nexusV1 as the model — it picks the best AI for your task automaticallycurl -X POST https://osint.lostingness.site/nexusai.php \
-H "Content-Type: application/json" \
-d '{
"action": "nexusv1",
"messages": [
{"role": "user", "content": "Aaj ka gold price kya hai?"}
]
}'$ch = curl_init('https://osint.lostingness.site/nexusai.php');
curl_setopt_array($ch, [
CURLOPT_RETURNTRANSFER => true,
CURLOPT_POST => true,
CURLOPT_POSTFIELDS => json_encode([
'action' => 'nexusv1',
'messages' => [['role' => 'user', 'content' => 'Hello!']],
]),
CURLOPT_HTTPHEADER => ['Content-Type: application/json'],
CURLOPT_TIMEOUT => 60,
CURLOPT_SSL_VERIFYPEER => false,
]);
$res = curl_exec($ch);
curl_close($ch);
$data = json_decode($res, true);
echo $data['content'];const res = await fetch('https://osint.lostingness.site/nexusai.php', {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({
action: 'nexusv1',
messages: [{role: 'user', content: 'What is AI?'}]
})
});
const data = await res.json();
console.log(data.content);import requests
res = requests.post('https://osint.lostingness.site/nexusai.php', json={
'action': 'nexusv1',
'messages': [{'role': 'user', 'content': 'Explain Python asyncio'}]
}, timeout=60)
data = res.json()
print(data['content'])// Success
{
"ok": true,
"content": "AI response here...", // nexusv1 / chat
"model": "nexusV1",
"type": "nexusV1-search", // which sub-model was used
"query_type": "SEARCH", // SEARCH/CODING/VISION/REASONING/CREATIVE/LONG/GENERAL
"search_used": true, // web search triggered?
"sources": ["https://..."], // search sources
"has_memory": true, // memory context injected?
"usage": {
"prompt_tokens": 150,
"completion_tokens": 80,
"total_tokens": 230
},
"powered_by": "lostingness AI v6.0.0"
}
// Error
{ "ok": false, "error": "message", "code": 400 }
// Rate limited (HTTP 429)
{ "ok": false, "error": "Rate limit message", "rate_limited": true, "retry_after": 60 }| Model ID | Best For | Notes |
|---|---|---|
nexusV1 | Everything — auto routing | ★ START HERE |
nexusV1-search | News, prices, real-time | + Tavily + Serper |
nexusV1-code | PHP, Python, JS, debug | Code expert |
nexusV1-vision | Image analysis, OCR | VISION |
nexusV1-reason | Math, logic, deep thinking | REASON |
nexusV1-creative | Stories, poems, shayari | Creative mode |
nexusV1-long | Long documents, summaries | 128k context |
nexusV1-fast | Quick short answers | Lightweight |
nexusV1-image | Image generation | zimage engine |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
gemini-2.5-flash | 1M | General, code, fast | ★ BEST CHEAP |
gemini-2.5-pro | 1M | Complex, detailed tasks | Premium |
gemini-3-flash-preview | 1M | Vision + general | VISION ★ |
gemini-1.5-flash | 1M | Fast general | Stable |
gemini-1.5-pro | 2M | Huge context | 2M tokens |
gemma-3 | 128k | Lightweight open | Open source |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
gpt-4.5-turbo | 128k | Search + reasoning | ★ SEARCH |
gpt-4o | 128k | Vision + general | VISION |
gpt-4o-mini | 128k | Cheap + capable | ★ CHEAP |
gpt-4 | 8k | Premium quality | Classic |
gpt-4-turbo | 128k | Fast GPT-4 | Turbo |
gpt-4.1 | 1M | Latest 1M context | 1M tokens |
gpt-4.1-mini | 1M | Fast + cheap | Mini |
gpt-4.1-nano | 1M | Ultra fast | Nano |
o1 | 200k | Deep step-by-step | REASON |
o1-mini | 128k | Fast reasoning | REASON |
o3 | 200k | Advanced reasoning | REASON |
o3-mini | 200k | Fast o3 | REASON |
o4-mini | 200k | Latest mini | REASON |
o4-mini-high | 200k | High effort | Thorough |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
grok-3 | 128k | Creative, witty | ★ CREATIVE |
grok-3-mini | 128k | Fast creative | Lightweight |
grok-2-1212 | 128k | Stable version | Dec 2024 |
grok-beta | 128k | Latest features | Beta |
grok-3-vision-beta | 128k | Vision + creative | VISION |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
llama-3.1-8b-instruct | 128k | Fast lightweight | 8B |
llama-3.1-70b-instruct | 128k | Balanced | 70B |
llama-3.1-405b-instruct | 128k | Powerful Llama | 405B |
llama-3.2-11b-vision-instruct | 128k | Vision small | VISION |
llama-3.2-90b-vision-instruct | 128k | Vision large | VISION |
llama-3.3-70b-instruct | 128k | Latest 70B | Improved |
llama-4-scout | 10M | 10M context! | Massive |
llama-4-maverick | 1M | Latest multimodal | VISION |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
deepseek-v3.2 | 128k | Code, analysis | ★ CODE VALUE |
deepseek-r1 | 64k | Math, reasoning | ★ REASON |
deepseek-r1-distill-qwen-32b | 32k | Fast reasoning | Distilled |
deepseek-r1-distill-llama-70b | 64k | Llama-based | Distilled |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
claude-3-5-sonnet-20241022 | 200k | Writing, analysis, vision | VISION |
claude-3-haiku-20240307 | 200k | Fast lightweight | Cheap |
claude-sonnet-4-5 | 200k | Latest Sonnet | Newest |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
qwen3-235b-a22b | 128k | Giant 235B model | Massive |
qwen3-30b-a3b | 128k | Mid-size capable | 30B |
qwen3-8b | 128k | Fast lightweight | 8B |
qwen-turbo | 128k | Fast + cheap | Turbo |
qwen-max | 32k | Most capable | Premium |
qwq-32b | 32k | Math + reasoning | REASON |
| Model ID | Context | Best For | Tag |
|---|---|---|---|
mistral-large-3 | 128k | General + tools | TOOLS |
mistral-small-3.1 | 128k | Vision + small | VISION |
mistral-nemo-instruct-2407 | 128k | 12B general | 12B |
mistral-7b-instruct-v0.3 | 32k | Lightweight | 7B |
mistral-codestral-2501 | 256k | Code specialist | Code |
mistral-codestral-mamba-v0.1 | 256k | Code Mamba arch | Code |
mistral-mixtral-8x7b-instruct | 32k | MoE model | MoE |
| Model ID | Provider | Context | Best For |
|---|---|---|---|
kimi-k2.5 | MoonShot | 128k | Long context, vision |
perplexity-sonar | Perplexity | 128k | Built-in web search |
perplexity-sonar-pro | Perplexity | 128k | Pro search quality |
phi-4 | Microsoft | 16k | Small reasoning |
phi-4-mini | Microsoft | 16k | Ultra lightweight |
nova-lite | Amazon | 300k | Fast + cheap |
nova-micro | Amazon | 128k | Ultra fast |
nova-pro | Amazon | 300k | Most capable Nova |
cloudflare-llama-3.1-8b | Cloudflare | 128k | Edge CDN inference |
cloudflare-qwen-1.5-7b | Cloudflare | 32k | Edge Qwen |
cloudflare-mistral-7b | Cloudflare | 32k | Edge Mistral |
| Model ID | Provider | Best For |
|---|---|---|
gemini-3-flash-preview | ★ Best vision overall | |
gemini-2.5-flash | Fast vision | |
gemini-2.5-pro | Detailed vision | |
gemini-1.5-flash | Quick image analysis | |
gemini-1.5-pro | Long image context | |
gpt-4o | OpenAI | Vision + reasoning |
gpt-4o-mini | OpenAI | Cheap vision |
gpt-4.1 | OpenAI | Latest vision |
grok-3-vision-beta | xAI | Creative + vision |
kimi-k2.5 | MoonShot | Vision + long context |
llama-3.2-11b-vision-instruct | Meta | Open source vision |
llama-3.2-90b-vision-instruct | Meta | Large open vision |
llama-4-maverick | Meta | Latest multimodal |
mistral-small-3.1 | Mistral | Vision + tools |
mistral-large-3 | Mistral | Vision analysis |
claude-3-5-sonnet-20241022 | Anthropic | Vision + writing |
model in action: "generate_image". ⚠ Images expire in 2 hours!action in JSON POST body to https://osint.lostingness.site/nexusai.php| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | nexusv1 |
messages |
array | ✅ | [{role,content}] conversation history |
system |
string | — | Custom persona/instruction |
temperature |
float | — | 0.0–2.0, default: 0.7 |
max_tokens |
int | — | Max tokens, default: 1200 |
multi_model |
bool | — | Multi-model synthesis (3 API calls) |
image_url |
string | — | Image URL or base64 for vision |
content| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | chat |
model |
string | ✅ | Any model ID from models list |
messages |
array | ✅ | Messages array |
system |
string | — | System prompt |
temperature |
float | — | 0.0–2.0 |
max_tokens |
int | — | Max tokens |
content| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | generate_image (or "image", "img") |
prompt |
string | ✅ | Detailed image description |
model |
string | — | zimage★, flux, klein, klein-large, gptimage |
width |
int | — | Width px, max 2048 (default: 512) |
height |
int | — | Height px, max 2048 (default: 512) |
image_url| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | vision (or "analyze_image", "ocr") |
image_url |
string | ✅ | HTTPS URL or data:image/jpeg;base64,... |
question |
string | — | Question about image (default: Describe this) |
model |
string | — | Vision model (default: best available) |
max_tokens |
int | — | Max tokens (default: 1024) |
reply| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | text (or "text_generate", "generate") |
model |
string | ✅ | Model ID |
prompt |
string | ✅ | Plain text prompt |
system |
string | — | System instruction |
temperature |
float | — | 0.0–2.0 |
max_tokens |
int | — | Max tokens (default: 500) |
completion| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | responses |
model |
string | ✅ | Model ID |
input |
string | ✅ | Your message |
instructions |
string | — | System-level instructions |
previous_response_id |
string | — | Chain to previous turn |
text + response_id| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | models (or "list_models") |
data[] array| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | memory_view | memory_clear | memory_save |
question |
string | * | For memory_save: question text |
answer |
string | * | For memory_save: answer text |
memory[], count| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | search (or "web_search") |
query |
string | ✅ | Search query |
tavily{}, serper{}| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | detect_search |
query |
string | ✅ | Query to analyze |
result{search,conf,kw}, type| Parameter | Type | Required | Description |
|---|---|---|---|
action |
string | ✅ | ping (or "health") |
service, version, memory, php| Type | Limit | Per | HTTP Response |
|---|---|---|---|
| Per minute | 20 requests | Per IP | 429 + Retry-After: 60 |
| Per hour | 200 requests | Per IP | 429 + Retry-After: 3600 |
| Per day | 800 requests | Per IP | 429 + Retry-After: 86400 |
| Memory store | 200 Q&A entries | Global | Auto-pruned |
| Image expiry | 2 hours | Per image | Save immediately! |