QuestionPunkQuestionPunk
Start free

Choosing a model

How to pick the right AI model for your study.

QuestionPunk offers models from multiple AI providers including Anthropic Claude, OpenAI GPT, Google Gemini, and more. This guide explains how to choose the right model for your study.

aimodels5-15 minutesIntermediateResearchersProduct teams

Steps

  1. Understand the options
    QuestionPunk supports 163 models from 16 providers. New text AI interviews default to OpenAI GPT-5.4 Mini, while new voice interviews default to Claude Sonnet 5. Existing surveys keep their saved model.
    Anthropic Claude: Claude Haiku 4.5 (fast and economical), Sonnet 4.6 through Sonnet 5.5 (balanced speed and depth), Opus 4.6 through Opus 5.5 (richest follow-ups for deep qualitative work), and Fable 5 and 5.1.
    OpenAI: GPT-6 Astra/Sol/Luna (latest generation), GPT-5.6 Luna/Sol/Terra, GPT-5.5/Pro, GPT-5.4/Pro/Mini/Nano, plus GPT-5.3 Codex, 5.2, 5.1, and 5 series models, GPT-4.1 family, GPT-4o, o3, o3 Mini, o3 Pro, o4 Mini, gpt-oss open-weight models, and specialized Codex and Chat variants.
    Google: Gemini 3.8, 3.7 and 3.6 Flash, Gemini 3.5 Flash/Lite, Gemini 3.1 Pro/Flash Preview, Gemini 2.5 Flash/Pro, plus Gemma 4 and Gemma 3 open models.
    Meta: Llama 4 Maverick, Llama 4 Scout, Llama 3.3, and 3.2 models.
    Mistral: Medium 3.5, Large 3, Medium 3.1, Small 4, Nemo, Ministral 3, Devstral, Codestral, and Saba models.
    DeepSeek: V4.1 Flash, V4 Pro/Flash, V3.2, V3.1, R1 series.
    xAI: Grok 4.7, 4.6 and 4.5.
    Amazon: Nova Pro, Lite, and Micro.
    Moonshot: Kimi K3 and Kimi K2 Thinking.
    Cohere: Command A.
    Qwen, Nvidia, StepFun, Arcee, Upstage, Zhipu, and others are also available, including free-tier and zero-cost options.
  2. Select in survey settings
    Choose the model in the AI interviewer settings for each interview question. You can set different models for different interview questions within the same survey. Voice interviews choose from a separate list of 13 conversation models from Anthropic, Google, and OpenAI.
  3. Pilot and compare
    Run a short A/B pilot with different model settings to compare output quality before sending to your full sample.

QuestionPunk supports 163 models from 16 providers: Anthropic, OpenAI, Google (Gemini), Meta (Llama), Mistral, DeepSeek, xAI (Grok), Amazon (Nova), Moonshot (Kimi), Cohere, Qwen, Nvidia, StepFun, Arcee, Upstage, and Zhipu. The full list is available on Pro. New text AI interviews default to OpenAI GPT-5.4 Mini, while new voice interviews default to Claude Sonnet 5. Existing surveys keep their saved model.

For most studies, Claude Haiku 4.5 or Sonnet 4.6 provides the best balance of quality and speed. Opus 4.6 through Opus 5.5 deliver the richest, most nuanced follow-ups for complex qualitative research. A few reasoning models, such as Kimi K2 Thinking and Qwen3 Max Thinking, are also available.

Free-plan users have access to Claude Haiku 4.5, OpenAI GPT-5.4 Mini, and Google Gemma 4 31B. Haiku and GPT-5.4 Mini consume AI credits at low rates, while Gemma 4 31B uses no credits. On Pro, many other open-weight models, including Llama 4, Mistral Small, and Nvidia Nemotron, are available at very low cost.

Run a short pilot with 5-10 respondents using different model settings to compare output quality before committing to your full sample.