Eligible new accounts get $0.10 in free API credit. Once per account; abuse limits apply. Create an account

Outrun
Sign in Get your key

One AI API with uncensored and abliterated models.

Outrun runs 24 uncensored and abliterated LLMs, 12 uncensored image models and 3 uncensored video models through one OpenAI-compatible API key. Text starts at $0.10 per 1M tokens, billed from prepaid USD credit with no subscription.

Try uncensored models Get an API key Compare prices

$0.10free credit for eligible new accounts, and 10 free web searches a day in the Playground.

24uncensored and abliterated LLMs
12uncensored image models
$0.10lowest input price per 1M tokens
$0.16per second of 480p video
  • Uncensored$0.10 in / $0.10 out
    GLM-5.3 Flash Uncensoredglm-5.3-flash-uncensored

    Lowest-priced uncensored LLM on Outrun

  • Abliterated$2.00 in / $2.00 out
    GLM-5.3 Abliteratedglm-5.3-abliterated

    Native tool calls verified in Roo Code

  • Uncensored$0.22 in / $1.46 out
    GPT OSS 120B Uncensoredgpt-oss-120b-uncensored

    Uncensored build of the open-weight GPT OSS 120B

Understand the model

Different approaches.
The same API.

Uncensored and abliterated describe how a model is changed. Thinking describes how it answers. Here is what each label means.

01 / Behaviour

Uncensored

A different approach to refusals.

Tuned or configured to answer requests that mainstream models decline.

Keep in mind

Some GLM variants include a system prompt of about 14,000 tokens, billed as input on every request.

02 / Model weights

Abliterated

Changed at the weights.

Refusal behaviour is removed from the model weights.

Tool support

GLM-5.3 Abliterated and GLM-5.3 Flash Abliterated were verified with native tool calls in Roo Code.

03 / Reasoning

Thinking

Reasons before it answers.

MiMo V2.6 Flash Uncensored Thinking uses the output rate for reasoning tokens.

Request setting

Leave reasoning_effort unset to keep its default thinking mode.

04 / Model selection

Alternative routes

Same base. A separate route.

A model marked (2) or (3) is an alternative route to the same base model, with its own ID and price.

Choosing a version

Use the exact model ID of the version you want.

Compare them in your own app. Keep your integration and switch the model ID.

Compare model prices

Uncensored LLM API prices

The lowest-priced uncensored LLM on Outrun is GLM-5.3 Flash Uncensored at $0.10 per 1M input tokens and $0.10 per 1M output tokens. All 23 uncensored and abliterated text models are listed below, grouped by base model and sorted by price, from $0.10 to $12.00 per 1M output tokens.

Text modelsUSD per 1M tokens
ModelInputOutputCached input
GLM-5.3 FlashGuide
GLM-5.3 Flash Uncensoredglm-5.3-flash-uncensoredBuilt-in system prompt of about 14k tokens, billed as input$0.10$0.10$0.01
Route 2 of GLM-5.3 Flash Uncensored: glm-5.3-flash-uncensored-2Route 2$0.22$0.77$0.03
Route 3 of GLM-5.3 Flash Uncensored: glm-5.3-flash-uncensored-3Route 3$0.40$1.60$0.14
Route 4 of GLM-5.3 Flash Uncensored: glm-5.3-flash-uncensored-4Route 4$0.48$1.92$0.17
GLM-5.3 Flash Cybersecurity Uncensoredglm-5.3-flash-cybersecurity-uncensored$1.05$3.50$0.53
Apex Flash 1 Abliteratedglm-5.3-flash-apex-abliteratedRefusals removed in the model weights, not by a prompt$0.30$1.00$0.15
GLM-5.3 Flash Abliteratedglm-5.3-flash-abliteratedRefusals removed in the model weights, not by a prompt · alternative route$0.30$1.22$0.10
Route 2 of GLM-5.3 Flash Abliterated: glm-5.3-flash-abliterated-2Route 2$3.52$3.52$0.96
GLM-5.3 Flash Code Uncensoredglm-5.3-flash-code-uncensoredUncensored version of GLM-5.3 Flash Code$12.00$12.00$2.40
GLM-5.3Guide
GLM-5.3 Uncensoredglm-5.3-uncensoredBuilt-in system prompt of about 14k tokens, billed as input$0.20$0.20$0.04
Route 2 of GLM-5.3 Uncensored: glm-5.3-uncensored-2Route 2$0.59$1.75$0.17
Route 3 of GLM-5.3 Uncensored: glm-5.3-uncensored-3Route 3$2.50$4.50$0.60
GLM-5.3 Abliteratedglm-5.3-abliteratedRefusals removed in the model weights, not by a prompt · Native tool calls verified in Roo Code$2.00$2.00$0.55
Route 2 of GLM-5.3 Abliterated: glm-5.3-abliterated-2Route 2$4.50$4.50$1.32
Route 3 of GLM-5.3 Abliterated: glm-5.3-abliterated-3Route 3$2.44$4.88$0.37
GPT OSS
GPT OSS 120B Uncensoredgpt-oss-120b-uncensoredUncensored version of GPT OSS 120B$0.22$1.46$0.22
DeepSeekGuide
DeepSeek V4 Pro Uncensoreddeepseek-v4-pro-uncensoredUncensored version of DeepSeek V4 Pro$1.00$1.00$0.20
DeepSeek V4.1 Flash Uncensored 1017deepseek-v4.1-flash-1017-uncensored-3Uncensored version of DeepSeek V4.1 Flash 1017$0.66$2.64$0.02
Route 4 of DeepSeek V4.1 Flash Uncensored 1017: deepseek-v4.1-flash-1017-uncensored-4Route 4$0.81$3.23$0.03
DeepSeek V4.1 Flash Uncensored Thinking 1017deepseek-v4.1-flash-1017-uncensored-thinking-3Uncensored version of DeepSeek V4.1 Flash 1017, reasons before answering$0.66$2.64$0.02
Route 4 of DeepSeek V4.1 Flash Uncensored Thinking 1017: deepseek-v4.1-flash-1017-uncensored-thinking-4Route 4$0.81$3.23$0.03
DeepSeek V4.1 Flash Abliterateddeepseek-v4.1-flash-abliteratedRefusals removed in the model weights, not by a prompt$2.10$2.10$0.36
Route 3 of DeepSeek V4.1 Flash Abliterated: deepseek-v4.1-flash-abliterated-3Route 3$0.35$1.22$0.09
DeepSeek V4.1 Flash 1017 Abliterateddeepseek-v4.1-flash-1017-abliterated$0.60$0.60$0.20
DeepSeek V4.1 Flash 1017 Abliterated Fastdeepseek-v4.1-flash-1017-abliterated-fast$1.40$1.40$0.32
MiMo
MiMo V2.6 Flash Abliteratedmimo-v2.6-flash-abliteratedRefusals removed in the model weights, not by a prompt$1.00$3.00$0.55
Route 2 of MiMo V2.6 Flash Abliterated: mimo-v2.6-flash-abliterated-2Route 2$1.17$3.49$0.63
MiMo V2.6 Flash Uncensoredmimo-v2.6-flash-uncensoredUncensored version of MiMo V2.6 Flash$1.00$3.00$0.40
Route 2 of MiMo V2.6 Flash Uncensored: mimo-v2.6-flash-uncensored-2Route 2$1.22$3.66$0.49
MiMo V2.6 Pro Uncensoredmimo-v2.6-pro-uncensored$2.29$4.57$0.02
MiMo V2.6 Flash Uncensored Thinkingmimo-v2.6-flash-uncensored-thinkingReasoning tokens use the output rate$1.00$3.00$0.40
Outrun Red Team
Outrun Red Team Flashoutrun-redteam-flashUncensored text model$1.35$4.50$0.24
Outrun Red Team Prooutrun-redteam-proUncensored text model$2.25$9.00$0.64
MiniMaxGuide
MiniMax M3 Uncensoredminimax-m3-uncensoredUncensored version of MiniMax M3$1.50$8.00$0.38
Nemotron
Nemotron 3 Ultra 550B Uncensorednemotron-3-ultra-550b-a55b-uncensoredUncensored version of Nemotron 3 Ultra 550B$1.69$9.90$0.43
Qwen
Qwen 3.8 27B Abliteratedqwen3.8-27b-abliteratedRefusals removed in the model weights, not by a prompt$0.51$2.27$0.07

Rates are shown rounded up to the cent; billing uses the exact rate.

Uncensored image and video generation API

Outrun runs 12 uncensored image models, from $0.03 per image, and 3 uncensored video models from $0.16 per second of output. Images use POST /v1/images/generations and video uses /v1/videos, with the same key and USD balance as text models.

Image modelsUSD per image
ModelPer image
Chroma Uncensoredchroma-uncensored$0.16
Lustify SDXL Uncensoredlustify-sdxl-uncensored$0.07
CyberRealistic XL Uncensoredcyberrealistic-xl-uncensored2048x2048 · 512x512 $0.03 · other sizes $0.05$0.06
WAI Illustrious SDXL Uncensoredillustrious-xl-uncensored2048x2048 · 512x512 $0.03 · other sizes $0.05$0.06
Qwen Image 2.1 Uncensoredqwen-image-2.1-uncensored1K · 2K $0.40$0.08
Qwen Image 3 Uncensoredqwen-image-3-uncensored$0.16
HunyuanImage 3.0 Instruct Uncensoredhunyuan-image-3-instruct-uncensored$0.23
Qwen Edit Uncensoredqwen-edit-uncensored$0.16
Vision Image Uncensoredvision-image-uncensored$0.08
Anime Image Uncensoredanime-image-uncensored$0.06
Seedream 5.0 Lite Edit Uncensoredseedream-5.0-lite-edit-uncensoredNeeds a reference image$0.07
Vision Pro Image Uncensoredvision-pro-image-uncensored$0.19
Video modelsUSD per second of output
ModelPer second
Wan 3.0 Video Uncensoredwan-3.0-video-uncensored480p$0.40
LTX-2.3 Image-to-Video Uncensoredltx-2.3-i2v-uncensored480p$0.16
720p$0.32
1080p$0.48
Wan 3.0 Image-to-Video Uncensoredwan-3.0-i2v-uncensored480p$0.40
720p$0.80
1080p$1.60
Wan 3.0 Video Uncensored, 720p$0.80
Wan 3.0 Video Uncensored, 1080p$1.60
  • First image. Start with vision-image-uncensored for text-to-image.
  • Reference images. Seedream 5.0 Lite Edit Uncensored needs a reference image, and Qwen Image 2.1 Uncensored accepts input.image_urls with a 1K or 2K input.resolution.
  • Video. Send a prompt with seconds from 2 to 30 and a resolution of 480p, 720p or 1080p.
  • Prices per image and per clip. See the uncensored image API page and video API pricing per clip.
No setupChat with uncensored modelsUse any uncensored text model in your browser, with the same balance and prices as the API. Image and video models run through the API.

How do I connect an app to uncensored models?

  1. 01

    Get your key

    Open the Telegram bot and copy your personal key. Paste it only into your app's private key field.

  2. 02

    Add an OpenAI-compatible provider

    Set the base URL to https://api.outrun.to/v1 exactly as shown, without /chat/completions.

  3. 03

    Pick a model ID

    Start with glm-5.3-abliterated, the model the setup guides test with, and save other IDs as separate profiles to compare them.

  4. 04

    Send a short test

    Ask for "Reply with OK only." A short reply confirms the connection, and the test is billed from your credit like any other request.

Why the guide uses Roo Code. Coding agents send their own built-in system prompt with every request, and in many of them that prompt tells the model to refuse certain tasks, which can override an uncensored model. Roo Code is the agent Outrun tested these models with, including native tool calls on GLM-5.3 Abliterated and GLM-5.3 Flash Abliterated.

POST/v1/chat/completions 
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-abliterated",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
Swap the model
GLM-5.3 Abliterated$2.00 in/$2.00 outper 1M tokens All uncensored prices

Keep your key in an environment variable, never in client-side code.

No computer neededSet it up on your phoneA 9-step guide with a screenshot for every step connects Cumbersome on iPhone to your Outrun key. AnythingLLM on Android uses the same values.

Setup guides

Does Outrun store my prompts and responses?

No. Outrun does not store your prompts, images or outputs unless you choose to save them. This applies to every model, uncensored and abliterated ones included. API calls are never added to your chat history. For each request Outrun keeps only the billing record: the model, request ID, time, token counts, status and charge.

Read the full privacy policy

POST /v1/chat/completionsExample request record
Model
glm-5.3-abliterated
Tokens
1,284 in · 312 out
Charge
$0.0032 at $2.00 in / $2.00 out per 1M
Status
200 OK
Prompt
Not stored
Response
Not stored

The billing record is all Outrun keeps for an API request.

  • Your prompts are not stored

    Outrun does not store your prompts, images or outputs unless you choose to save them. Outrun keeps only the account, billing and usage records needed to run the service, without your content.

  • API calls leave no transcript

    Direct API text calls are not added to account chat history. Apps you connect, such as Roo Code or a mobile client, can keep their own copies on your device.

  • Playground history is your choice

    Playground text chats start temporary and are gone when you close the page. Turn on saved history and conversations are encrypted at rest, and you can delete them at any time. Image and video jobs you start are saved to your account so you can download the results.

  • Same rule on every model

    Uncensored and abliterated models follow the same privacy rule as every other model in the catalog.

What is not allowed on uncensored models?

The same acceptable use policy covers every Outrun model, uncensored and abliterated ones included. Fewer refusals from a model does not change what the terms allow.

  • Child safety

    Child sexual abuse material and sexual content involving anyone under 18 are prohibited across all Outrun models, including uncensored, abliterated, image and video models.

Uncensored API questions

The Roo Code guide covers model settings and error codes step by step.

How much does the built-in system prompt add per request?

GLM-5.3 Flash Uncensored and GLM-5.3 Uncensored bill about 14,000 extra input tokens on every request, which adds about $0.0007 and $0.0014 per request at their rates. For many short requests, compare the total with an abliterated model before you choose.

What settings do abliterated GLM models need in a coding agent?

Set the context window to 1,000,000 tokens and the maximum output to 65,536 tokens. With those limits, GLM-5.3 Abliterated and GLM-5.3 Flash Abliterated were verified with native tool calls in Roo Code, and the Roo Code guide shows each setting.

What is the difference between uncensored and abliterated models?

Uncensored models are tuned or configured to refuse far less than mainstream chat models. Abliterated models have their refusal behaviour removed from the model weights. Behaviour and quality differ by model, so test the one you choose.

Which uncensored model costs the least?

GLM-5.3 Flash Uncensored (glm-5.3-flash-uncensored) has the lowest input price on this page: $0.10 per 1M input tokens and $0.10 per 1M output tokens.

Does Outrun store my prompts on uncensored models?

Outrun does not store your prompts, images or outputs unless you choose to save them. The same rule applies to every model in the catalog.

How do I pay for the uncensored API?

Add balance by debit or credit card from $5, top up with crypto from $5, or redeem a prepaid code. The same key and balance work for every model.

Try an uncensored model in the Playground.

Test any model in your browser with your own key and credit, then connect Roo Code or a mobile app with the same key.

Try the Playground Get a key in Telegram ↗