# AI models for authorized security testing

> Red team and cybersecurity models on Outrun for authorized security testing, from $0.30 in per 1M tokens. Authorization checklist; prices as of 2026-10-29.

Outrun lists 6 model IDs for authorized security work: `glm-5.3-flash-cybersecurity`, `outrun-redteam-flash`, `outrun-redteam-pro`, plus 3 less-restricted MiMo V2.6 Flash models. Prices start at $0.30 input and $1.00 output per 1M tokens. Use them only on systems you own or have written permission to test.

Prices as of 2026-10-29 16:34 ET, from the live price feed.

[Get your API key](https://outrun.to/overview)[Authorization checklist](https://outrun.to/red-team-ai-api#authorization)

$0.10 free API credit for eligible new accounts.

Security models on one Outrun key

## What authorization do I need before testing?

Have each of these in place before you send a single request about a target.

1. [ ok ]Written permission from the owner of every system you test, naming you or your team.
2. [ ok ]A defined scope: hosts, IP ranges, applications, accounts and dates.
3. [ ok ]Rules of engagement: allowed techniques, testing windows and what is off-limits.
4. [ ok ]A contact person and a stop procedure if something breaks.
5. [ ok ]A plan for findings you handle, such as credentials and personal data: report them, do not keep or reuse them.
6. [ ok ]A check of the laws and contracts that apply to you and to the systems in scope.

6/6 checks

## Which models are built for security testing?

All 6 security model IDs, sorted by input price.

| Model | Input | Output | Cached input |
| --- | --- | --- | --- |
| [GLM-5.3 Flash Cybersecurity](https://outrun.to/model/glm-5.3-flash-cybersecurity) `glm-5.3-flash-cybersecurity` | $0.30 | $1.00 | $0.15 |
| [MiMo V2.6 Flash Abliterated](https://outrun.to/model/mimo-v2.6-flash-abliterated) `mimo-v2.6-flash-abliterated` | $1.00 | $3.00 | $0.55 |
| [MiMo V2.6 Flash Uncensored](https://outrun.to/model/mimo-v2.6-flash-uncensored) `mimo-v2.6-flash-uncensored` | $1.00 | $3.00 | $0.40 |
| [MiMo V2.6 Flash Uncensored Thinking](https://outrun.to/model/mimo-v2.6-flash-uncensored-thinking) `mimo-v2.6-flash-uncensored-thinking` | $1.00 | $3.00 | $0.40 |
| [Outrun Red Team Flash](https://outrun.to/model/outrun-redteam-flash) `outrun-redteam-flash` | $1.35 | $4.50 | $0.24 |
| [Outrun Red Team Pro](https://outrun.to/model/outrun-redteam-pro) `outrun-redteam-pro` | $2.25 | $9.00 | $0.64 |

Prices as of 2026-10-29 16:34 ET, from the live price feed.

## Which terms apply?

Security models follow the same rules as every other model.

The [Terms](https://outrun.to/terms) apply to every request, on every model. They prohibit using Outrun to distribute malware, steal credentials or facilitate unlawful harm. Work only on systems you are authorized to test, and keep the authorization on file.

Outrun does not store your prompts, images or outputs unless you choose to save them.

## How do I call a security model?

Any OpenAI-compatible client works with the Outrun base URL.

Request example

```
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3-flash-cybersecurity", "messages": [{"role": "user", "content": "Review this function for injection bugs: ..."}]}'
```

## Red team AI API questions

Each model name opens its own page with setup values.

### What is a red team AI API?

A model you call over an API to help with authorized security work, such as reviewing code for bugs, planning test cases or writing reports. On Outrun it uses the same key and balance as every other model.

### Which Outrun models are meant for security testing?

GLM-5.3 Flash Cybersecurity, which is tuned for security research, red teaming and bug finding, plus Outrun Red Team Flash and Outrun Red Team Pro. The less-restricted MiMo V2.6 Flash Uncensored, MiMo V2.6 Flash Uncensored Thinking and MiMo V2.6 Flash Abliterated are listed too.

### How much do the security models cost?

From $0.30 input and $1.00 output per 1M tokens. The table lists every security model ID with its cached input price.

### Do I need authorization before testing?

Yes. Test only systems you own or have written permission to test, with a defined scope and rules of engagement.

### What is not allowed?

The Terms prohibit using Outrun to distribute malware, steal credentials or facilitate unlawful harm, on any model.

### Does Outrun keep my prompts?

Outrun does not store your prompts, images or outputs unless you choose to save them.

## Related pages

- [Text **Uncensored AI API**](https://outrun.to/uncensored-ai-api)
- [Images **Uncensored image API**](https://outrun.to/uncensored-image-api)
- [Chat **API for SillyTavern**](https://outrun.to/api-for-sillytavern)
- [Guide **GLM-5.3 API**](https://outrun.to/glm-api)
- [Legal **Terms of Service**](https://outrun.to/terms)
- [Dashboard **Get your API key**](https://outrun.to/overview)

---
Source: https://outrun.to/red-team-ai-api
Outrun: https://outrun.to/ | API base: https://api.outrun.to/v1 | Prices (JSON): https://api.outrun.to/pricing | Docs: https://outrun.to/docs/