Start free with your email on XCurOS 2.2. A verified phone or any paid plan opens XCurOS 2.2 Max; a bigger plan gives you more room.
For trying XCurOS and learning. A key in a minute, with no card.
Requests
Tokens
Includes:
For real work, a little every day.
Requests
Tokens
Everything in Free, plus:
For people who code, write and research with XCurOS every day.
Requests2.5× Lite
Tokens2× Lite
Everything in Lite, plus:
For long coding sessions and agents that run for hours.
Requests5× Lite
Tokens4× Lite
Everything in Pro, plus:
For companies that need limits sized to their traffic, a licence, or the model inside their own network.
Everything in Max, plus:
Every key has a weekly and a monthly limit. The week is the last 7 days and frees up day by day; the month starts again on the 1st.
Pay for Lite, Pro and Max with PayPal, or with InstaPay in Egypt. The plan goes on your existing key.
| What you get | Free | Lite | Pro | Max | Custom |
|---|---|---|---|---|---|
| How much you get | |||||
| Requests a week | 2,500 | 5,000 | 12,500 | 25,000 | Agreed |
| Requests a month | 10,000 | 20,000 | 50,000 | 100,000 | Agreed |
| Tokens a week | 50M | 125M | 250M | 500M | Agreed |
| Tokens a month | 200M | 500M | 1B | 2B | Agreed |
| The model | |||||
| XCurOS 2.2 Max with a 512K context | With your phone | Yes | Yes | Yes | Yes |
| Claude's models in Claude Code, GPT's in Codex, at 1M | With your phone | Yes | Yes | Yes | Yes |
| XCurOS 2.2 Ultra with a 1M context | No | No | Yes | Yes | Yes |
| First to get new models | No | No | No | Yes | Yes |
| Thinks before it answers | Yes | Yes | Yes | Yes | Yes |
| Sees images, documents and video | Yes | Yes | Yes | Yes | Yes |
| Arabic and English | Yes | Yes | Yes | Yes | Yes |
| Where you use it | |||||
| The Playground | Yes | Yes | Yes | Yes | Yes |
| Claude Code, Codex, GitHub Copilot and seven more | Yes | Yes | Yes | Yes | Yes |
| OpenAI and Anthropic APIs | Yes | Yes | Yes | Yes | Yes |
| When the model is busy | |||||
| Your place in line | Normal | Normal | Ahead | First | First |
| Your key | |||||
| How long the key works | 90 days | While you subscribe | While you subscribe | While you subscribe | Agreed |
| Check your usage at any time | Yes | Yes | Yes | Yes | Yes |
| Help and your company | |||||
| A live status page | Yes | Yes | Yes | Yes | Yes |
| Help from the team by email | No | Yes | Yes | Yes | Yes |
| Help from the team on WhatsApp | No | No | Yes | Yes | Yes |
| A direct line to the team | No | No | No | Yes | Yes |
| Can run inside your company | No | No | No | No | Yes |
| A licence for the model | No | No | No | No | Yes |
| Keys for your whole team, on one invoice | No | No | No | No | Yes |
| Security questionnaires | No | No | No | No | Yes |
Start with Free. When your work reaches its limits, move to Lite. Pro gives you 2.5 times Lite's requests and Max five times. Your key stays the same when you move.
Choose your plan and pay with PayPal, or with InstaPay in Egypt. The plan goes on your existing key, so there is nothing to reconfigure. If you need another way to pay, write to us from the contact page.
No. Your key stays the same and its limits change, so every tool you have connected keeps working.
A piece of a word. Both what you send and what the model writes back are counted.
How much the model can hold in mind at once in one conversation. A bigger context means longer conversations and bigger files before it starts to forget.
The API answers 429 and says which limit was reached and when it frees up. Nothing is cut silently and no other model answers in its place.
Requests a month Every request, whatever its size. The count starts again on the 1st of each month, UTC.
Tokens a month Input and output tokens in the calendar month. The count starts again on the 1st of each month, UTC.
The weekly limit Requests and tokens over the last 7 days. They free up day by day as older use leaves the window.
Requests at once One key may run up to half of the model's capacity at the same moment, so nobody can take all of it. Past that the API answers 429 with Retry-After.
When the model is busy A request waits a few seconds for a free place. If none frees up, the API answers 503 with Retry-After — never a different model in our place. Every OpenAI and Anthropic SDK retries this by itself.
XCurOS 2.2 Max is an AI model: the part that understands what you ask and works out the answer. Chat apps, coding tools and company systems run on top of it — and it can run inside your own company, so your data never leaves.
Works with the coding agents you already use
Every AI app has two parts: the screen you type into, and the model that understands you and writes the reply. XCurOS is the model: the part that does the thinking.
Reads and writes Arabic, English and many other languages.
Photos, screenshots, charts, scanned papers and video.
Up to 1M tokens (pieces of words) at once — several long books. The Playground runs at 200K, still a whole book.
Works through maths, science and hard questions step by step.
Builds features and fixes bugs inside the coding tools developers already use.
Searches, runs commands and works with other apps until the whole job is done.
-- means the score was not published
Full model card →
Many AI services send what you type to another company's computers. XCurOS can run on your own servers instead — even with no internet connection at all.
Ask XCurOS anything, right in your browser. Nothing to install.
Try it freeA key in a minute. Works with Claude Code, Codex and 8 more tools.
Get an API keyLicences, pilots and a private setup on your own servers.
Talk to the teamAn AI model that thinks, sees and gets the job done.
Use it free in the Playground, or inside your coding tools with an API key.
8 of 256 experts write each word
It works the problem out before it answers.
Competition mathsAIME26
Contest programmingLiveCodeBench v6
It reads pictures, charts and video.
Understanding videoVideoMME
Reading chartsCharXiv RQ
It plans, uses your tools and finishes the work.
Fixing real softwareSWE-bench Pro
Working in a terminalTerminal-Bench 2.1
Short name: XCurOS 2.2 Max · Name in the API: xcuros-2.2-max
Model ID XCurOS-2.2-A4B-Max; architecture
designation XCurOS-2.2-35B-A4B, shared with the base tier — a multimodal
Mixture-of-Experts causal language model with an integrated vision encoder: ~35B total parameters,
~4B active per token, and a context window of up to 1,048,576 tokens. It is post-trained from
XCurOS 2.2 A4B, the tier before it, and both tiers share everything listed here.
XCurOS-2.2-A4B · XCurOS-2.2-A4B-MaxReasoning is what the hard answers are worth, so the API reasons before every answer. In the Playground it is a switch — the Think button by the composer — because a greeting does not need a reasoning pass and a proof does.
Only the Gated Attention layers cache; the DeltaNet layers carry a fixed recurrent state. ~20 KB per token at fp16.
On-premise copilots, document and chart understanding, OCR extraction, agentic automation, long-context analysis.
Trained further from A4B: it set itself tasks, built the tests that grade them, and learned from the results. That makes it our strongest model for real engineering work, in the terminal and across a whole code base.
The 2.2 model itself, with general training: reasoning, pictures, documents, tool calls and the full context window. Max is trained from it.
Both tiers are measured under the same protocol, so the two columns compare directly. Across all 56 published benchmarks Max leads on 52, is level on 3, and trails on one — MVBench, by 0.2. Eight of the widest gaps and the headline rows:
| Benchmark | XCurOS 2.2 A4B | XCurOS 2.2 A4B Max | Difference |
|---|---|---|---|
| Tool Decathlon | 31.8 | 49.1 | +17.3 |
| NL2Repo | 33.5 | 46.4 | +12.9 |
| Terminal-Bench 2.1 | 55.2 | 68.0 | +12.8 |
| OJBench | 46.2 | 54.3 | +8.1 |
| SWE-bench Pro | 53.2 | 59.6 | +6.4 |
| HLE | 20.7 | 24.7 | +4.0 |
| MMMU | 78.7 | 82.7 | +4.0 |
| SWE-bench Verified | 76.3 | 79.0 | +2.7 |
| Component | Total | Active — text | Active — image/video |
|---|---|---|---|
| Routed experts — 256 × 3 × 2048 × 512 × 40 layers | 32.21B | 8/256 → 1.01B | 1.01B |
| Shared expert — 3 × 2048 × 512 × 40 layers, always active | 0.13B | 0.13B | 0.13B |
| Attention — 10 Gated Attention + 30 Gated DeltaNet layers, incl. gates & conv projections | 1.28B | 1.28B | 1.28B |
| Embeddings (input + output, untied, vocab 248,320) | 1.02B | 1.02B | 1.02B |
| Vision encoder (depth 27, hidden 1152) | 0.44B | — | 0.44B |
| Total | ~35.1B ≈ 35B | ~3.4B | ~3.9B ≈ 4B |
The vision encoder runs only when an image or video is present, so a
text-only turn activates ~3.4B. The A4B designation refers to the multimodal figure.
Memory is set by the total parameter count — every expert must be resident even though only 8 of 256 fire per token.
| Precision | Weights | KV @ 32K | KV @ 262K | Minimum GPU configuration |
|---|---|---|---|---|
BF16 | ~70 GB | ~0.6 GB | ~5 GB | 2× 80 GB (H100 / A100) |
Every XCurOS Team product other than the open-weight releases is proprietary software — XCurOS 2.1 5B Instruct, XCurOS OCR, XCurOS 2.2 A4B, XCurOS 2.2 A4B Max and the serving stack that runs them. A valid paid licence is required for any use — personal, academic, evaluation or commercial. Access to the weights is gated on a licence reference.
Scores on coding, maths, reasoning, pictures and languages, next to other well-known models. Higher is better. The full model card, as published with the model, follows.
The card is published in English.
t=1.0 · top_p=0.95 · top_k=20The XCurOS Team does AI research and engineering. We build the models and the software that runs them, so your data never leaves your company.
XCurOS founded — secure AI systems for regulated environments.
The first release. Weights published openly.
413,510 downloads →Vision arrives: the model reads pictures.
548,352 downloads →Tool calling, and the first deployments inside companies.
Document understanding — text, layout and tables off the page.
A far larger model: video, and whole books at once.
The current model, trained for coding, tools and long tasks.
See the model →Download figures are Hugging Face's own, read in August 2026.
Licences, evaluations, on-premise pilots and partnerships — the fastest route is a direct email.
A question about your key or a tool, or a licence for your company? Write to us here, or pick another way below.
Tell us the tool (for example Claude Code), your computer (Windows, macOS or Linux) and the error you see. Many answers are already on the API page.
For a licence quote, it helps to include your deployment target (cloud, on-premise or air-gapped), expected concurrency, and whether you need vision and long context.
Licensed users can reproduce every published figure with the bundled harness. Ask us for the evaluation notebook when you write.
Send them to [email protected] — the model runs entirely inside your perimeter, which answers most of them.
Is XCurOS working right now? Live status of the API, the Playground and our servers. This page runs on a separate system, so it keeps working when they do not.
Contacting the status service.
One moment…
Get your key, try it in code, or connect your tools in one line.
Your key comes with your account. Create one at xcuros.com/signup: it takes a minute and it is free.
Your own requests and tokens. Only you can see them.
Run this one line in your terminal, then paste your key in the page that opens. Every tool below is ready.
On a computer — Windows, macOS or Linux. Not on a phone.
curl -fsSL https://xcuros.com/vendor/i.sh | sh
Open Terminal: on a Mac press ⌘ Space, type Terminal and press Enter. On Linux press Ctrl Alt T.
Open PowerShell: press the Windows key, type PowerShell and press Enter.
Paste it in Terminal with ⌘ V and press Enter.
Paste it in PowerShell with Ctrl V and press Enter.
A page opens in your browser: paste your key and press Connect.
Pick your tool to see its steps here.
It works with the OpenAI and Anthropic SDKs: set the base URL, your key and the model below.
A Mixture of Experts model shares its work among many small experts. For each word, a router picks the few that fit best. So most of the model rests, and the answer still comes from everything it knows.
https://xcuros.com/v1Authorization: Bearer YOUR_KEYxcuros-2.2xcuros-2.2 XCurOS 2.2, with a 256K-token context.
xcuros-2.2-max XCurOS 2.2 A4B Max with a 512K-token context — and Claude's models in Claude Code, GPT's in Codex, at 1M.
On Free, 10,000 requests and 200M tokens a month, with at most 2,500 requests and 50M tokens in any 7 days. The key works for 90 days; to renew it, contact the XCurOS team.
xcuros-2.2-ultra XCurOS 2.2 Ultra with a 1M-token context, on the Pro, Max and Custom plans. Paid plans start at $5 a month and go up to 100,000 requests and 2B tokens a month: see the plans.
| Endpoint | What it is for |
|---|---|
POST /v1/chat/completions | OpenAI Chat Completions: messages, streaming, tool calls, pictures (image_url) and JSON replies (response_format). |
POST /v1/responses | OpenAI Responses, as Codex and the newer OpenAI SDKs speak it. |
POST /v1/messages | Anthropic Messages, as Claude Code and the Anthropic SDKs speak it: streaming, tools and pictures. |
POST /v1/messages/count_tokens | How many tokens a request would use, before you send it. |
GET /v1/models | The models your key can use, with each one's context window. |
GET /v1/me | Your key's plan, its limits, what you have used and when each limit resets. Every answer also carries the same numbers in x-ratelimit-* headers. |
| Model | Context | Notes |
|---|---|---|
xcuros-2.2 | 256K | XCurOS 2.2, what a key made with an email opens. Text, pictures and documents in; tool calls. |
xcuros-2.2-max | 512K | XCurOS 2.2 A4B Max. Opens with a verified phone number or any paid plan, with Claude's models in Claude Code and GPT's in Codex at a 1M-token context. |
xcuros-2.2-ultra | 1M | XCurOS 2.2 Ultra. Opens with the Pro, Max or Custom plan, beside Max and everything that comes with it. |
| Status | What it means |
|---|---|
400 | The request is longer than the model's context. Shorten it and send it again — the error gives both sizes. |
401 | The key is missing, wrong or expired. Check it above; if it has expired, contact the XCurOS team to renew it. |
403 | That model is not on your key. xcuros-2.2-max, and Claude's and GPT's models with it at 1M, open when you verify your phone number or pick a plan. |
413 | The request is larger than 48 MB. Send fewer or smaller attachments. |
429 | Too many requests at once on this key, or its allowance is used up. Wait as long as Retry-After says; the error names the limit and when it frees up. |
503 | The model is busy right now or starting up. Wait as long as Retry-After says and send it again; every OpenAI and Anthropic SDK does this by itself. |
5xx | The service is not answering. Try again in a few seconds; the Uptime page shows its state. |
Yes. The Free plan costs nothing: 10,000 requests and 200M tokens a month, on a key that works for 90 days. For more, see the plans.
No. Connect sets up your tools for you: copy one line, paste it, press Enter, then pick your tools in the page that opens.
Claude Code, Codex, GitHub Copilot, Antigravity, Kilo Code, OpenCode, Qwen Code, Grok Build, Cline and Continue. Any app that speaks the OpenAI or Anthropic API works too.
Yes, in the Playground. Connecting coding tools needs a computer: Windows, macOS or Linux.
Enter the same email above. You get the same key back, not a new one.
It is optional. Your key works with your email alone, on xcuros-2.2 with a 256K context. Verifying your phone through Telegram opens xcuros-2.2-max with 512K, and Claude's models in Claude Code and GPT's in Codex at a 1M-token context.
Run the same line again and press Disconnect. Every file goes back exactly as it was.
One moment…