collections/roleplay · 23 models
Models built or tuned for long-form fiction, character work, and open-ended writing. Some are here because the provider says so outright, some because the provider publishes them as unmoderated, and the rest are picks: the general-purpose models that hold a voice and a long thread well, which no provider advertises as a capability. Context length matters more here than almost anywhere else, so the list leads with the largest windows.
Models
23
Labs
13
model creators
From (input)
$0.07
per 1M tokens
Max context
1M
Private routes
17 / 23
up to E2EE
Ordered by largest context.
DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.
Claude Sonnet 5 is Anthropic's latest Sonnet model, substantially improving on Sonnet 4.6 in coding and agentic work and reaching near-Opus quality on many tasks. It features a 1M token context window, adaptive thinking, and strong document and vision understanding.
DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
Qwen 3.6 Plus Uncensored is Alibaba's latest flagship reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.
Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.
MiniMax-M3 preview is a 1.4T-parameter frontier model from MiniMax for coding, agentic workflows, and complex reasoning, served at fp8 with a 512K context window.
GLM 5.2 running in a Trusted Execution Environment (TEE). Z.AI's flagship model for long-horizon tasks with enhanced reasoning and project-level engineering context, with hardware attestation evidence available for independent verification.
Kimi K3 served in a Tinfoil verified confidential enclave.
Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation.
Mistral Large 3 675B Instruct through Amazon Bedrock Mantle with zero retention.
Kimi K2.6 is an open-source, native multimodal agentic model from Moonshot AI with 1T total parameters and 32B active parameters. It excels at long-horizon coding, coding-driven design, agent swarm orchestration, and proactive autonomous execution with 256K context windows.
GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.
GLM-4.7 is a large language model developed by Zhiyuan AI, featuring strong reasoning capabilities and support for multiple languages. Supports the largest context window for processing extensive text and detailed analysis.
DeepSeek-V3.2 is an efficient large language model with DeepSeek Sparse Attention (DSA) for long contexts. It features strong reasoning and tool-use skills, achieving top results on the 2025 IMO and IOI.
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.
Euryale 3.1 - 70B v2.2 is a model focused on creative roleplay from Sao10k
Aion 3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
Hermes 3 405B is a frontier level, full parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.
Optimized for creative roleplay scenarios with maximum freedom. Designed for immersive storytelling, character interactions, and open-ended creative writing.
Venice Uncensored 1.2 is designed for maximum creative freedom and authentic interaction. Built for open-ended exploration, roleplay, and unfiltered dialogue with improved capabilities over 1.1.
Gemma 4 26B A4B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Google's Gemma 4 MoE model with 25.2B total / 3.8B active parameters, supporting multimodal input across text and images, with hardware attestation evidence available for independent verification.
This list is rebuilt from the live catalog rather than stored as a snapshot, so it tracks pricing, context windows, and privacy tiers as providers change them. Ordering is yours to pick, and there is no popularity option: prompts are never retained, and the usage metadata kept for billing is not turned into a public ranking.
Strongest guarantee in this collection:E2EE
