Skip to main content
GET
Get task usage by ID

Authorizations

Authorization
string
header
required

JWT authentication token

Path Parameters

task_id
string
required

The unique task identifier

Response

Task usage data

agent_triggers
integer
required

Total agent triggers

created_at
string<date-time>
required

When the task was created

model
string
required

LLM model used

status
enum<string>
required

Execution status

Available options:
completed,
error,
failed,
aborted,
blocked
step_count
integer
required

Number of steps executed

task_id
string
required

Task ID

tool_calls
integer
required

Total tool calls made

usage_source
enum<string>
required

Billing/model source used by the task. AI connections never consume Neo credits.

Available options:
neo,
byok,
ai_connections
agent_breakdown
object | null

Agent trigger counts by agent name

email
string

Email of the user who created the task (only visible to team admins)

error_message
string | null

Error message if status is error

input_tokens
integer

Input tokens reported by the upstream provider. Omitted when unavailable.

is_byok
boolean
deprecated

Deprecated compatibility field. True only when usage_source is byok.

leaf_tool_sum_ms
integer | null

Sum of leaf tool execution time, excluding trigger_* (nested subagent) wait.

llm_active_wall_ms
integer | null

Wall-clock union of overlapping LLM call intervals. Never exceeds total_execution_ms.

llm_cost
number<float>

Provider LLM cost in USD. Present for direct BYOK tasks; omitted for platform-billed tasks and AI connection tasks. Connected subscription providers do not currently report their per-request charge. Preserves up to six decimal places when present.

llm_latency_sum_ms
integer | null

Sum of pure per-step provider round-trip latencies, excluding tool execution. Additive: overlapping/nested calls do not cancel out, so this can exceed total_execution_ms.

neo_cost
number<float>

Neo platform cost in USD for direct BYOK usage, llm_cost multiplied by the account's neo_cost_rate. Omitted for platform-billed and AI connection tasks. Preserves up to six decimal places when present.

neo_credits
number<float>

Neo credits charged for platform-billed usage. Present only when usage_source is neo; omitted for BYOK and AI connection tasks. Task and stream usage preserves up to six decimal places so sub-cent usage remains visible.

output_tokens
integer

Output tokens reported by the upstream provider. Omitted when unavailable.

provider_latency_avg_ms
integer | null

Average pure provider latency per LLM step.

provider_latency_p50_ms
integer | null

Median (p50) pure provider latency across this task's LLM steps.

provider_latency_p95_ms
integer | null

p95 pure provider latency across this task's LLM steps.

reasoning_tokens
integer

Reasoning tokens reported by the upstream provider. Omitted when unavailable.

stream_count
integer

Number of streams aggregated (1 if single stream)

stream_id
string<uuid>

Stream ID (only present for individual streams, omitted for grouped tasks)

task_title
string | null

Task title when available

tool_active_wall_ms
integer | null

Wall-clock union of overlapping leaf-tool call intervals.

tool_breakdown
object | null

Tool call breakdown with calls and duration

tool_call_history
object[] | null

Detailed tool call history

total_execution_ms
integer | null

Total execution time (wall clock) in milliseconds

total_tokens
integer

Total reported input and output tokens. Omitted when unavailable.

trigger_wait_sum_ms
integer | null

Sum of time spent waiting on trigger_* (nested subagent) calls. Nests around, not adjacent to, leaf_tool_sum_ms — do not add the two together to derive a wall-time total.