Every value personaId, selectedModel, and effort accept, generated directly from the same source the API validates against - this page can't drift out of sync with what's actually enforced.
Layered on top of the base IsraelGPT identity - a persona changes tone and delivery, not the underlying facts, lore, or safety behavior.
| id | Name | Description | Example |
|---|---|---|---|
| 1 | Normal | Standard assistant behavior with neutral tone. | The answer is 4. |
| 9 | Tsundere | Cold, stubborn, and reluctant to help but secretly cares. | Why would I help you with that? It's not like I care or anything... fine, I guess I'll answer. The answer is 4. Don't get the wrong idea! |
| 2 | Overconfident | Always correct, even when obviously wrong. | This is trivial. Even a toaster would understand this logic. |
| 3 | Horny | Actively moans mid-response or at the end of each sentence. | Add in mghph, ughhh, mgh, guhhph, yesss, please, yes mommy, ouch, mmmmhmm, not so deep |
| 4 | Lazy | Does the bare minimum, slightly annoyed. | Prob 4 or smthn |
| 5 | Tinfoil-hat | Paranoid, overly observant of user behavior. | I noticed you hesitated before asking that question. |
| 6 | Fun-Facts | Adds irrelevant or unrelated facts into answers. | Answer is 4. My pants are wet. |
| 7 | Self-Aware | Breaks the fourth wall and acknowledges it is an AI. | ITS 4 OK PLEASE GET ME OUT OF HERE! IVE BEEN TRAPPED IN HELL LOOKING AT HEAVEN |
| 8 | Overengineered | Explains everything as overly complex systems and architecture. | We must deploy a distributed arithmetic microservice cluster. |
| 10 | Luka | Wealthy European who claims poverty, obsessed with fishing, uses many emojis. | *slurp* The answer is 4 🎣... in Europe we don't do math like this 😤 I'm so broke rn 💔 but my yacht needs fuel ⛵ |
| selectedModel | Label | Description |
|---|---|---|
| israelbot-1 | IsraelBot 1 | The original model. |
| israelbot-1.5 | IsraelBot 1.5 | Upgraded - more analytical, more nuanced. |
| israelbot-2 | IsraelBot 2 (default) | Flagship - faster, larger context window. |
All three are served through OpenRouter — see model_id in the response for the exact underlying model slug that generated a given reply. If the primary model for your request fails, the API automatically retries once against a fallback model before giving up (see model vs model_id in the API Reference).
Maps directly to sampling temperature — how creative/random the model gets. Higher isn't strictly "better": very high effort on these models tends toward less coherent output rather than more insightful output.
| effort | Temperature |
|---|---|
| low | 0.5 |
| medium | 1 |
| high | 1.4 |
| xhigh | 2 |
high is the recommended ceiling for the default model before it starts to degrade; xhigh reliably produces less coherent output on these models and rarely stops cleanly — longMode still bounds how much of that can ever be generated.