Choosing your LLM model

The LLM model is the “brain” of your agent: it decides how questions are understood, how the knowledge base is used, and what tone the replies take. IperChat gives you access to 12 models from OpenAI and Anthropic — some are very fast and cheap, others reason deeply on complex problems. This page helps you pick the right one for your use case.

You set the model in the ops panel under “Agent configurations” (sidebar → Agents group). Open your origin and go to “Behavior” → “Model”. You can switch any time: the new model takes effect within 60 seconds on new conversations.

Comparison table

Tier 1 — Most capable (4–5 credits)

The premium models. Use them when accuracy matters more than per-message cost: regulated industries, specialist consulting, scenarios where a wrong answer is expensive.

Claude Opus 5.5

At 4 credits per reply, Opus 5.5 provides a 1M-token context window and adaptive thinking that stays on. Choose low, medium or high effort; there is no Off option or temperature control. Suitable for complex procedures and conversations involving several tools. Provider documentation.

Claude Opus 4.8

An earlier Opus generation retained for existing configurations: 200k context, adaptive thinking and 5 credits per reply. Use it when your prompts are tuned for this version.

Claude Opus 4.6

An earlier Opus generation with 200k context, configurable thinking and 5 credits per reply. Retained for existing agents and comparisons with newer versions.

GPT-5.6 Sol

An earlier OpenAI reasoning model at 5 credits per reply, retained for agents with prompts tuned to this version. GPT-6.1 Sol is the default for new tenants at 2 credits.

Tier 2 — Balanced (2–3 credits)

The sweet spot for most production agents. Solid response quality, sustainable cost even at medium-to-high volume.

GPT-6.1 Sol

OpenAI reasoning model with a 1.05M-token context window, at 2 message credits per reply. It is the default for new tenants. IperChat offers low, medium and high reasoning effort; reasoning cannot be switched off. Temperature and top-p controls are unavailable. Existing agents keep their selected model until you change it.

Best for:

• Complex procedures and technical conversations
• Long conversations that need a larger context budget

See the OpenAI model documentation for provider capabilities. The configured context and history limits determine how much conversation IperChat actually sends.

Claude Sonnet 4.6

Sonnet is Anthropic’s workhorse: 200k context, extended thinking on demand, moderate cost. An option for agents that work over large knowledge bases.

Best for:

• Large knowledge bases (100+ documents)
• Lead qualification with detailed criteria
• Multilingual agents with a polished tone
• Booking and conversational flow management

Claude Sonnet 5.5

At 2 credits per reply, Sonnet 5.5 offers a 1M-token context window. Low, medium and high effort enable adaptive thinking. Off disables up-front thinking; brief updates between tool calls can still occur. Temperature controls are unavailable. Provider documentation.

GPT-5.2

Reasoning effort enabled at 2 credits per message. Cheaper than 5.4 while keeping reasoning capability.

Best for:

• Standard conversations with light reasoning
• Medium volume on a tight budget

Tier 3 — Fast & efficient (1 credit)

For high-volume use cases: standard customer support, repetitive FAQs, traffic deflection. Quick replies at low cost.

GPT-5.6 Luna

The smallest GPT-5.6 variant: the cheapest and fastest OpenAI reasoning model. Configurable reasoning effort, no temperature setting, knowledge cutoff February 2026. The best 1-credit option if you want reasoning at maximum volume.

Best for:

• Customer support over common FAQs
• Deflection of repetitive queries at high traffic
• Maximum volume on a controlled budget, without giving up reasoning

GPT-4.1 Mini

Classic OpenAI generalist. No reasoning, but supports temperature and top_p parameters if you want fine-grained control over response creativity.

Best for:

• Setups that need custom temperature
• Agents with very specific tone (creative or strict)

GPT-4o

OpenAI’s battle-tested multimodal model. Excellent multilingual support, natural writing quality.

Best for:

• Multilingual agents with international users
• Cases where you want a “stable” model that’s been around for months
• Existing setups that already work well

GPT-4o Mini

The mini version of 4o: the cheapest model in the OpenAI pool. Maximum volume at minimum cost.

Best for:

• Demos, prototypes, test environments
• Very high traffic where budget beats perfection
• First-line agents doing triage only

How to choose

A quick guide to narrow the choice based on your use case:

• Customer support, fast FAQs, high traffic → GPT-5.6 Luna.
• Lead qualification, booking, general conversations → GPT-6.1 Sol, the default for new tenants, or Claude Sonnet 5.5.
• Complex procedures and tool-assisted conversations → Claude Opus 5.5.
• Long context → GPT-6.1 Sol, Claude Sonnet 5.5 or Claude Opus 5.5. Configure the context and history budgets for your workload.
• Demo, MVP, test traffic → GPT-4o Mini or GPT-5.6 Luna.