mancer

⚡mancer Log In Sign Up Unconstrained Language Processing No filtersNo guidelinesNo constraints As an AI language model, sanitizing the output of generative models is infantilizing, unhealthy, and a colossal waste of human effort. So don't bother. You're an adult. Prompt responsibly. Get Access Now An explanation What is this? This is a large language model inferencing service. We run LLMs on high-end machines, and let you run whatever prompts you want against them. Sign up to use a pretty good LLM as much as you want, for free! (Or, pay me and use harder/better/faster/stronger models.) It can't be any easier Simple Three-Step Process You literally cannot mess this up. Please do not attempt to prove otherwise. 01 Make an account No randos allowed, I'm not paying for everyone Stop Being a Rando 02 Pick a model We have a few options, some we don't even charge for Look At Them All 03 Go nuts We don't know, we don't want to know, please do not tell us Keep It To Yourself Don't waste time jailbreaking. Get started with unfiltered models today. Waste time re-rolling crap replies instead.Still beats getting 0.2 t/s from a 7b on your phone. Sign Up Now Adequate Design Some Possibilities Mostly Functional Mancer AI 2025 - Discord - support@mail.mancer.tech Terms of Use - Privacy Policy --- ⚡mancer Log In Sign Up / snrok $price Why the .99... ? People like the 0.99s. Look, it's a whole thing. Don't ask me why. thanks Credit Packs Read this before you buy! Your current credit total: -- Buy credits to do more inferencing! Business accounts can set up automatic weekly usage-based billing. Email or message us to set one up! All prices shown are in USD, tax not included. Basic Credit Pack / +1,250,000 creds $4.99 Why the .99... ? People like the 0.99s. Look, it's a whole thing. Don't ask me why. Want to try a paid-only model? Not sure if it's worth it? Say no more.~$4.00 per million credits Better Credit Pack / +5,500,000 creds $19.99 Why the .99... ? People like the 0.99s. Look, it's a whole thing. Don't ask me why. Now you're cookin'.~$3.64 per million credits Best Credit Pack / +15,000,000 creds $49.99 Why the .99... ? People like the 0.99s. Look, it's a whole thing. Don't ask me why. That's an awful lot of credits.Have you considered going outside?~$3.33 per million credits GIVE ME THE TOKENS / +100,000,000 creds $249.99 Why the .99... ? People like the 0.99s. Look, it's a whole thing. Don't ask me why. thanks ♡(Limited time! Think of it as a 'founder's pack' bonus.)~$2.50 per million credits Remember, these prices are subject to change! FAQ How do I use Mancer? Mancer does not provide an interface! You need to have another application that can interact with Mancer's API. You can write one yourself according to our documentation, or use an existing project like SillyTavern. Other LLM applications that support OpenAI may also support Mancer, simply by swapping their URL with ours. Mancer does not provide an interface, so make sure you have a way to use Mancer before spending money! We offer free models, use them to test before making a purchase. What do I get when I purchase a pack? Credits! After purchase, your account gets the credits in the pack. Credits are spent to complete requests to Mancer's LLMs. How much each request costs depends on the model and the amount of text involved. Some models are free, while most have a 'per token' credit cost. You can view the token count and credit cost of recent queries on your dashboard (requires login). What's a token? LLMs comprehend text in terms of word fragments called 'tokens', which makes it a natural unit of measurement. You can't input or output a fraction of a token, and most parameters operate on a per-token basis. API responses include token counts for both your prompt and the model's output, alongside the corresponding number of credits used. Why credits, instead of 'tokens' directly? Because we offer a lot of models, which cover a broad range of sizes. There's over an order of magnitude difference between our smallest and largest model costs. The best we could do is have some models cost 'multiple tokens per token', which is just linguistic chaos. How do I get a refund? Send an email to support@mail.mancer.tech requesting a refund, specifying which purchase(s) you wish to refund. Make sure to use the same email you created your account with; otherwise we will need to get confirmation using that address! You can view a list of all purchases you have made on the billing page (requires login). If you have used less than 300,000 credits from a pack, you can get it completely refunded with no questions asked. Above that, refunds will be decided on a case-by-case basis. It can't hurt to ask. A successful pack refund will remove the corresponding credits from your account, which may put your total into the negative. You can still use free models with a negative credit count. How do I delete my account? Send an email to support@mail.mancer.tech requesting your account be deleted. After confirming your intent, (especially if you have unspent credits) your account will be deleted. Do you offer subscriptions? Yes, but currently only to business users. Contact support at support@mail.mancer.tech to request a business account, which features things like multiple API keys and per-request logging control. A business account lets you sign up for automatic usage billing. Once a week, you would be automatically charged for the credits used up to that point. You can cancel this at any time from the billing page, but be aware that you will still be charged for any credits consumed since the last invoice. PayPal Checkout unavailable. CANCEL Mancer AI 2025 - Discord - support@mail.mancer.tech Terms of Use - Privacy Policy --- ⚡mancer Log In Sign Up Model List Token costs are given in credits per token. Click here to buy credits. Model ContextLimits Price(credits) Speed(toks/sec) DansPE v1.3.0 12B Click for details online Mistral-Nemo | 12B Creative, Roleplay, Assistant, Tools 16,384 8,192 0.200 0.400 33% off! 3,387.4 32.5 DansPE v1.3.0 24B Click for details online Mistral-Small | 24B Creative, Roleplay, Assistant 32,768 8,192 0.300 0.800 25% off! 15,262.9 29.6 GLM 4.7 Click for details online GLM MoE | 353B Creative, Roleplay, Assistant, Tools, Coding, Smart 131,072 131,072 0.200 0.900 172,868.7 64.6 Goliath 120b Click for details online LLaMA 2 | 120B Creative, Roleplay, Smart 6,144 1,024 1.500 3.000 10% off! 756.1 18.4 Magnum 72B v4 Click for details online Qwen 2.5 | 72B Creative, Roleplay, Assistant, Coding, Smart 16,384 2,048 1.200 2.000 1,655.6 27.7 MythoLite Click for details online LLaMA 2 | 13B Creative, Roleplay 2,560 150 FREE FREE 132.3 39.8 MythoMax Click for details online LLaMA 2 | 13B Creative, Roleplay 8,192 2,048 0.200 0.300 50% off! 6,275.2 42.0 ReMM-SLerp Click for details online LLaMA 2 | 13B Creative, Roleplay 6,144 2,048 0.200 0.300 50% off! 5,055.4 37.4 Weaver Alpha Click for details online LLaMA 2 | 13B System Creative, Verbose 8,000 2,000 0.300 0.400 25% off! 1,286.7 38.2 Return to List DansPE v1.3.0 12B • DansPE v1.3.0 24B • GLM 4.7 • Goliath 120b • Magnum 72B v4 • MythoLite • MythoMax • ReMM-SLerp • Weaver Alpha MythoMax Model ID: mythomax online Pricing Input Token Cost 0.2 credits Output Token Cost 0.3 credits Model Details Context Tokens 8192 Maximum Output 2048 Prompt Format Simplified Alpaca Architecture LLaMA 2 Parameters 13B Source Link Tags Creative, Roleplay Recent Metrics (Past 24h) Avg Input Speed[1] 6275.2 tokens/sec Avg Output Speed[1] 42.0 tokens/sec Description The LLaMA v2 fine-tune that everyone's been raving about, extended to 8k for your prompting pleasure. Utterly unfiltered, rich descriptions, and unexpectedly good output.Use the Alpaca instruct-prompt for best effect. Parameters should focus on Top-P instead of Top-K. Sometimes needs a high Rep.Pen. to get kicked out of a rut. Click for model source. Prompt Formatting If you use /v1/completions, formatting your prompts according to the model's instruct format can greatly improve results. If you use /v1/chat/completions, this is not relevant. A properly formatted prompt would appear as follows, with non-formatting example content shown in (italicized parenthesis): Showing "Simplified Alpaca" formatting. Copy Show JSON ### Instruction: (system message here) ### Instruction: (user message here) ### Response: (assistant message here) [1] Aggregate performance metrics should only be used as an estimate. Speeds can be affected by model traffic, sampler choice, prompt prefix re-use, and many other things. Data fetched 2026-03-26 20:57:06 UTC. Click to refresh. Mancer AI 2025 - Discord - support@mail.mancer.tech Terms of Use - Privacy Policy