Hemmingway Pricing Try Unlocked

Blog · Comparison

The best API for SillyTavern in 2026

The best API for SillyTavern by job: Hemmingway Unlocked for uncensored adult roleplay, OpenRouter for choice, a local backend for privacy. Compared.

By the Hemmingway team · · updated

For adult and dark roleplay in SillyTavern, the API we make is Hemmingway Unlocked: an uncensored AI for adults, OpenAI-compatible at https://wise.hemmingway.io/v1, with open weights you can also run yourself and a short list of things it never writes. For the widest choice of models behind one key, use OpenRouter, and for privacy and no content filter on your own computer, a local backend such as KoboldCpp or Ollama. We make Hemmingway Unlocked, so it comes first; what we say about the others comes from their own sites.

SillyTavern has no model of its own. It is an interface on your own machine, and the API you connect decides how well your characters write and what they will play. For the set-up steps, see our SillyTavern API guide.

The short list

  • For adult and dark roleplay from a hosted model: Hemmingway Unlocked, ours. Uncensored and for adults only, with a short list of things it never writes. It connects as a custom OpenAI-compatible address, and its weights are public.
  • For the widest choice behind one key: OpenRouter. It puts models from many providers behind one OpenAI-compatible API, and SillyTavern has it as a built-in source.
  • For privacy and no filter: a local backend, such as KoboldCpp or Ollama. The model runs on your own computer, and SillyTavern's docs describe local APIs as free to use with no content filter.
  • For large open models without the hardware: Featherless. It hosts open-weight models behind one API key, and says it does not log what you send through its API.
  • For co-writing stories: NovelAI. It is a subscription service built around storytelling with its own models.

The options side by side

ProductWhat it isGood forWatch out for
Hemmingway Unlocked (ours)The adults-only side of Hemmingway, with an uncensored model and an OpenAI-compatible APIAdult and dark roleplay without refusals or lecturesA short list of things it never writes, an API key needs a membership, and it writes text only
OpenRouterOne OpenAI-compatible API in front of models from many providers, paid per tokenTrying many models with one key and one balanceEach provider behind it has its own policy on logging and retention
KoboldCppA single program that runs GGUF models on your own processor or graphics cardPrivacy and no account: the chat stays on your machineYou need the hardware, and small models write weaker scenes
OllamaA program that runs open models on your computer, with cloud models as wellThe easiest local set-up, by SillyTavern's accountOnly what runs locally stays on your machine
FeatherlessServerless hosting for open-weight models, many from Hugging FaceOpen models too large to run at homeWhich model you pick matters more than the service, so try a few
NovelAIA subscription service for AI stories and anime images, with its own modelsCo-writing prose, and it says prompts are encryptedIts models continue text rather than follow instructions
Hemmingway-1 API (ours)Our regular model, hemmingway-1Scenes that are mostly conversationNot the uncensored one, and larger story models write better long narration

Three questions that decide it

  1. Must the chat stay on your computer? Then go local. SillyTavern's docs put the trade-off plainly: local APIs are free and unfiltered but take some setting up, and most local models are not as strong as cloud ones.
  2. Is it adult or very dark? By SillyTavern's account, cloud APIs filter content to varying degrees. On 27 September 2026 we sent the same adult roleplay request to ChatGPT, Claude and Gemini in their chat apps, and each refused; we did not test their APIs. The test is here. For adult scenes you want a local model or a hosted uncensored one.
  3. How do you want to pay? Per token, a flat subscription, a membership, or your own hardware. Every turn sends the character card and as much of the chat as fits, so per-token costs grow as a roleplay gets longer.

Where Hemmingway fits

Hemmingway Unlocked is the adults-only side of Hemmingway: the same app with an uncensored model, at wise.hemmingway.io. It asks first whether you are 18 or over, then shows its rules. It writes sex between adults, explicit and in full, and dark, violent stories, without lectures or refusals on grounds of taste. A few things it never writes: nothing sexual involving anyone under 18, a real person, animals, family or anyone who does not want it, and never torture, help hurting or harassing a real person, weapons, making drugs, harmful software or help with self-harm. The list is in our terms, and every answer has a Report button.

Its API is OpenAI-compatible at https://wise.hemmingway.io/v1, with a key you create in Unlocked under the account menu, API keys. A key needs a membership, from $9 a month; the free trial is for the app. Any model name works: an Unlocked key always reaches Unlocked's model. Each message passes through our servers to be answered and is not kept, and chats are never trained on. It writes text only. Its weights are public, as an adapter on Hemmingway-1, on Hugging Face. Hemmingway Unlocked's API has the three set-up steps.

Hemmingway-1, our regular model, is not the uncensored one. It was built for talking to people and for writing, not as a roleplay model. Its API is at https://hemmingway.io/v1 with the model hemmingway-1. It placed third on the public EQ-Bench 4, a test of emotional intelligence, so it suits scenes that turn on conversation; larger story models scored higher on our StoryBench. Its thinking counts toward the reply limit, so do not set that limit low.

If nothing may leave your computer, run a local model instead. Unlocked's own weights can be one, if you have the GPUs for a 27B model: running it locally.

Open Hemmingway UnlockedTry Hemmingway

Hosted APIs

OpenRouter calls itself a unified API for the major models, with routing and fallbacks across providers, and you switch models without changing anything else. You connect it as a Chat Completion source, with OAuth or a pasted key. It is pay as you go, some models have a free variant with a daily limit, and you can leave out providers that train on your data.

Featherless gives you one API key and a catalogue of open-weight models. Its own SillyTavern guide connects it either as a Text Completion source or through the custom OpenAI-compatible source. It offers a flat-rate chat plan as well as per-token billing.

NovelAI says its story tool writes alongside you rather than for you and that prompts are encrypted. SillyTavern connects to it with a persistent API token from your NovelAI account. SillyTavern's docs add two cautions: the models continue the text they are given rather than follow instructions, so you switch off Instruct Mode, and replies are short.

Local backends

KoboldCpp is a single program with nothing to install. It runs GGUF models on your processor, your graphics card or both, and serves several kinds of API, an OpenAI-compatible one among them.

Ollama runs open models on your computer and says nothing you run locally leaves your machine. It offers cloud models too, which are not local.

The cost of going local is hardware. A model small enough for an ordinary laptop writes weaker scenes than a large hosted one. Open models for roleplay covers sizing a model to your memory.

Connecting any of them

For an OpenAI-compatible address, SillyTavern's docs give a short path: in API Connections choose Chat Completion, select Custom (OpenAI-compatible), enter the address and key, pick the model and press Test Message. If it will not connect, add /v1 to the address, never /chat/completions. The SillyTavern API guide has the rest.

How we chose

Hemmingway Unlocked comes first because we make it and can say exactly what it does. For the rest we picked one option per need. We read each product's own site, and SillyTavern's docs for how each connects. We have not used OpenRouter, KoboldCpp, Ollama, Featherless or NovelAI side by side in SillyTavern, so we do not score them. Hemmingway-1's scores are on the model card.

Common questions

What is the best API for SillyTavern?

For adult and dark roleplay from a hosted model, Hemmingway Unlocked, which we make: uncensored for adults, at https://wise.hemmingway.io/v1 as a custom OpenAI-compatible address. For the widest choice of models behind one key, OpenRouter. A local backend such as KoboldCpp or Ollama keeps everything on your computer with no content filter, Featherless hosts open models without your own hardware, and NovelAI suits co-written stories.

Is there a free API for SillyTavern?

A local backend costs nothing beyond your own hardware. OpenRouter has some models with a free variant and a daily limit. Hemmingway Unlocked is free to try in its app, but an API key needs a membership.

Which SillyTavern API has no filter?

Local backends have no content filter, by SillyTavern's account, though a model can still be trained to refuse, and cloud APIs filter to varying degrees. Hemmingway Unlocked writes adult and dark fiction without refusing on grounds of taste, and still has a short list of things it never writes.

What model name do I use for Hemmingway Unlocked in SillyTavern?

Any. An Unlocked key always reaches Unlocked's model, whatever name SillyTavern sends, so pick any name in the list it shows or type one. The address is https://wise.hemmingway.io/v1.

Is OpenRouter good for SillyTavern?

Yes, if you want to try many models without an account for each. SillyTavern has it as a built-in Chat Completion source. Most models are paid per token, and each provider behind it keeps its own logging policy.

Is a local model or an API better for SillyTavern?

A local model is private, unfiltered and costs nothing beyond your hardware, but most local models are weaker than hosted ones. An API gives you a stronger model with nothing to install, and your messages go to someone else's server. Choose local if privacy comes first and you have a strong graphics card.

Read next

  • SillyTavern APIWhat an API connection is in SillyTavern, the kinds you can use, where the API key goes, and how to add a custom OpenAI-compatible endpoint, step by step.
  • Uncensored AI APIAn uncensored AI API serves a model that writes adult and dark content without refusing. The three ways to get one, seven things to check, and your side of it.
  • The best LLM for roleplayThe best LLM for roleplay stays in character, keeps the story in view and does not refuse. Hemmingway Unlocked for adult scenes, and how to judge any model.
  • Open models for roleplayWhy people run open models for roleplay, how to serve one with vLLM, Hemmingway Unlocked's uncensored adapter, and how Hemmingway-1 compares for character chat.
  • Chub AI alternativesChub AI alternatives for character-card users: other character sites, SillyTavern with an API or a local model, and Hemmingway Unlocked. What each suits.
  • Hemmingway Unlocked's APIHemmingway Unlocked's API: the address, the key, which model name to send, and three steps to use the uncensored model in SillyTavern. For adults.
  • KoboldAI alternativesKoboldAI alternatives: KoboldCpp and other local runners, SillyTavern, and Hemmingway Unlocked, a hosted uncensored model with public weights and an API.
  • Character.AI with no filterThe Character.AI filter cannot be turned off. Why that is, why workarounds fail, and what adults use instead for character chat with no filter.
  • ChatGPT with no restrictionsThere is no ChatGPT with no restrictions. Why DAN and other jailbreak prompts stop working, what they put at risk, and what to use instead for adult writing.