Every model.
One memory.
Switch between GPT-5.6 Sol, Claude Opus 5, Gemini 3.6 Flash, Llama 4, and 200+ more. your memory follows seamlessly.
// Monday: Use GPT-5.6 Sol
model: "gpt-5.6-sol"
// Tuesday: Try Claude
model: "anthropic/claude-opus-5"
// Wednesday: Test Gemini
model: "google/gemini-3.6-flash"
// Memory persists across all of them No lock-in. No migration. Just change the model parameter.
Supported AI model providers
GPT-5.6 Sol
OpenAI flagship for complex professional reasoning, coding, research, and computer use. 128K max output.
GPT-5.6 Terra
Balanced GPT-5.6 model for everyday production work, with frontier tools and lower cost than Sol.
GPT-5.6 Luna
Fast, cost-efficient GPT-5.6 model for high-volume workflows and multi-step tool use.
GPT-Live-1
OpenAI voice model for natural, continuous conversation with frontier-model delegation for deeper work.
Claude Opus 5
Anthropic premium model for serious coding, long-running agents, and complex professional work.
Claude Sonnet 5
Anthropic's most agentic Sonnet: strong reasoning, browser and terminal use, coding, and knowledge work.
Claude Haiku 4.5
Fast, economical Claude model for responsive assistants and simple tasks at scale.
Gemini 3.6 Flash
Google's stable agentic workhorse for coding, multimodal tasks, spatial reasoning, and rapid tool loops.
Gemini 3.5 Flash
Frontier-speed model for subagents, multi-step workflows, and long-horizon coding tasks.
Gemini 3.5 Flash-Lite
Low-latency, cost-efficient multimodal model for document parsing and high-throughput subagents.
Gemini 3.1 Pro
Google Pro-class reasoning model for advanced knowledge work and multimodal workflows.
Mistral Medium 3.5
128B open-weight multimodal flagship for long-horizon coding, reasoning, and productivity agents.
Mistral Small 4
Apache 2.0 hybrid model unifying instruct, reasoning, multimodal, and agentic coding capabilities.
Mistral OCR 4
Document-intelligence model with bounding boxes, confidence scores, and support for 170 languages.
Grok 4.3
General Grok model for fast chat, reasoning, and tool-heavy agents.
Grok 4.20
High-capability Grok 4 line model available through OpenRouter.
Grok Build 0.1
xAI build-focused model for implementation-heavy agent workflows.
DeepSeek V4 Pro
1.6T-total, 49B-active open model for agentic coding, reasoning, and rich world knowledge.
DeepSeek V4 Flash 0731
Public-beta V4 Flash update with thinking modes, native Responses API support, and Codex optimization.
DeepSeek V4 Flash
284B-total, 13B-active high-throughput model with thinking and non-thinking modes.
Sonar Pro Search
Perplexity search model for grounded answers and web-aware agents.
Sonar Reasoning Pro
Perplexity reasoning model for grounded, multi-step research tasks.
Sonar Deep Research
Deep research model for long-form investigations and synthesis.
200+ More Models
Cohere, Perplexity, Together, and dozens more. If it's on OpenRouter, it works with MemoryRouter.
Ready to Add Memory?
One line change. Same code. Persistent memory across every model.
AI memory infrastructure. Same memory, any model. Stop paying for AI to forget.
Give your AI a memory that lasts.
14 days free. Set up in two minutes. Your AI remembers you from the very next conversation.