Properties
| Name | Type | Description |
|---|---|---|
| task_selection | object | Task coverage fixed at launch; null for legacy or diagnostic runs. |
| agent_id | object | Persisted owner; null for unassigned legacy runs. |
| eval_run_id | string | Unique evaluation run identifier. |
| bench_id | string | Benchmark evaluated by this run. |
| rollout_xid | object | XID containing this run's evaluation trajectories. |
| display_name | object | User-facing name for the evaluation run; null for legacy rows. |
| base_model_slug | object | Base model evaluated by this run. |
| options | object | |
| status | object | Current evaluation lifecycle status; null for legacy rows. |
| deployment_id | object | Hosted deployment snapshotted at launch. |
| parent_checkpoint_id | object | Checkpoint evaluated by this run, when applicable. |
| training_run_id | object | Training run that produced the evaluated checkpoint. |
| step | object | Evaluated checkpoint training step. |
| reward_mean | object | Completed mean of effective evaluation rewards; cut-off trajectories can contribute zero without a logged grader reward. |
| total_rollouts | object | Rollout total fixed at launch; null for legacy or diagnostic runs. |
| created_at | string | Time when the evaluation run was created. |
| updated_at | string | Time when the evaluation run was last updated. |
| completed_at | object | Time when the evaluation reached a terminal status. |
| failure | object | Structured failure when status is failed. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/api-evangelist/trajectory/main/json-schema/trajectory-eval-run-schema.json",
"title": "EvalRun",
"x-generated": "2026-10-24",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/trajectory-openapi.json#/components/schemas/EvalRun",
"properties": {
"task_selection": {
"anyOf": [
{
"$ref": "#/$defs/EvalTaskSelection"
},
{
"type": "null"
}
],
"description": "Task coverage fixed at launch; null for legacy or diagnostic runs."
},
"agent_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Agent Id",
"description": "Persisted owner; null for unassigned legacy runs."
},
"eval_run_id": {
"type": "string",
"title": "Eval Run Id",
"description": "Unique evaluation run identifier."
},
"bench_id": {
"type": "string",
"title": "Bench Id",
"description": "Benchmark evaluated by this run."
},
"rollout_xid": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Rollout Xid",
"description": "XID containing this run's evaluation trajectories."
},
"display_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Display Name",
"description": "User-facing name for the evaluation run; null for legacy rows."
},
"base_model_slug": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Base Model Slug",
"description": "Base model evaluated by this run."
},
"options": {
"$ref": "#/$defs/RecordedRunOptions"
},
"status": {
"anyOf": [
{
"$ref": "#/$defs/EvalRunLifecycleStatus"
},
{
"type": "null"
}
],
"description": "Current evaluation lifecycle status; null for legacy rows."
},
"deployment_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Deployment Id",
"description": "Hosted deployment snapshotted at launch."
},
"parent_checkpoint_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Parent Checkpoint Id",
"description": "Checkpoint evaluated by this run, when applicable."
},
"training_run_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Training Run Id",
"description": "Training run that produced the evaluated checkpoint."
},
"step": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Step",
"description": "Evaluated checkpoint training step."
},
"reward_mean": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Reward Mean",
"description": "Completed mean of effective evaluation rewards; cut-off trajectories can contribute zero without a logged grader reward."
},
"total_rollouts": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Total Rollouts",
"description": "Rollout total fixed at launch; null for legacy or diagnostic runs."
},
"created_at": {
"type": "string",
"format": "date-time",
"title": "Created At",
"description": "Time when the evaluation run was created."
},
"updated_at": {
"type": "string",
"format": "date-time",
"title": "Updated At",
"description": "Time when the evaluation run was last updated."
},
"completed_at": {
"anyOf": [
{
"type": "string",
"format": "date-time"
},
{
"type": "null"
}
],
"title": "Completed At",
"description": "Time when the evaluation reached a terminal status."
},
"failure": {
"anyOf": [
{
"$ref": "#/$defs/AsyncFailure"
},
{
"type": "null"
}
],
"description": "Structured failure when status is failed."
}
},
"type": "object",
"required": [
"agent_id",
"eval_run_id",
"bench_id",
"display_name",
"options",
"status",
"created_at",
"updated_at"
],
"$defs": {
"AsyncFailure": {
"properties": {
"type": {
"type": "string",
"title": "Type",
"description": "Stable category used for exception mapping."
},
"code": {
"type": "string",
"title": "Code",
"description": "Stable programmatic reason for the asynchronous failure."
},
"message": {
"type": "string",
"title": "Message",
"description": "Human-readable explanation for this failure occurrence."
},
"context": {
"additionalProperties": true,
"type": "object",
"title": "Context",
"description": "Machine-readable values specific to this failure code."
}
},
"type": "object",
"required": [
"type",
"code",
"message"
],
"title": "AsyncFailure"
},
"EvalRunLifecycleStatus": {
"type": "string",
"enum": [
"pending",
"registered",
"running",
"completed",
"failed",
"cancelled"
],
"title": "EvalRunLifecycleStatus"
},
"EvalTaskSelection": {
"properties": {
"split": {
"$ref": "#/$defs/EvalTaskSplit"
},
"available_task_count": {
"type": "integer",
"minimum": 0.0,
"title": "Available Task Count",
"description": "Tasks in the selected scope at launch."
},
"selected_task_count": {
"type": "integer",
"minimum": 0.0,
"title": "Selected Task Count",
"description": "Distinct tasks selected for execution."
},
"max_samples": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Samples",
"description": "Explicit options.evaluation_max_samples, or null to run every task in the selected scope."
}
},
"type": "object",
"required": [
"split",
"available_task_count",
"selected_task_count"
],
"title": "EvalTaskSelection"
},
"EvalTaskSplit": {
"type": "string",
"enum": [
"test",
"all"
],
"title": "EvalTaskSplit"
},
"RecordedRunOptions": {
"properties": {
"intelligent_density_training": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Intelligent Density Training"
},
"algorithm": {
"anyOf": [
{
"$ref": "#/$defs/TrainingAlgorithm"
},
{
"type": "null"
}
]
},
"train_on_truncation": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Train On Truncation"
},
"train_on_error": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Train On Error"
},
"train_on_timeout": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Train On Timeout"
},
"evaluation_enabled": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Evaluation Enabled"
},
"evaluation_frequency": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Evaluation Frequency"
},
"evaluation_max_samples": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Evaluation Max Samples"
},
"evaluation_samples_per_task": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Evaluation Samples Per Task"
},
"evaluation_max_active_rollouts": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Evaluation Max Active Rollouts"
},
"evaluation_collection_timeout_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Evaluation Collection Timeout Seconds"
},
"learning_rate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Learning Rate"
},
"lr_warmup_steps": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Lr Warmup Steps"
},
"lr_hold_steps": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Lr Hold Steps"
},
"min_lr_ratio": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Min Lr Ratio"
},
"reasoning_effort": {
"anyOf": [
{
"type": "string",
"enum": [
"off",
"on",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
},
{
"type": "null"
}
],
"title": "Reasoning Effort"
},
"temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Temperature"
},
"top_p": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Top P"
},
"top_k": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Top K"
},
"evaluation_reasoning_effort": {
"anyOf": [
{
"type": "string",
"enum": [
"off",
"on",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
},
{
"type": "null"
}
],
"title": "Evaluation Reasoning Effort"
},
"evaluation_temperature": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Evaluation Temperature"
},
"evaluation_top_p": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Evaluation Top P"
},
"evaluation_top_k": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Evaluation Top K"
},
"num_steps": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Num Steps"
},
"train_batch_size": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Train Batch Size"
},
"group_size": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Group Size"
},
"samples_per_instance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Samples Per Instance"
},
"min_samples_per_group": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Min Samples Per Group"
},
"max_active_rollouts": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Active Rollouts"
},
"max_steps_off_policy": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Steps Off Policy"
},
"execution_timeout_seconds": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Execution Timeout Seconds"
},
"batch_collection_idle_timeout_seconds": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Batch Collection Idle Timeout Seconds"
},
"max_output_tokens_per_step": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Output Tokens Per Step"
},
"max_total_tokens_per_trajectory": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Total Tokens Per Trajectory"
},
"max_turns_per_trajectory": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Turns Per Trajectory"
}
},
"additionalProperties": false,
"type": "object",
"title": "RecordedRunOptions",
"description": "Recorded settings retain values outside the public launch limits."
},
"TrainingAlgorithm": {
"type": "string",
"enum": [
"gspo",
"grpo",
"reinforce_plus_plus"
],
"title": "TrainingAlgorithm"
}
}
}Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/trajectory-eval-run"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.