---
title: "Estimate evaluation context requirements without launching"
method: POST
path: "/api/eval-runs/context-check/"
tags: ["eval-runs"]
---

# Estimate evaluation context requirements without launching

`POST /api/eval-runs/context-check/`

## Request

- Base URL: `https://api.overmindlab.ai`
- URL: `https://api.overmindlab.ai/api/eval-runs/context-check/`
- Auth: one of:
  - HTTP bearer
  - API key in header `X-Api-Key`
  - API key in cookie `sessionid`
  - API key in header `X-Api-Key`
  - HTTP bearer

## Request body

- EvaluationContextRequestRequest
  - `project` string, uuid, required
  - `dataset` string, uuid, required
  - `cell` string, uuid, nullable
  - `eval_set` string, uuid, nullable
  - `judge_model` union: Explanation judge for this run. Blank uses the configured default. * `` - * `gpt-5.6-luna` - gpt-5.6-luna * `gpt-5.6-terra` - gpt-5.6-terra * `claude-sonnet-5` - claude-sonnet-5 * `claude-haiku-4-5` - claude-haiku-4-5 * `gemini-3.1-pro-preview` - gemini-3.1-pro-preview * `gemini-3.8-flash` - gemini-3.8-flash * `deepseek-v3.2` - deepseek-v3.2
    - 'gpt-5.6-luna' | 'gpt-5.6-terra' | 'claude-sonnet-5' | 'claude-haiku-4-5' | 'gemini-3.1-pro-preview' | 'gemini-3.8-flash' | 'deepseek-v3.2': * `` - * `gpt-5.6-luna` - gpt-5.6-luna * `gpt-5.6-terra` - gpt-5.6-terra * `claude-sonnet-5` - claude-sonnet-5 * `claude-haiku-4-5` - claude-haiku-4-5 * `gemini-3.1-pro-preview` - gemini-3.1-pro-preview * `gemini-3.8-flash` - gemini-3.8-flash * `deepseek-v3.2` - deepseek-v3.2
    - ''
  - `targets` EvalRunTargetRequest[]
    - `label` string
    - `mode` 'recorded' | 'generate': * `recorded` - recorded * `generate` - generate
    - `model_name` string
    - `model_ref` string, uuid, nullable
    - `params` object
    - `is_baseline` boolean
    - `output_tokens` integer

## Response `200`

- EvaluationContextReport
  - `checks` EvaluationContextCheck[], required
    - `role` string, required
    - `label` string, required
    - `model` string, required
    - `context_window` integer, nullable, required
    - `max_output_tokens` integer, nullable, required
    - `estimated_input_tokens` integer, required
    - `total_input_tokens` integer
    - `configured_model` string
    - `reserved_output_tokens` integer, required
    - `required_context` integer, required
    - `checked_rows` integer, required
    - `affected_rows` integer, required
    - `row_indices` integer[], required
    - `estimated` boolean, required
    - `status` string, required
    - `message` string, required
    - `estimated_cost_usd` number, double, nullable
    - `cost_basis` string
    - `suggestions` EvaluationContextSuggestion[]
      - `model` string, required
      - `name` string, required
      - `context_window` integer, required
      - `max_output_tokens` integer, required
      - `reserved_output_tokens` integer, required
      - `estimated_cost_usd` number, double, nullable, required
      - `cost_delta_usd` number, double, nullable, required
    - `suggestion_note` string
  - `judge_models` EvaluationJudgeOption[], required
    - `model` string, required
    - `name` string, required
    - `context_window` integer, nullable, required
    - `max_output_tokens` integer, nullable, required
    - `reserved_output_tokens` integer, required
    - `estimated_cost_usd` number, double, nullable, required
    - `cost_delta_usd` number, double, nullable, required
    - `status` string, required

---

[API](https://skmtc.dev/overmindlab/apis/overmind-api.md) - [All operations](https://skmtc.dev/overmindlab/apis/overmind-api/llms.txt) - [OpenAPI document](https://skmtc.dev/overmindlab/apis/overmind-api/revisions/0ecfd39e80c6?raw)