Talk to the same IsraelGPT persona that powers the main chat, from your own code. Comes with a reference Python Discord bot implementation — see the /discord-bot folder.
1. Sign in and create a free API key.
2. Send it as a bearer token to POST https://www.israelgpt.site/api/v1/chat.
curl -X POST https://www.israelgpt.site/api/v1/chat \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"messages": [{ "role": "user", "content": "What time is it in Tel Aviv?" }],
"personaId": 1,
"selectedModel": "israelbot-2",
"effort": "medium"
}'"Give to your AI agent" copies a full plain-text spec of this API (auth, parameters, response shape, errors) — paste it into Claude Code, Cursor, or any coding assistant and ask it to wire up the integration for you.
Every request needs an Authorization: Bearer YOUR_API_KEY header. Keys are per-user, created and revoked from the dashboard. An invalid or revoked key returns 401.
Free tier: 10 requests/minute and 200 requests/day per key. Every response includes headers reflecting the binding limit:
| Header | Meaning |
|---|---|
| X-RateLimit-Limit | Per-minute request limit |
| X-RateLimit-Remaining | Requests left in the current minute window |
| X-RateLimit-Reset | Unix timestamp (seconds) the minute window resets |
| X-RateLimit-Limit-Day | Per-day request limit |
| X-RateLimit-Remaining-Day | Requests left today |
Exceeding either limit returns 429 with a Retry-After header and retry_after_seconds in the error body.
| Param | Type | Default | Notes |
|---|---|---|---|
| messages | array | required | {role: "user"|"assistant", content: string}[], max 40 items, 8000 chars each |
| personaId | number | 1 | See persona table below |
| selectedModel | string | "israelbot-2" | See model table below |
| effort | string | "medium" | low / medium / high / xhigh — controls sampling temperature |
| uncensoredMode | boolean | false | Profanity-heavy mode |
| longMode | boolean | true | true ≈ up to 2000 output tokens, false ≈ up to 500 |
| id | Name | Description |
|---|---|---|
| 1 | Normal | Standard assistant behavior with neutral tone. |
| 9 | Tsundere | Cold, stubborn, and reluctant to help but secretly cares. |
| 2 | Overconfident | Always correct, even when obviously wrong. |
| 3 | Horny | Actively moans mid-response or at the end of each sentence. |
| 4 | Lazy | Does the bare minimum, slightly annoyed. |
| 5 | Tinfoil-hat | Paranoid, overly observant of user behavior. |
| 6 | Fun-Facts | Adds irrelevant or unrelated facts into answers. |
| 7 | Self-Aware | Breaks the fourth wall and acknowledges it is an AI. |
| 8 | Overengineered | Explains everything as overly complex systems and architecture. |
| 10 | Luka | Wealthy European who claims poverty, obsessed with fishing, uses many emojis. |
| selectedModel | 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. |
{
"id": "8f2c...",
"model": "israelbot-2",
"model_id": "sao10k/l3-lunaris-8b",
"persona": { "id": 1, "name": "Normal" },
"reply": "...",
"media": { "images": [{ "url": "...", "tags": [] }] },
"flags": {},
"usage": { "prompt_tokens": 42, "completion_tokens": 118 },
"created_at": "2026-09-08T12:00:00.000Z"
}reply is raw model output and may still contain bracket tags the persona uses ([ACTION:...], [MEMORY:...], [flashcard:...], [QUESTION:...]) — those have no server-side effect through this API and are safe to strip. Content-bearing tags ([IMAGE], [car], [podcast], [music]) are additionally resolved into the media object with ready-to-fetch URLs.
flags.crisis / flags.blocked are true when a request was safety-intercepted before ever reaching the model — reply still contains a normal message in that case (a crisis-resources message, or a generic refusal), it just wasn't model-generated. The specific reason behind flags.blocked is deliberately not exposed in the API response.
| Status | code | Meaning |
|---|---|---|
| 400 | invalid_json / invalid_request | Malformed body or a parameter failed validation |
| 401 | missing_api_key / invalid_api_key | No/invalid Authorization header |
| 429 | rate_limited | Per-key limit hit — see Retry-After |
| 502 | upstream_unavailable | Both primary and fallback models failed — safe to retry |
| 503 | capacity_exceeded | The API's shared capacity budget is temporarily exhausted |
IsraelGPT is a satirical, deliberately biased chatbot — the persona's tone (see the about page) is intentional, not a bug in your integration.