Best models for roleplay (RP) and creative writing
Roleplay and character chat need long memory, consistent tone, and sustainable cost over long sessions. This collection targets Janitor AI, SillyTavern, and creative writing with dialogue-strong models — via Geek Hub.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
 Claude Sonnet 5Anthropic | Chat | 1M tokens | $3.2702/M in · $16.3509/M out |
 Gemini 2.5 ProGoogle | Chat | 2M tokens | $1.3626/M in · $10.9006/M out |
 DeepSeek V4 ProDeepSeek | Chat | 1M tokens | $0.4742/M in · $0.9484/M out |
 Grok 4.5xAI | Chat | 500k tokens | $2.1801/M in · $6.5404/M out |
 Llama 3.3 70B InstructMeta | Chat | 128k tokens | $0.6431/M in · $0.8611/M out |
 Kimi K3Moonshot (Kimi) | Chat | 1M tokens | $3.2702/M in · $16.3509/M out |
 GPT-5.1OpenAI | Chat | 400k tokens | $1.3626/M in · $10.9006/M out |
| Claude Haiku 4.5Anthropic | Chat | 200k tokens | $1.0901/M in · $5.4503/M out |
Why these models
Sonnet and Gemini Pro for character quality; DeepSeek Pro and Llama for budget; Grok and Kimi for a different tone; Haiku when you want cheap message volume.
Use them with Geek Hub
One OpenAI-compatible base URL and API key. Swap any model id from this list without rewriting your client.
Get an API keyFAQ
- Which model for Janitor AI?
- Claude Sonnet 5 or Gemini 2.5 Pro usually give better roleplay. DeepSeek Pro if price wins. See the Janitor AI guide under Apps.
- Does context length matter?
- Yes. Long lore-heavy chats benefit from 200k–1M. Check the context column in the table.
- Are there “uncensored” models?
- Each provider has policies. Geek Hub routes to the model you pick; follow the provider’s and the app’s terms.
