Skip to content

Opik adds reusable playground variants and tightens provider logging

Updated Opik

Summary

Four related releases combine prompt-variant controls with logging, retry and cost-accounting corrections.

Tool
Opik
Category
Agent infra
Date
Pricing
Not stated in the sources we cited.

Opik 2.2.128 through 2.2.131 are grouped here as one product update.

Reuse playground prompts

The playground can duplicate any prompt variant, add a blank variant, and load or save Text and Chat prompts. This is the main new workflow: users can preserve a baseline while preparing another prompt configuration rather than rebuilding every variant manually.

Provider handling changes

The follow-up releases keep provider header values and error bodies out of retry and error logs. They also adjust streaming header waits, transient-failure retries and handling of OpenAI error responses with additional fields.

Cost accounting changes include prompt-size tiers and one-hour cache writes. These are corrections to Opik’s accounting behavior, not new provider prices or a guarantee that a displayed estimate equals an invoice.

Other patches address optimization pagination and retained span payloads. The series is counted once because the later versions refine the same product workflow and provider integration, not because each patch is a separate launch.

See the opik hub.

More from Opik

View all

Questions

What is Opik?

According to its docs, Opik is an open-source platform that helps you understand what your LLM application is doing, measure how well it works, and improve it.

Is Opik open source?

Yes. The docs say Opik is open source, and the GitHub API reports the repository license as Apache-2.0.

Does Opik have an MCP server?

The docs say you can install the Opik MCP server to drive your workspace from tools such as Claude Code, Cursor, VS Code Copilot, Codex or opencode.

Filed on Agent Radar. Claims in this note are limited to the sources above.