Playground

Browse supported base models and your fine-tuned model artifacts. Interactive completions are disabled while hosted inference is not enabled.

Note: The tt CLI does not yet include playground commands. Use the dashboard Playground or the REST endpoints documented below.

Overview

The Playground is available at Dashboard → Playground and via two REST endpoints. It lists the fine-tunable base models configured in Tuned Tensor plus any fine-tuned model you have created through a run.

Key capabilities:

Single & compare mode — select one model or two side by side
System prompt — optionally prepend a system message
Temperature & max tokens — adjustable per request (0–2 temperature, 64–4 096 tokens)
Model inventory — base models and fine-tuned artifacts are listed from the same account-scoped API

Available Base Models

These models are available for hosted fine-tuning.

Model	Context Length
`Qwen/Qwen3.5-2B`	131,072
`Qwen/Qwen3.5-4B`	262,144
`google/gemma-4-E2B-it`	128,000
`google/gemma-4-E4B-it`	128,000
`meta-llama/Llama-3.2-3B-Instruct`	128,000
`microsoft/Phi-4-mini-instruct`	128,000
`ibm-granite/granite-3.3-2b-instruct`	128,000
`bigcode/starcoder2-3b`	16,384

Fine-tuned models you create through runs also appear in the model selector with their provider_model_id.

List Playground Models

GET /api/v1/playground/models

curl https://tunedtensor.com/api/v1/playground/models \
  -H "Authorization: Bearer tt_your_api_key"

Response:

{
  "data": {
    "base_models": [
      {
        "id": "Qwen/Qwen3.5-2B",
        "name": "Qwen3.5-2B",
        "type": "base"
      }
    ],
    "fine_tuned_models": [
      {
        "id": "user/Qwen3.5-2B-ft-abc123",
        "name": "Qwen3.5-2B-ft-abc123",
        "type": "fine-tuned",
        "base_model": "Qwen/Qwen3.5-2B"
      }
    ]
  }
}

Field	Description
`base_models`	Supported base models
`fine_tuned_models`	Your fine-tuned models (includes `base_model` for reference)

Run a Completion

POST /api/v1/playground/completions returns 501 playground_unavailable when hosted inference is not enabled.

curl -X POST https://tunedtensor.com/api/v1/playground/completions \
  -H "Authorization: Bearer tt_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3.5-2B",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Explain LoRA fine-tuning in one paragraph." }
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

Request Body

Parameter	Type	Default	Description
`model`	string	—	Model ID (base or fine-tuned). Required.
`messages`	{role, content}[]	—	Chat messages. At least one required. Roles: `system`, `user`, `assistant`.
`temperature`	number	0.7	Sampling temperature (0–2).
`max_tokens`	integer	1024	Maximum tokens to generate (1–4 096).

Current Response

{
  "error": {
    "code": "playground_unavailable",
    "message": "Playground inference is unavailable for hosted fine-tuned models."
  }
}

Inference Response Fields

When interactive inference is enabled, successful responses use this shape:

Field	Description
`content`	Generated text from the model when inference is enabled
`latency_ms`	Wall-clock inference time in milliseconds
`usage.prompt_tokens`	Tokens consumed by the input prompt
`usage.completion_tokens`	Tokens generated in the response

Error Codes

Status	Code	Meaning
400	`validation_error`	Invalid request body (missing model, empty messages, etc.)
501	`playground_unavailable`	Interactive inference is not enabled for hosted fine-tuned models

Comparing Base vs Fine-Tuned

When interactive inference is enabled, a common workflow is to compare a base model against your fine-tuned version to verify that fine-tuning improved behaviour:

Open the Playground and enable Compare mode
Select the base model (e.g. Qwen/Qwen3.5-2B) in Model A
Select your fine-tuned model in Model B
Enter a system prompt and user message from your behaviour spec
Click Run — if inference is enabled, both models run in parallel and responses appear side by side with latency and token metrics

Via the API, when inference is enabled, make two separate POST /api/v1/playground/completions calls with the same messages but different model values.