Search/
Skip to content
/
OpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Apps
  • Models
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Announcements
  • CareersHiring
  • Privacy
  • Terms of Service
  • Support
  • State of AI
  • Works With OR

Developer

  • Documentation
  • API Reference
  • SDK
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Collections/Roleplay

Best AI Models for Roleplay (RP) and Creative Writing

Model rankings updated March 2026 based on real usage data.

Discover the top AI models for roleplay (RP), character chat and creative writing, ranked by real usage data on OpenRouter. These LLMs excel at maintaining consistent personas, rich dialogue and immersive storytelling across long-context sessions.

Whether you're using Janitor AI, SillyTavern or another frontend, or building your own character chatbot or interactive fiction engine, OpenRouter gives you access to the best roleplay models through a single API.

LLM Leaderboard for Roleplay Models

1.
Deepseek V3.2
by deepseek
494B
37.0%
2.
gpt-oss-120b
by openai
86.2B
6.5%
3.
Grok 4.1 Fast
by x-ai
78B
5.8%
4.
Hunter Alpha
by openrouter
75B
5.6%
5.
Gemini 2.5 Flash Lite
by google
69.7B
5.2%
6.
Gemini 3 Flash Preview
by google
54.3B
4.1%
7.
Step 3.5 Flash (free)
by stepfun
31.4B
2.3%
8.
GLM 5
by z-ai
29.6B
2.2%
9.
Gemini 2.5 Flash
by google
29B
2.2%
10.
Others
by unknown
388B
29.1%

Top Roleplay Models on OpenRouter

Based on top weekly usage data from millions of users accessing AI models for roleplay through OpenRouter.

Favicon for deepseek

DeepSeek: DeepSeek V3.2

1.16T tokens

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs

by deepseek164K context$0.26/M input tokens$0.38/M output tokens
Favicon for google

Google: Gemini 3 Flash Preview

1.08T tokens

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.

The model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.

by google1.05M context$0.50/M input tokens$3/M output tokens$1/M audio tokens
Favicon for anthropic

Anthropic: Claude Sonnet 4.6

1.05T tokens

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

by anthropic1M context$3/M input tokens$15/M output tokens
Favicon for anthropic

Anthropic: Claude Opus 4.6

979B tokens

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.

Beyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.

For users upgrading from earlier Opus versions, see our official migration guide here

by anthropic1M context$5/M input tokens$25/M output tokens
Favicon for google

Google: Gemini 2.5 Flash

637B tokens

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.

Additionally, Gemini 2.5 Flash is configurable through the "max tokens for reasoning" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).

by google1.05M context$0.30/M input tokens$2.50/M output tokens$1/M audio tokens
Favicon for moonshotai

MoonshotAI: Kimi K2.5

608B tokens

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

by moonshotai262K context$0.45/M input tokens$2.20/M output tokens
Favicon for x-ai

xAI: Grok 4.1 Fast

522B tokens

Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window.

Reasoning can be enabled/disabled using the reasoning enabled parameter in the API. Learn more in our docs

by x-ai2M context$0.20/M input tokens$0.50/M output tokens
Favicon for google

Google: Gemini 2.5 Flash Lite

517B tokens

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.

by google1.05M context$0.10/M input tokens$0.40/M output tokens$0.30/M audio tokens
Favicon for xiaomi

Xiaomi: MiMo-V2-Flash

469B tokens

MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi. It is a Mixture-of-Experts model with 309B total parameters and 15B active parameters, adopting hybrid attention architecture. MiMo-V2-Flash supports a hybrid-thinking toggle and a 256K context window, and excels at reasoning, coding, and agent scenarios. On SWE-bench Verified and SWE-bench Multilingual, MiMo-V2-Flash ranks as the top #1 open-source model globally, delivering performance comparable to Claude Sonnet 4.5 while costing only about 3.5% as much.

Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs.

by xiaomi262K context$0.09/M input tokens$0.29/M output tokens
Favicon for openai

OpenAI: gpt-oss-120b

413B tokens

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

by openai131K context$0.039/M input tokens$0.19/M output tokens