Explore LLMs for roleplay, character conversations, and creative writing. Compare model options and API costs to choose a fit for your storytelling or dialogue application.
Featured models include deepseek-v4-flash, DeepSeek V4 Pro, and claude-fable-5, ranked by live weekly usage when available.
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding. deepseek-v4-flash by DeepSeek is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
A frontier reasoning model with a 1M-token window, built for multi-step analysis, repository-scale code review and research workflows — at a fraction of the cost of comparable frontier models. DeepSeek V4 Pro by DeepSeek is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Claude model for creative writing, analysis, and controlled agent workflows. claude-fable-5 by Anthropic is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
deepseek-v3 by DeepSeek is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
deepseek-v3.1 by DeepSeek is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
deepseek-v3.2 by DeepSeek is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
deepseek-v3.2-thinking by DeepSeek is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Fast Gemini workhorse for multimodal apps where latency and price matter. gemini-2.5-flash by Google is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents. gemini-2.5-flash-lite by Google is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs. gemini-3-flash-preview by Google is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Low-latency Gemini model for high-volume multimodal and agent workloads. gemini-3.1-flash-lite by Google is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Fast Gemini model balancing multimodal reasoning, tool use, and cost. gemini-3.5-flash by Google is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Fast Gemini model balancing multimodal reasoning, tool use, and cost. gemini-3.5-flash-lite by Google is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Fast Gemini model balancing multimodal reasoning, tool use, and cost. gemini-3.6-flash by Google is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Mature GLM model for dependable coding, reasoning, and structured agent tasks. glm-4.7 by Z.ai is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
General GLM flagship for coding, analysis, and tool-heavy engineering workflows. glm-5 by Z.ai is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Faster GLM-5 lane for coding agents that need lower latency. glm-5-turbo by Z.ai is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Strong GLM coding model for agentic engineering, terminals, and repository generation. glm-5.1 by Z.ai is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Open flagship GLM for long-horizon coding agents and million-token context work. glm-5.2 by Z.ai is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Flagship GLM model for long-horizon coding, agents, and complex project delivery. glm-5.3 by Z.ai is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Earlier Kimi frontier model for long-context agents, coding, and multimodal work. kimi-k2.5 by Moonshot AI is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context. kimi-k2.6 by Moonshot AI is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Tuned for long-horizon agent work. It holds a full 1M-token context, chains tool calls without losing the thread, and keeps an entire codebase in view across a session. Kimi K3 by Moonshot AI is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
minimax-m2 by MiniMax is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
minimax-m2.5 by MiniMax is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
minimax-m2.7 by MiniMax is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Qwen vision-language model for visual reasoning, documents, and agent tasks. qwen3.5-27b by Alibaba is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Qwen vision-language model for visual reasoning, documents, and agent tasks. qwen3.5-flash by Alibaba (China) is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Qwen vision-language model for visual reasoning, documents, and agent tasks. qwen3.5-plus by Alibaba is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Earlier Qwen multimodal workhorse for million-token agent and document tasks. qwen3.6-plus by Alibaba is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
Multimodal Qwen workhorse for long-context agents, visual inputs, and coding. qwen3.7-plus by Alibaba is available through the Flatkey unified API and is included in our Roleplay & Creative Writing collection. Review its current pricing, context, and availability before integrating it.
