedback_maxNoMaximum weighted feedback score (-10 to 10)
virtual_keysNoLegacy Portkey query param for virtual key slugs. Comma-separated string; prefer virtual_key_slugs for structured inputs.
configsNoLegacy Portkey query param for config slugs. Comma-separated string; prefer config_slugs for structured inputs.
status_codesNoStructured alias for status_code. Use an array of HTTP status codes; normalized to the legacy comma-separated Portkey query param.
virtual_key_slugsNoStructured alias for virtual_keys. Use an array of virtual key slugs; normalized to the legacy comma-separated Portkey query param.
config_slugsNoStructured alias for configs. Use an array of config slugs; normalized to the legacy comma-separated Portkey query param.
workspace_slugNoFilter by specific workspace
api_key_idsYesLegacy Portkey query param for API key UUIDs. Comma-separated string; request_analytics also accepts an array and normalizes it to this form.
metadataNoLegacy Portkey query param for metadata filtering. Stringified JSON object, e.g. '{"env":"prod","app":"myapp"}'; prefer metadata_filter for structured inputs.
ai_org_modelNoLegacy Portkey query param for provider/model pairs. Format: 'provider__model' with double underscore, e.g. 'openai__gpt-4' or 'anthropic__claude-3-opus'. Comma-separated string; prefer provider_models for structured inputs.
provider_modelsNoStructured alias for ai_org_model. Use provider__model strings in an array; normalized to the legacy comma-separated Portkey query param.
trace_idNoLegacy Portkey query param for trace IDs. Comma-separated string; prefer trace_ids for structured inputs.
trace_idsNoStructured alias for trace_id. Use an array of trace IDs; normalized to the legacy comma-separated Portkey query param.
span_idNoLegacy Portkey query param for span IDs. Comma-separated string; prefer span_ids for structured inputs.
span_idsNoStructured alias for span_id. Use an array of span IDs; normalized to the legacy comma-separated Portkey query param.
metadata_filterNoStructured alias for metadata. Use an object such as { env: 'prod' }; normalized to a JSON string before the request is sent.
prompt_slugNoFilter by prompt slug

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether the tool call succeeded and returned structured data
dataNoStructured success payload when ok is true
errorNoStructured error payload when ok is false

Implementation Reference

  • The MCP tool handler for 'get_token_analytics' that registers the tool with server.tool(). It calls service.analytics.getTokenAnalytics(), maps data points to total/prompt/completion, and formats the response with summary.total_tokens, prompt_tokens, and completion_tokens.
    server.tool(
    	"get_token_analytics",
    	"Get token-usage time-series data with summary.total_tokens, summary.prompt_tokens, summary.completion_tokens, and per-bucket total/prompt/completion counts. Use this for consumption trends; use get_cost_analytics when you need spend instead of token volume.",
    	baseAnalyticsSchema,
    	async (params) => {
    		const analytics = await service.analytics.getTokenAnalytics(
    			normalizeAnalyticsParams(params as Record<string, unknown>),
    		);
    		const dataPoints = analytics.data_points.map((point) => ({
    			timestamp: point.timestamp,
    			total: point.total,
    			prompt: point.prompt,
    			completion: point.completion,
    		}));
    		return {
    			content: [
    				{
    					type: "text",
    					text: JSON.stringify(
    						formatGraphAnalytics(
    							{
    								total_tokens: analytics.summary.total,
    								prompt_tokens: analytics.summary.prompt,
    								completion_tokens: analytics.summary.completion,
    							},
    							dataPoints,
    						),
    						null,
    						2,
    					),
    				},
    			],
    		};
    	},
    );
  • Input schema (baseAnalyticsSchema) used by get_token_analytics. Defines all filter parameters including time range, token counts, cost, status codes, virtual keys, configs, metadata, provider models, trace IDs, span IDs, and more.
    const baseAnalyticsSchema = {
    	time_of_generation_min: z
    		.string()
    		.describe(
    			"Start time for the analytics period (ISO8601 format, e.g., '2024-01-01T00:00:00Z')",
    		),
    	time_of_generation_max: z
    		.string()
    		.describe(
    			"End time for the analytics period (ISO8601 format, e.g., '2024-02-01T00:00:00Z')",
    		),
    	total_units_min: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Minimum number of total tokens to filter by"),
    	total_units_max: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Maximum number of total tokens to filter by"),
    	cost_min: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Minimum cost in cents to filter by"),
    	cost_max: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Maximum cost in cents to filter by"),
    	prompt_token_min: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Minimum number of prompt tokens"),
    	prompt_token_max: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Maximum number of prompt tokens"),
    	completion_token_min: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Minimum number of completion tokens"),
    	completion_token_max: z.coerce
    		.number()
    		.positive()
    		.optional()
    		.describe("Maximum number of completion tokens"),
    	status_code: z
    		.string()
    		.optional()
    		.describe(
    			"Legacy Portkey query param for HTTP status codes. Comma-separated string; prefer status_codes for structured inputs.",
    		),
    	weighted_feedback_min: z.coerce
    		.number()
    		.min(-10)
    		.max(10)
    		.optional()
    		.describe("Minimum weighted feedback score (-10 to 10)"),
    	weighted_feedback_max: z.coerce
    		.number()
    		.min(-10)
    		.max(10)
    		.optional()
    		.describe("Maximum weighted feedback score (-10 to 10)"),
    	virtual_keys: z
    		.string()
    		.optional()
    		.describe(
    			"Legacy Portkey query param for virtual key slugs. Comma-separated string; prefer virtual_key_slugs for structured inputs.",
    		),
    	configs: z
    		.string()
    		.optional()
    		.describe(
    			"Legacy Portkey query param for config slugs. Comma-separated string; prefer config_slugs for structured inputs.",
    		),
    	status_codes: z
    		.array(z.string())
    		.optional()
    		.describe(
    			"Structured alias for status_code. Use an array of HTTP status codes; normalized to the legacy comma-separated Portkey query param.",
    		),
    	virtual_key_slugs: z
    		.array(z.string())
    		.optional()
    		.describe(
    			"Structured alias for virtual_keys. Use an array of virtual key slugs; normalized to the legacy comma-separated Portkey query param.",
    		),
    	config_slugs: z
    		.array(z.string())
    		.optional()
    		.describe(
    			"Structured alias for configs. Use an array of config slugs; normalized to the legacy comma-separated Portkey query param.",
    		),
    	workspace_slug: z
    		.string()
    		.optional()
    		.describe("Filter by specific workspace"),
    	api_key_ids: z
    		.preprocess((value) => {
    			if (value == null) {
    				return value;
    			}
    			if (Array.isArray(value)) {
    				return value.map((item) => String(item)).join(",");
    			}
    			return value;
    		}, z.string().optional())
    		.describe(
    			"Legacy Portkey query param for API key UUIDs. Comma-separated string; request_analytics also accepts an array and normalizes it to this form.",
    		),
    	metadata: z
    		.string()
    		.optional()
    		.describe(
    			'Legacy Portkey query param for metadata filtering. Stringified JSON object, e.g. \'{"env":"prod","app":"myapp"}\'; prefer metadata_filter for structured inputs.',
    		),
    	ai_org_model: z
    		.string()
    		.optional()
    		.describe(
    			"Legacy Portkey query param for provider/model pairs. Format: 'provider__model' with double underscore, e.g. 'openai__gpt-4' or 'anthropic__claude-3-opus'. Comma-separated string; prefer provider_models for structured inputs.",
    		),
    	provider_models: z
    		.array(z.string())
    		.optional()
    		.describe(
    			"Structured alias for ai_org_model. Use provider__model strings in an array; normalized to the legacy comma-separated Portkey query param.",
    		),
    	trace_id: z
    		.string()
    		.optional()
    		.describe(
    			"Legacy Portkey query param for trace IDs. Comma-separated string; prefer trace_ids for structured inputs.",
    		),
    	trace_ids: z
    		.array(z.string())
    		.optional()
    		.describe(
    			"Structured alias for trace_id. Use an array of trace IDs; normalized to the legacy comma-separated Portkey query param.",
    		),
    	span_id: z
    		.string()
    		.optional()
    		.describe(
    			"Legacy Portkey query param for span IDs. Comma-separated string; prefer span_ids for structured inputs.",
    		),
    	span_ids: z
    		.array(z.string())
    		.optional()
    		.describe(
    			"Structured alias for span_id. Use an array of span IDs; normalized to the legacy comma-separated Portkey query param.",
    		),
    	metadata_filter: z
    		.record(z.string(), z.unknown())
    		.optional()
    		.describe(
    			"Structured alias for metadata. Use an object such as { env: 'prod' }; normalized to a JSON string before the request is sent.",
    		),
    	prompt_slug: z.string().optional().describe("Filter by prompt slug"),
    };
  • Registration: 'get_token_analytics' is listed in the ENTERPRISE_GATED_TOOL_NAMES set in src/tools/index.ts, marking it as an enterprise-gated tool.
    const ENTERPRISE_GATED_TOOL_NAMES = new Set([
    	"get_cost_analytics",
    	"get_request_analytics",
    	"get_token_analytics",
    	"get_latency_analytics",
    	"get_error_analytics",
    	"get_error_rate_analytics",
    	"get_cache_hit_latency",
    	"get_cache_hit_rate",
    	"get_users_analytics",
    	"get_error_stacks_analytics",
    	"get_error_status_codes_analytics",
    	"get_user_requests_analytics",
    	"get_rescued_requests_analytics",
    	"get_feedback_analytics",
    	"get_feedback_models_analytics",
    	"get_feedback_scores_analytics",
    	"get_feedback_weighted_analytics",
    	"get_analytics_group_users",
    	"get_analytics_group_models",
    	"get_analytics_group_metadata",
  • Service-layer helper: getTokenAnalytics() in AnalyticsService makes a GET request to '/analytics/graphs/tokens' with built analytics params.
    async getTokenAnalytics(
    	params: BaseAnalyticsParams,
    ): Promise<TokenAnalyticsResponse> {
    	return this.get<TokenAnalyticsResponse>(
    		"/analytics/graphs/tokens",
    		this.buildAnalyticsParams(params),
    	);
    }
  • Type definitions: TokenDataPoint (timestamp, total, prompt, completion), TokenSummary (total, prompt, completion), and TokenAnalyticsResponse interface.
    export interface TokenDataPoint {
    	timestamp: string;
    	total: number;
    	prompt: number;
    	completion: number;
    }
    
    export interface TokenSummary {
    	total: number;
    	prompt: number;
    	completion: number;
    }
    
    export interface TokenAnalyticsResponse {
    	object: "analytics-graph";
    	data_points: TokenDataPoint[];
    	summary: TokenSummary;
    }
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. Description adds the enterprise-gating constraint and 403 response, which is useful context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences: output summary, usage guidance, and access restriction. No superfluous information, well front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (29 params, many legacy/structured pairs) and presence of an output schema, the description is fairly complete. It could mention pagination or default aggregation, but the enterprise gating and sibling differentiation make it solid.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for each parameter. The description does not add parameter-level detail but summarizes the output structure, which indirectly helps parameter understanding. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns 'token-usage time-series data' and lists specific fields (summary.total_tokens, etc.). It distinguishes from the sibling get_cost_analytics by specifying this is for token volume vs spend.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance: 'Use this for consumption trends; use get_cost_analytics when you need spend instead of token volume.' Also warns about enterprise gating and 403 error.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/s-b-e-n-s-o-n/portkey-admin-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server