DATOOL CLOUD
Traces, evaluations, prompts, and cost insights in one workspace. Monthly subscriptions, billed in US dollars.
A home for your AI projects.
$29.00
per organization / month
For teams building with AI every day.
$199.00
per organization / month
For teams with requirements of their own.
Let’s talk
a plan shaped around your team
Everything in Pro, with a plan built around your requirements.
Talk to us about higher record volumes, tailored trace retention, and what your team needs to grow.
Every product feature is included in Core and Pro. Choose the record volume, retention your team needs, or talk to us about Custom.
Scroll across to compare plans. Feature names stay in view.
| Features and limits | Core $29.00 / month Get Core | Pro $199.00 / month Get Pro | Custom Let’s talk |
|---|---|---|---|
| Usage and retention | |||
| Trace and span records / month | 100,000 | 1,000,000 | Custom volume |
| Trace retention | 90 days | 365 days | Tailored retention |
| Preserve saved evidence Traces kept in datasets, evaluations, or reviews. | Included | Included | Included |
| Observability | |||
| Traces Follow every step of a request. | Included | Included | Included |
| Agents Understand agent behavior across runs. | Included | Included | Included |
| Workflows See how each workflow performs. | Included | Included | Included |
| Sessions Keep related requests in context. | Included | Included | Included |
| Inputs, outputs, errors, and span timing | Included | Included | Included |
| Token usage and cost estimates | Included | Included | Included |
| Filters and saved views | Included | Included | Included |
| Build and experiment | |||
| Playground Try inputs against your connected app. | Included | Included | Included |
| Prompts Version the instructions behind your AI. | Included | Included | Included |
| Immutable prompt versions | Included | Included | Included |
| Prompt variables and previews | Included | Included | Included |
| Local and HTTP app connections | Included | Included | Included |
| Evaluation and human review | |||
| Datasets Turn real examples into repeatable tests. | Included | Included | Included |
| Scorers Define what a good answer looks like. | Included | Included | Included |
| Evaluations Compare changes on the same evidence. | Included | Included | Included |
| Reviews Bring human judgment into the loop. | Included | Included | Included |
| Human scores Give reviewers a shared set of criteria. | Included | Included | Included |
| Immutable dataset snapshots | Included | Included | Included |
| Turn traces into dataset cases | Included | Included | Included |
| JavaScript and Python scorers | Included | Included | Included |
| LLM judges and library scorers | Included | Included | Included |
| Re-score saved evidence | Included | Included | Included |
| Replay apps on frozen cases | Included | Included | Included |
| Run and case comparison | Included | Included | Included |
| CI quality gates | Included | Included | Included |
| Monitoring and analytics | |||
| Dashboards Watch quality, latency, usage, and cost. | Included | Included | Included |
| Alerts Know when a workflow needs attention. | Included | Included | Included |
| Custom charts and metric filters | Included | Included | Included |
| In-app and webhook alerts | Included | Included | Included |
| Integrations and workspace | |||
| Node.js SDK | Included | Included | Included |
| Command-line interface | Included | Included | Included |
| MCP for AI assistants | Included | Included | Included |
| OpenTelemetry and AI SDK tracing | Included | Included | Included |
| Scoped organization API keys | Included | Included | Included |
| Organizations and projects | Included | Included | Included |
AI model and sandbox compute costs are billed separately by your providers. Custom plan limits are agreed with your team.