GPT-4 family

The GPT-4 generation: no reasoning phase, so replies start immediately, which suits a phone call.

Reached through the LiveKit Inference gateway.

temperature and maxTokens are set on the model catalogue entry rather than in a provider body; everything else here is sent to the gateway exactly as written, so these use the upstream spelling. The two generations differ in what they honour, and the GPT-5 models ignore several settings rather than refusing them. There is no list of permitted settings on this route, so a name that is not a chat-completions parameter at all is not caught by OnCore: it fails inside the client LiveKit calls the provider with, before any request goes out, and automatic failover answers that turn instead, so the reply comes from a different model than the one you selected. A value the provider refuses ends the same way, and that is what the If invalid column means on this page. Every language model on this platform runs behind automatic failover, so a refused setting never reaches the caller as an error: another model answers that turn on its own settings, and the reply reads perfectly normally. Measured on 2026-09-03, an in-range frequency_penalty that Gemini refuses outright came back as an ordinary answer written by the failover model, with nothing in it to say so. Send only the settings listed here.

Settings#

Every setting is optional. Leave one out and OnCore sends nothing for it, so the Default applies. If invalid is what the provider does with a value it does not accept.

Overriding on a single call#

Return this from your assistant-request webhook to apply these settings to one call. This is the only route that carries them. A model in your catalogue stores the model id, temperature and maxTokens, and nothing else, so every other setting on this page is sent per call or not at all.

{
  "data": {
    "overrides": {
      "model": {
        "settings": {
          "temperature": 0.8,
          "maxTokens": 250,
          "top_p": 0.9,
          "frequency_penalty": 0.3,
          "presence_penalty": 0.3,
          "max_completion_tokens": 2000
        }
      }
    }
  }
}

Send only the keys you want. A key you leave out is not sent at all, so the Default applies rather than a stored value. Add "id" beside "settings" to swap the whole model for another one from your catalogue at the same time.

top_p: An alternative to temperature for controlling variation. Set one or the other, not both.

frequency_penalty: Discourages repeating the same wording. Small positive values are enough; high values make the reply read oddly.

presence_penalty: Pushes the model toward new topics, which on a phone call can make it wander off the caller's question.

max_completion_tokens: The raw form of maxTokens, and the only token limit these models accept. max_tokens is refused by every GPT-5 model, so prefer maxTokens on the model entry unless you need to override it for a single call.

Models this page covers#

gpt-4.1, gpt-4.1-mini and gpt-4o. Every setting below was measured against each of the three and behaves identically on all of them, which is why they share a page.

None of these models has a reasoning phase, so the token budget is spent entirely on the spoken reply and a few hundred tokens is enough. reasoning_effort is accepted here and does nothing.

Choosing between them#

gpt-4.1 is the general-purpose default and the most widely used model on the platform. gpt-4.1-mini is the cheaper, lighter option for assistants whose replies are short and predictable. gpt-4o is the older generation, kept for assistants already using it.

Next steps#

• GPT-5 family: the next OpenAI model.
• Providers introduction: per-call overrides, and how a wrong value behaves across providers.