Skip to main content
POST
/
v1
/
evals
/
runs
/
estimates
Estimate Eval Run
curl --request POST \
  --url https://api.bland.ai/v1/evals/runs/estimates \
  --header 'Content-Type: application/json' \
  --header 'authorization: <authorization>' \
  --data '
{
  "call_ids": {},
  "attached_agents": {},
  "workbench_setup_version_id": "<string>"
}
'
{
  "data": {
    "resolved_atom_count": 150,
    "estimated_input_tokens": 420000,
    "estimated_output_tokens": 15000,
    "estimated_cost_usd_cents": 87.5
  },
  "errors": null
}

Documentation Index

Fetch the complete documentation index at: https://docs.bland.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Headers

​
authorization
string
required
Your API key for authentication.

​
Body Parameters

Accepts the same body as Create Eval Run. Key fields:
​
call_ids
array of string
required
The call IDs to include in the estimate. Between 1 and 5000 calls.
​
attached_agents
array of objects
The eval agents to score with. Required when workbench_setup_version_id is not provided.
​
workbench_setup_version_id
string
Pinned workbench setup version whose agent roster supplies the agents. Required when attached_agents is not provided. Must be provided together with workbench_setup_id.

​
Response

​
resolved_atom_count
integer
Number of call-by-agent evaluations the run will perform.
​
estimated_input_tokens
integer
Estimated number of input tokens consumed by judge calls.
​
estimated_output_tokens
integer
Estimated number of output tokens produced by judge calls.
​
estimated_cost_usd_cents
number
Estimated billable cost in USD cents.
{
  "data": {
    "resolved_atom_count": 150,
    "estimated_input_tokens": 420000,
    "estimated_output_tokens": 15000,
    "estimated_cost_usd_cents": 87.5
  },
  "errors": null
}