LLM Playground

Test and iterate on your prompts directly in the Langfuse Prompt Playground. Tweak the prompt and model parameters to see how different models respond to these input changes. This allows you to quickly iterate on your prompts and optimize them for the best results in your LLM app without having to switch between tools or use any code.

Core features

Side-by-Side Comparison View

Compare multiple prompt variants alongside each other. Execute them all at once or focus on a single variant. Each variant keeps its own LLM settings, variables, tool definitions, and placeholders so you can immediately see the impact of every change.

Playground with one window. Click “New split window” to copy it, open the copy's “Variables” and change language from typescript to go, then click “Run All” to run both windows at once and compare their outputs. Close the copy with “Remove window”.

Open your prompt in the playground

You can open a prompt you created with Langfuse Prompt Management in the playground.

Prompts > movie-critic, version 3. Click “Playground” > “Fresh playground”, fill the variables criticlevel (expert) and movie (Dune: Part Two) in the Variables panel and click “Submit” to get the model's answer in Output.

Save your prompt to Prompt Management

When you're satisfied with your prompt, you can save it to Prompt Management by clicking the save button.

Playground with a chat prompt. Click “Save as prompt” in the window header > “Save as new prompt”. The new-prompt form opens with the playground's messages; enter the name movie-critic-chat, keep “Set the production label” checked and click “Create prompt”. It lands on version 1 with the production and latest labels.

Open a generation in the playground

You can open a generation from Langfuse Observability in the playground: select the generation in a trace, then choose Add to → Playground → Fresh playground. The playground opens with the generation's messages and model settings.

Trace detail with a qa-answer generation selected. Click “Add to” in the observation header > “Playground” > “Fresh playground”; the playground opens with the generation's system and user messages and model settings. Click “Submit” to rerun it.

Tool calling and structured outputs

The Langfuse Playground supports tool calling and structured output schemas, enabling you to define, test, and validate LLM executions that rely on tool calls and enforce specific response formats.

Tool Calling

• Define custom tools with JSON schema definitions
• Test prompts relying on tools in real-time by mocking tool responses
• Save tool definitions to your project

Structured Output

• Enforce response formats using JSON schemas
• Save schemas to your project
• Jump into the playground from your OpenAI generation using structured output

Add prompt variables

You can add prompt variables in the playground to simulate different inputs to your prompt.

Use your favorite model

You can use your favorite model by adding the API key for the model you want to use in the Langfuse project settings. Learn how to set up an LLM connection.

Optionally, many LLM providers allow for additional parameters when invoking a model. You can pass these parameters in the playground when toggling "Additional Options" in the model selection dropdown. Read this documentation about additional provider options for more information.

Related Resources

• For structured regression testing of prompt and model variants on datasets, use Experiments.

GitHub Discussions

---

---