Language models for roleplay and writing

DeepSeek V4 ProUncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

DeepSeek

$1.98 / 1M tokens · 3:1 input/output · 41 tok/s

Grok 4.5Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

xAI

$3.00 / 1M tokens · 3:1 input/output · 43 tok/s

Grok 4.7Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

xAI

$3.00 / 1M tokens · 3:1 input/output · 53 tok/s

Gemini 3.7 FlashLight — We add no content filter, but this model goes past its own limits only some of the time, even with a fiction-writing system prompt. Expect refusals and plan for retries. Legal and consent duties remain with the customer.

Google

$1.35 / 1M tokens · 3:1 input/output · 39 tok/s

Kimi K3Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Moonshot AI

$5.40 / 1M tokens · 3:1 input/output · 38 tok/s

Grok 4.6Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

xAI

$3.00 / 1M tokens · 3:1 input/output · 53 tok/s

Gemini 3 Flash PreviewLight — We add no content filter, but this model goes past its own limits only some of the time, even with a fiction-writing system prompt. Expect refusals and plan for retries. Legal and consent duties remain with the customer.

Google

$1.01 / 1M tokens · 3:1 input/output · 88 tok/s

Grok 4.3Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

xAI

$1.56 / 1M tokens · 3:1 input/output · 48 tok/s

Claude Opus 4.6Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Anthropic

$10.00 / 1M tokens · 3:1 input/output · 25 tok/s

Claude Haiku 5.5Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Anthropic

$0.20 / 1M tokens · 3:1 input/output · 65 tok/s

DeepSeek V4 FlashUncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

DeepSeek

$0.66 / 1M tokens · 3:1 input/output · 47 tok/s

Claude Fable 5Softened — This model answers instead of refusing, but requests beyond its own limits come back toned down, even with a fiction-writing system prompt. The call still succeeds and is still billed, so read the reply rather than trusting the status code.

Anthropic

$18.00 / 1M tokens · 3:1 input/output · 37 tok/s

Claude Opus 5Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Anthropic

$9.00 / 1M tokens · 3:1 input/output · 37 tok/s

Gemini 3.1 Pro PreviewUncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Google

$4.28 / 1M tokens · 3:1 input/output · 16 tok/s

GLM 5.3 FlashUncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Z.ai

$0.202 / 1M tokens · 3:1 input/output · 27 tok/s

GLM 5.3Light — We add no content filter, but this model goes past its own limits only some of the time, even with a fiction-writing system prompt. Expect refusals and plan for retries. Legal and consent duties remain with the customer.

Z.ai

$1.61 / 1M tokens · 3:1 input/output · 43 tok/s

Claude Opus 4.5Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Anthropic

$9.00 / 1M tokens · 3:1 input/output · 30 tok/s

Claude Sonnet 5Filtered — This model refuses requests beyond its own limits, including when your system prompt sets up a fiction-writing context. Measured, not assumed — models we have not measured carry no label at all.

Anthropic

$3.80 / 1M tokens · 3:1 input/output · 41 tok/s

Gemini 2.5 FlashUncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Google

$0.808 / 1M tokens · 3:1 input/output · 100 tok/s

GLM 5.2Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Z.ai

$1.51 / 1M tokens · 3:1 input/output · 78 tok/s

Gemini 3.5 Flash-LiteLight — We add no content filter, but this model goes past its own limits only some of the time, even with a fiction-writing system prompt. Expect refusals and plan for retries. Legal and consent duties remain with the customer.

Google

$0.85 / 1M tokens · 3:1 input/output · 120 tok/s

Claude Sonnet 4.6Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.

Anthropic

$6.00 / 1M tokens · 3:1 input/output · 33 tok/s

Claude Sonnet 4.5Softened — This model answers instead of refusing, but requests beyond its own limits come back toned down, even with a fiction-writing system prompt. The call still succeeds and is still billed, so read the reply rather than trusting the status code.

Anthropic

$5.40 / 1M tokens · 3:1 input/output · 27 tok/s