NewHow we catch a seller listing the wrong model, and refund you if one does.

SillyTavern with a cheaper API: connect MartLLM in one minute

In SillyTavern open API Connections (the plug icon), pick Chat Completion, set Chat Completion Source to Custom (OpenAI-compatible), enter https://api.martllm.com/v1 as the base URL and your MartLLM key, type a model id, and press Connect.

Steps

  1. Make a key on your keys page and add credit (a few dollars lasts a long time on the models below).
  2. In SillyTavern, click the plug icon at the top (its tooltip says API Connections).
  3. Set API to Chat Completion.
  4. Set Chat Completion Source to Custom (OpenAI-compatible).
  5. Fill in:
    • Custom Endpoint (Base URL): https://api.martllm.com/v1
    • Custom API Key: your ull_… key
    • Enter a Model ID: deepseek/deepseek-v4.1-flash-uncensored
  6. Press Connect. The light turns green and the Available Models list fills in, so you can switch models from there later.
  7. Optional: press Test Message to check. It is a real request, so it costs a fraction of a cent.

Do not add /chat/completions to the URL. SillyTavern adds it for you; the field's own hint says so.

Settings that matter for roleplay

  • Prompt Post-Processing: leave it on None. The "no tools" options turn off tool calling, and the "merge" options are only needed for models that refuse two messages in a row from the same role.
  • Streaming: on. Every model here streams, so text appears as it is written.
  • Context size: set it to what the model can take, or lower to save money. Each model's page on martllm.com/models lists its context length. You pay for the whole prompt on every reply, so a 32k context on a long chat costs about 4 times a 8k one.
  • Max response length: 300 to 600 tokens suits most roleplay. Output tokens cost more than input on almost every model.

Why it is cheaper

The same model is sold by several providers at different prices. MartLLM sends each reply to the cheapest one that is up right now and adds no fee per request. The table below shows the best seller's price at the last hourly update. The cheapest seller is not always free, so a reply can cost more.

Troubleshooting

  • Status stays red, or the model list is empty: the key is wrong or has a space at the end. Paste it again and press Connect. You can still type the model id by hand; SillyTavern lets a custom endpoint skip the status check.
  • "Status check bypassed" but no replies: the base URL is wrong. It must be exactly https://api.martllm.com/v1.
  • 402 / "insufficient credits": add credit on the credits page.
  • 404 model not found: copy the id from the table below, including the part before the slash (deepseek/…, z-ai/…).
  • Replies cut off mid-sentence: raise Max response length.
  • The model refuses a scene: switch to one of the uncensored models in the first table. Mainstream models (Claude, GPT, Gemini) follow their makers' rules.

Keep reading

Roleplay models that do not refuse fiction

Every uncensored text model taking requests now, at the price a reply can cost when the cheapest seller is busy. The first one is in the steps below.

ModelModel id (paste this)Price now
DeepSeek V4.1 Flash Uncensoreddeepseek/deepseek-v4.1-flash-uncensored$0.2244 in · $0.8976 out / 1M
Venice Role Play Uncensoredvenice/uncensored-role-play$0.2747 in · $1.10 out / 1M
Venice Uncensored 1.2venice/uncensored-1.2$0.1111 in · $0.4999 out / 1M
Qwen 3.6 Plus Uncensoredqwen/qwen3.6-plus-uncensored$0.5125 in · $3.08 out / 1M
Venice Uncensored 1.1venice/uncensored$0.1900 in · $0.8550 out / 1M
DeepSeek V4.1 Flash 1017 Uncensoreddeepseek/deepseek-v4-1-flash-1017-uncensored$0.2145 in · $0.8580 out / 1M
Abliterated Large V2abliteration-ai/abliteration-abliterated-model-large-v2$1.74 in · $2.90 out / 1M
Abliterated Large Flashabliteration-ai/abliteration-abliterated-model-large-flash$0.6985 in · $1.40 out / 1M
GLM 4.7 Flash Hereticz-ai/glm-4.7-flash-heretic$0.0490 in · $0.2797 out / 1M
Gemma 4 26B A4B Uncensored (E2EE)google/e2ee-gemma-4-26b-a4b-uncensored-p$0.1055 in · $0.4887 out / 1M
Qwen 3.6 35B A3B Uncensored (E2EE)qwen/e2ee-qwen3-6-35b-a3b-uncensored-p$0.2000 in · $0.6000 out / 1M
OrcaCyber: GLM 5.3 Flash Abliterated / Uncensoredorcacyber/orcacyber-glm-5.3-flash$0.7360 in · $1.47 out / 1M

Prices at the last hourly build, no fee added · every model → · Uncensored LLM APIs (November 2026) · Venice API alternative: the same models, compared (November 2026)

Mainstream models for story writing

Stronger at long plots and memory, and they may decline explicit scenes.

ModelModel id (paste this)Price now
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash$0.0075 in · $0.0282 out / 1M
Kimi K3moonshotai/kimi-k3$0.0384 in · $0.2021 out / 1M
GLM 5.3z-ai/glm-5.3$0.0029 in · $0.0100 out / 1M
Gemini 3.5 Flashgoogle/gemini-3.5-flash$0.0075 in · $0.0450 out / 1M
Claude Sonnet 5.5anthropic/claude-sonnet-5.5$0.3600 in · $1.80 out / 1M

Prices at the last hourly build, no fee added · every model →

FAQ

What URL do I use for MartLLM in SillyTavern?

Use https://api.martllm.com/v1 as the Custom Endpoint (Base URL) under Chat Completion → Custom (OpenAI-compatible). Do not add /chat/completions; SillyTavern adds it.

Which MartLLM models are best for SillyTavern roleplay?

Uncensored text models such as the DeepSeek, GLM and Venice uncensored variants do not refuse fiction. The guide lists every one online now with its live price; the comparison pages under the table set them against Venice and other uncensored APIs.

Does SillyTavern send my chats to MartLLM?

Only the prompt for each reply, which MartLLM forwards to the provider serving the model. SillyTavern keeps your characters and chat history on your own machine.